Free Inference
Browse models, API limits and free-tier terms from the Free Inference catalog.
Source catalog date · Last synced
See recent source changes367 listings · 52 providers
Limits and eligibility come from Free Inference. Categories are inferred from source names and descriptions. Confirm current access with the provider.
Synap by Linkrra
Rate-limited free · API key
1 listing
Synap by Linkrra
Rate-limited free · API key
Provider terms reported by Free Inference
Synap provides a no-card free tier for qwen3-coder-30b through an OpenAI-compatible API. Google or email sign-in grants 100,000 tokens and 50 requests per day, with a 10 requests/minute per-key limit. Prompts and completions are not stored or used for training. Allowances reset daily at 00:00 UTC and are limited per account and network address.
- Source provider check
- · Live probe
- Timeout
- Not published
- API base URL
https://synap402.com/v1- Access channel
- web
- Use listed by source
- code
Named models
qwen3-coder-30b
Source cost · $0 (100,000 tokens/day account allowance)Provider-confirmed allowance ·
For the first seven days, up to 100,000 tokens and 50 requests daily. After that, up to 50,000 tokens and 10 requests daily.
View verified access routeLimits reported by Free Inference
- Context
- 98.3K
- Requests/min
- 10
- Tokens/min
- Not published
- Requests/day
- 50
- Tokens/day
- 100,000
Source model check
OpenCode Zen
Promo free (limited time) · API key
16 listings
OpenCode Zen
Promo free (limited time) · API key
Provider terms reported by Free Inference
OpenCode Zen provides a zero-cost promotional tier covering experimental open models across text and vision modalities. Developers authenticate via API key to query high-throughput endpoints directly without upfront billing. Access is bounded by limited-time promotional windows, a zero-data-retention policy, and fair-use concurrency caps.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://opencode.ai/inference/openai/v1- Access channel
- web
- Use listed by source
- code
Named models
Big Pickle
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
Iceman Free
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
Inkling 2 Small Free
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
Crouton Alpha Free
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
GLM-5.3-Flash Free
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
DeepSeek V4.1 Flash Free
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
Beam Free
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
Flint 40B Free
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
MiMo-V2.6-Flash Free
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
Nemotron 3 Ultra Free
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
Nemotron 3.5 Lightning Free
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
Nemotron 3.5 Super VL Free
$0- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
Jev 1.13 Free
Source cost · $0Provider-confirmed allowance ·
Free for a limited time. Numeric request cap not published.
View verified access routeLimits reported by Free Inference
- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
MiniMax M3.1 Flash Free
$0- Context
- 1.0M
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
LongCat 2.5 Free
$0- Context
- 1.0M
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
Hy4 flash Free
$0- Context
- 1M
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- Unknown
Source model check
OpenRouter
Rate-limited free · API key
28 listings
OpenRouter
Rate-limited free · API key
Provider terms reported by Free Inference
OpenRouter offers 13 permanently free models (:free suffix) with 64K–500K context, translating to 50 requests/day (1,000 requests/day with + purchased credits). No credit card required. Upstream model availability determines live rate limits.
- Source provider check
- · Live probe
- Timeout
- Not published
- API base URL
https://openrouter.ai/api/v1- Access channel
- api
- Use listed by source
- code
Named models
cohere/north-mini-code:free
Source cost · $0Provider-confirmed allowance ·
50 requests/day, up to 20/minute. Shared across free models.
View verified access routeLimits reported by Free Inference
- Context
- 250K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
dots-studio/dots-3-note-preview:free
Source cost · $0Provider-confirmed allowance ·
50 requests per day and 20 requests per minute on a free account, shared across :free variants. Failed attempts count toward the daily cap.
View verified access routeLimits reported by Free Inference
- Context
- 500K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
google/gemma-4-26b-a4b-it:free
Source cost · $0Provider-confirmed allowance ·
50 requests/day, up to 20/minute. Shared across free models.
View verified access routeLimits reported by Free Inference
- Context
- 256K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
google/gemma-4-31b-it:free
Source cost · $0Provider-confirmed allowance ·
50 requests/day, up to 20/minute. Shared across free models.
View verified access routeLimits reported by Free Inference
- Context
- 256K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
liquid/lfm-2.5-2.6b:free
$0- Context
- 64K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
liquid/lfm-3-1.7b:free
Source cost · $0Provider-confirmed allowance ·
50 requests/day, up to 20/minute. Shared across free models.
View verified access routeLimits reported by Free Inference
- Context
- 256K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
Source cost · $0Provider-confirmed allowance ·
50 requests/day, up to 20/minute. Shared across free models.
View verified access routeLimits reported by Free Inference
- Context
- 250K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3-ultra-550b-a55b:free
Source cost · $0Provider-confirmed allowance ·
50 requests/day, up to 20/minute. Shared across free models.
View verified access routeLimits reported by Free Inference
- Context
- 1000000
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3.5-lightning:free
Source cost · $0Provider-confirmed allowance ·
50 requests/day, up to 20/minute. Shared across free models.
View verified access routeLimits reported by Free Inference
- Context
- 1000000
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3.5-super-vl:free
Source cost · $0Provider-confirmed allowance ·
50 requests/day, up to 20/minute. Shared across free models.
View verified access routeLimits reported by Free Inference
- Context
- 1000000
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
recursive/flint-v1.0:free
Source cost · $0Provider-confirmed allowance ·
50 requests/day, up to 20/minute. Shared across free models.
View verified access routeLimits reported by Free Inference
- Context
- 256K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
xingchen-agi/xing4.0-29b-a4b:free
$0- Context
- 256K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
meta/muse-spark-1.3-contributor:free
$0- Context
- 1000000
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Crouton Alpha
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Lyria 3 Clip Preview
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Lyria 3 Pro Preview
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Google: Lyria 3 Pro Preview
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Google: Lyria 3 Clip Preview
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Inkling 2 Small (free)
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Thinking Machines: Inkling 2 Small (free)
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Baidu: ERNIE-5.5-Flash-Preview (free)
$0- Context
- 1.0M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
ERNIE-5.5-Flash-Preview (free)
$0- Context
- 1.0M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Particle-1 (free)
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Apodex 1.1 Mini (free)
$0- Context
- 256K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Particle AI: Particle-1 (free)
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
inclusionAI: Ling 3.2 Flash (free)
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Ling 3.2 Flash (free)
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Provider-level or mixed access
Free Models Router
$0Shared pool, tool feature or unspecified model.
- Context
- 195.3K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 50 (below $10 credits) / 1,000 ($10+ credits)
- Tokens/day
- Not published
Source model check
Google AI Studio (Gemini API)
Rate-limited free · API key
16 listings
Google AI Studio (Gemini API)
Rate-limited free · API key
Provider terms reported by Free Inference
Google AI Studio offers 16 free models with up to 1M context. Flagship light models (Gemini 3.5 Flash-Lite, 3.1 Flash-Lite) offer 500 RPD, 15 RPM, and 250K TPM, while open-weight Gemma 4 models (26B, 31B) provide 14.4K RPD, 30 RPM, and 16K TPM. No credit card required. Free-tier prompts and outputs are retained for model training.
- Source provider check
- · Live probe
- Timeout
- Not published
- API base URL
https://generativelanguage.googleapis.com/v1beta/openai/- Access channel
- api
- Use listed by source
- code
Named models
gemini-3.5-flash-lite
$0- Context
- 1024K
- Requests/min
- 15
- Tokens/min
- 250K
- Requests/day
- 500
- Tokens/day
- Not published
Source model check
gemini-3.1-flash-lite
$0- Context
- 1024K
- Requests/min
- 15
- Tokens/min
- 250K
- Requests/day
- 500
- Tokens/day
- Not published
Source model check
gemma-4-26b-a4b-it
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- 16K
- Requests/day
- 14.4K
- Tokens/day
- Not published
Source model check
gemma-4-31b-it
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- 16K
- Requests/day
- 14.4K
- Tokens/day
- Not published
Source model check
gemini-3.5-flash
$0- Context
- 1024K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
gemini-3-flash-preview
$0- Context
- 1024K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
gemini-3.1-flash-lite-preview
$0- Context
- 1024K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
gemini-3.6-flash
$0- Context
- 1024K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
gemini-3.7-flash
$0- Context
- 1024K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
gemini-3.8-flash
$0- Context
- 1024K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
gemini-flash-latest
$0- Context
- 1024K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
gemini-flash-lite-latest
$0- Context
- 1024K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
gemini-2.5-flash
$0- Context
- 1024K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
gemini-2.5-flash-lite
$0- Context
- 1024K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
gemini-omni-1.1-flash
$0- Context
- 128K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
gemini-omni-flash-preview
$0- Context
- 128K
- Requests/min
- Varies by account
- Tokens/min
- Varies by account
- Requests/day
- Varies by account
- Tokens/day
- Not published
Source model check
Groq
Rate-limited free · API key
15 listings
Groq
Rate-limited free · API key
Provider terms reported by Free Inference
Groq offers 13 free models (9 LLMs, 2 Whisper STT, 2 Orpheus TTS), translating to up to 14,400 text requests/day and 2,000 audio transcriptions/day (~8 hours/day). No credit card required. Limits are pooled at organization level.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.groq.com/openai/v1- Access channel
- web
- Use listed by source
- code
Named models
llama-3.3-70b-versatile
$0- Context
- 128K
- Requests/min
- 30
- Tokens/min
- 12K
- Requests/day
- 1,000
- Tokens/day
- 100K tokens/day
Source model check
llama-3.1-8b-instant
$0- Context
- 128K
- Requests/min
- 30
- Tokens/min
- 6K
- Requests/day
- 14,400
- Tokens/day
- 500K tokens/day
Source model check
meta-llama/llama-4-scout-17b-16e-instruct
$0- Context
- 128K
- Requests/min
- 30
- Tokens/min
- 30K
- Requests/day
- 1,000
- Tokens/day
- 500K tokens/day
Source model check
openai/gpt-oss-120b
Source cost · $0Limits reported by Free Inference
- Context
- 128K
- Requests/min
- 30
- Tokens/min
- 8K
- Requests/day
- 1,000
- Tokens/day
- 200K tokens/day
Source model check
openai/gpt-oss-20b
Source cost · $0Provider-confirmed allowance ·
30 requests/min, 1,000 requests/day, 8,000 tokens/min, 200,000 tokens/day.
View verified access routeLimits reported by Free Inference
- Context
- 128K
- Requests/min
- 30
- Tokens/min
- 8K
- Requests/day
- 1,000
- Tokens/day
- 200K tokens/day
Source model check
qwen/qwen3.6-27b
$0- Context
- 128K
- Requests/min
- 30
- Tokens/min
- 8K
- Requests/day
- 1,000
- Tokens/day
- 200K tokens/day
Source model check
qwen/qwen3.8-27b
Source cost · $0Provider-confirmed allowance ·
30 requests/min, 1,000 requests/day, 8,000 tokens/min, 200,000 tokens/day.
View verified access routeLimits reported by Free Inference
- Context
- 128K
- Requests/min
- 30
- Tokens/min
- 8K
- Requests/day
- 1,000
- Tokens/day
- 2M tokens/day
Source model check
meta-llama/llama-prompt-guard-2-22m
Source cost · $0Provider-confirmed allowance ·
30 requests/min, 14,400 requests/day, 15,000 tokens/min, 500,000 tokens/day.
View verified access routeLimits reported by Free Inference
- Context
- 128K
- Requests/min
- 30
- Tokens/min
- 15K
- Requests/day
- 14,400
- Tokens/day
- 500K tokens/day
Source model check
compound-beta
$0- Context
- 128K
- Requests/min
- 30
- Tokens/min
- 70K
- Requests/day
- 250
- Tokens/day
- Not published
Source model check
whisper-large-v3-turbo
Source cost · $0Provider-confirmed allowance ·
20 requests/min, 2,000 requests/day, 7,200 audio seconds/hour, 28,800 audio seconds/day.
View verified access routeLimits reported by Free Inference
- Context
- 25MB audio
- Requests/min
- 20
- Tokens/min
- 7.2K ASH (Audio sec/hr)
- Requests/day
- 2,000
- Tokens/day
- 28.8K ASD (8h audio/day)
Source model check
whisper-large-v3
Source cost · $0Provider-confirmed allowance ·
20 requests/min, 2,000 requests/day, 7,200 audio seconds/hour, 28,800 audio seconds/day.
View verified access routeLimits reported by Free Inference
- Context
- 25MB audio
- Requests/min
- 20
- Tokens/min
- 7.2K ASH (Audio sec/hr)
- Requests/day
- 2,000
- Tokens/day
- 28.8K ASD (8h audio/day)
Source model check
canopylabs/orpheus-v1-english
Source cost · $0Provider-confirmed allowance ·
10 requests/min, 100 requests/day, 1,200 tokens/min, 3,600 tokens/day.
View verified access routeLimits reported by Free Inference
- Context
- Text-to-speech
- Requests/min
- 10
- Tokens/min
- 1.2K ASH (Audio sec/hr)
- Requests/day
- 100
- Tokens/day
- 3.6K ASD (1h audio/day)
Source model check
canopylabs/orpheus-arabic-saudi
Source cost · $0Provider-confirmed allowance ·
10 requests/min, 100 requests/day, 1,200 tokens/min, 3,600 tokens/day.
View verified access routeLimits reported by Free Inference
- Context
- Text-to-speech
- Requests/min
- 10
- Tokens/min
- 1.2K ASH (Audio sec/hr)
- Requests/day
- 100
- Tokens/day
- 3.6K ASD (1h audio/day)
Source model check
ALLaM-2-7b
$0- Context
- 4K
- Requests/min
- 30
- Tokens/min
- 12K
- Requests/day
- 1,000
- Tokens/day
- 100K tokens/day
Source model check
meta-llama/llama-prompt-guard-2-86m
Source cost · $0Provider-confirmed allowance ·
30 requests/min, 14,400 requests/day, 15,000 tokens/min, 500,000 tokens/day.
View verified access routeLimits reported by Free Inference
- Context
- 128K
- Requests/min
- 30
- Tokens/min
- 15K
- Requests/day
- 14,400
- Tokens/day
- 500K tokens/day
Source model check
Cerebras
Trial credits · API key
2 listings
Cerebras
Trial credits · API key
Provider terms reported by Free Inference
Cerebras offers $5 trial credit across 2 models (gpt-oss-120b, qwen-3.8-27b with 8K context cap), translating to 1M tokens/day at 2,000+ tokens/sec. Credit card required. Trial credits expire in 30 days.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.cerebras.ai/v1- Access channel
- web
- Use listed by source
- code
Named models
gpt-oss-120b
$5 trial credits (30-day, card required)- Context
- 8K cap on free tier
- Requests/min
- 5
- Tokens/min
- 30K
- Requests/day
- Not published
- Tokens/day
- 1M tokens/day (per model)
Source model check
qwen-3.8-27b
$5 trial credits (30-day, card required)- Context
- 8K cap on free tier
- Requests/min
- 5
- Tokens/min
- 30K
- Requests/day
- Not published
- Tokens/day
- 1M tokens/day (per model)
Source model check
Cloudflare Workers AI
Rate-limited free · API key
6 listings
Cloudflare Workers AI
Rate-limited free · API key
Provider terms reported by Free Inference
Cloudflare Workers AI is Generally Available with ~80 free models (including Llama 3.3 70B, DeepSeek-R1 distills, Whisper, and FLUX), translating to 10,000 neurons/day (~hundreds of queries or audio minutes). No credit card required. Hard stop at 10,000 neurons until 00:00 UTC daily reset.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.cloudflare.com/client/v4/accounts/%7Baccount_id%7D/ai/v1- Access channel
- web
- Use listed by source
- code
Named models
@cf/meta/llama-3.3-70b-instruct-fp8-fast
Source cost · $0Provider-confirmed allowance ·
10,000 shared Neurons/day. This model uses 26668 neurons per M input tokens; 204805 neurons per M output tokens.
View verified access routeLimits reported by Free Inference
- Context
- 128K
- Requests/min
- 300
- Tokens/min
- Model-dependent
- Requests/day
- Not published
- Tokens/day
- 10,000 neurons/day
Source model check
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b
Source cost · $0Provider-confirmed allowance ·
10,000 shared Neurons/day. This model uses 45170 neurons per M input tokens; 443756 neurons per M output tokens.
View verified access routeLimits reported by Free Inference
- Context
- 128K
- Requests/min
- 300
- Tokens/min
- Model-dependent
- Requests/day
- Not published
- Tokens/day
- 10,000 neurons/day
Source model check
@cf/qwen/qwen2.5-72b-instruct
$0- Context
- 128K
- Requests/min
- 300
- Tokens/min
- Model-dependent
- Requests/day
- Not published
- Tokens/day
- 10,000 neurons/day
Source model check
@cf/meta/llama-3.1-8b-instruct
$0- Context
- 128K
- Requests/min
- 300
- Tokens/min
- Model-dependent
- Requests/day
- Not published
- Tokens/day
- 10,000 neurons/day
Source model check
@cf/openai/whisper
Source cost · $0Provider-confirmed allowance ·
10,000 shared Neurons/day. This model uses 41.14 neurons per audio minute.
View verified access routeLimits reported by Free Inference
- Context
- 25MB audio
- Requests/min
- 300
- Tokens/min
- Model-dependent
- Requests/day
- Not published
- Tokens/day
- 10,000 neurons/day
Source model check
Provider-level or mixed access
~80 free models (Llama 3.x/4, Qwen, Gemma, DeepSeek-R1 distills, FLUX, Whisper, BGE embeddings)
$0Shared pool, tool feature or unspecified model.
- Context
- 8K-128K+ (model-dependent)
- Requests/min
- 300 text gen (720-1,500 other tasks)
- Tokens/min
- Model-dependent
- Requests/day
- Not published
- Tokens/day
- 10,000 neurons/day
Source model check
Mistral La Plateforme
Rate-limited free · API key
3 listings
Mistral La Plateforme
Rate-limited free · API key
Provider terms reported by Free Inference
Mistral provides a rate-limited free tier on La Plateforme for developers evaluating frontier and open models. Access is available via direct API key upon account registration with no credit card required upfront. Usage is bounded by default platform rate limits and standard evaluation terms of service.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.mistral.ai/v1- Access channel
- web
- Use listed by source
- code
Named models
mistral-small-latest
$0- Context
- 128K
- Requests/min
- 60
- Tokens/min
- 500K
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
codestral-latest
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- 300K
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
open-mistral-nemo
$0- Context
- 128K
- Requests/min
- 60
- Tokens/min
- 500K
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
SambaNova Cloud
Trial credits · API key
1 listing
SambaNova Cloud
Trial credits · API key
Provider terms reported by Free Inference
SambaNova Cloud provides a free developer tier with initial pay-as-you-go exploratory credits for ultra-fast SN40L inference. Developers access production open-weights models including Llama 3.3 70B via an OpenAI-compatible endpoint. API keys are generated directly in the developer portal with no credit card required, subject to platform concurrency caps.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.sambanova.ai/v1- Access channel
- api
- Use listed by source
- code
Named models
Meta-Llama-3.3-70B-Instruct
$0 (trial credits)- Context
- unknown
- Requests/min
- unknown
- Tokens/min
- unknown
- Requests/day
- unknown
- Tokens/day
- unknown
Source model check
NVIDIA NIM (build.nvidia.com)
Trial credits · API key
40 listings
NVIDIA NIM (build.nvidia.com)
Trial credits · API key
Provider terms reported by Free Inference
NVIDIA NIM offers 1,000 free trial credits across catalog models (including Nemotron 3.5 Lightning with 1M context), translating to ~40 hours of inference testing. No credit card required; corporate email required for extended credits. Credits tie to a 90-day evaluation window.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://integrate.api.nvidia.com/v1- Access channel
- web
- Use listed by source
- code
Named models
GLM-5
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Kimi-2.5
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
MiniMax-M3.1-Flash
$0 (trial credits)- Context
- 256K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Whisper Large v3
$0 (trial credits)- Context
- 448
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
GPT OSS 20B
$0 (trial credits)- Context
- 128K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Qwen Image
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Qwen Image Edit
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Llama Guard 4 12B
$0 (trial credits)- Context
- 160K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Llama-3.2-90B-Vision-Instruct
$0 (trial credits)- Context
- 125K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Muse Glimmer 30B
$0 (trial credits)- Context
- 128K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Llama 3.2 11b Vision Instruct
$0 (trial credits)- Context
- 125K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Gemma-4-31B-IT
$0 (trial credits)- Context
- 250K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
DiffusionGemma 26B A4B IT
$0 (trial credits)- Context
- 244.1K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
paligemma
$0 (trial credits)- Context
- 125K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
DeepSeek V4.1 Flash
$0 (trial credits)- Context
- 1.0M
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
FLUX.1-dev
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
FLUX.2 Klein 4B
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
FLUX.1-Kontext-dev
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
FLUX.1-schnell
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Laguna XS 2.1
$0 (trial credits)- Context
- 256K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
magpie-tts-zeroshot
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
cosmos-transfer2.5-2b
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
llama-nemotron-embed-vl-1b-v2
$0 (trial credits)- Context
- 8K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Nemotron 3.5 Lightning 30B A3B
$0 (trial credits)- Context
- 256K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Active Speaker Detection
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
llama-nemotron-rerank-vl-1b-v2
$0 (trial credits)- Context
- 10K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Nemotron 3 Ultra 550B A55B
$0 (trial credits)- Context
- 1.0M
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Nemotron 3 Nano Omni
$0 (trial credits)- Context
- 250K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
llama-3.1-nemotron-safety-guard-8b-v3
$0 (trial credits)- Context
- 125K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
nemotron-voicechat
$0 (trial credits)- Context
- 125K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
streampetr
$0 (trial credits)- Context
- 125K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
bevformer
$0 (trial credits)- Context
- 125K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Nemotron 3.5 Content Safety
$0 (trial credits)- Context
- 125K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
sparsedrive
$0 (trial credits)- Context
- 125K
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Nemotron 3.5 Super VL 120B A12B
$0 (trial credits)- Context
- 1M
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
synthetic-video-detector
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
studiovoice
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
GLM-5.3-Flash
$0 (trial credits)- Context
- 1.0M
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Step 5 Preview
$0 (trial credits)- Context
- 1M
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Provider-level or mixed access
NIM-packaged open models
$0 (trial credits)Shared pool, tool feature or unspecified model.
- Context
- Model-dependent
- Requests/min
- ~40
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- ~1,000 credits at signup (up to ~5,000)
Source model check
Z.AI (Zhipu)
Rate-limited free · API key
5 listings
Z.AI (Zhipu)
Rate-limited free · API key
Provider terms reported by Free Inference
Z.AI offers free API access to GLM-5.1, GLM-4.7-Flash, and GLM-4.6V-Flash with 128K context, translating to 15 requests/minute. No credit card required. Shared free tier throttles during peak platform traffic hours.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://open.bigmodel.cn/api/paas/v4/- Access channel
- web
- Use listed by source
- code
Named models
GLM-5.1
$0- Context
- Up to 203K
- Requests/min
- 3 (burst)
- Tokens/min
- Not published
- Requests/day
- 1,000 (1K RPD tier)
- Tokens/day
- Not published
Source model check
GLM-4.5-Flash
$0- Context
- Up to 203K
- Requests/min
- 3 (burst)
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
GLM-4.7-Flash
$0- Context
- Up to 203K
- Requests/min
- 3 (burst)
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
GLM-4.6V-Flash (vision)
$0- Context
- Up to 203K
- Requests/min
- 3 (burst)
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
GLM-4.6V-Flash
$0- Context
- 125K
- Requests/min
- 3 (burst)
- Tokens/min
- Not published
- Requests/day
- 1,000 (1K RPD tier)
- Tokens/day
- Not published
Source model check
DeepInfra
Trial credits · API key
4 listings
DeepInfra
Trial credits · API key
Provider terms reported by Free Inference
DeepInfra offers $5 signup trial credit across 185+ models (including DeepSeek-V3.1, Qwen 3 32B, and GLM-4.7), translating to ~50M tokens at 200 concurrent requests. No credit card required. Credits remain active until depleted.
- Source provider check
- · Live probe
- Timeout
- Not published
- API base URL
https://api.deepinfra.com/v1/openai- Access channel
- api
- Use listed by source
- code
Named models
deepseek-ai/DeepSeek-V3.1
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~60 (varies by model)
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- $5 signup credits
Source model check
Qwen/Qwen3-32B
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~60 (varies by model)
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- $5 signup credits
Source model check
Qwen/Qwen2.5-72B-Instruct
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~60 (varies by model)
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- $5 signup credits
Source model check
zai-org/GLM-4.7
$0 (trial credits)- Context
- Model-dependent
- Requests/min
- ~60 (varies by model)
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- $5 signup credits
Source model check
GitHub Copilot (Free)
Rate-limited free · Account login
1 listing
GitHub Copilot (Free)
Rate-limited free · Account login
Provider terms reported by Free Inference
GitHub provides Copilot Free with limited features for individual developers to try AI-powered coding assistance. The system delivers restricted agent access and limited AI credit allowances alongside Copilot Chat on GitHub.com and mobile. The implementation uses automated web data extraction, HTML table parsing, and policy analysis scripts via bash. Users receive free access subject to specific AI model availability constraints and organization or enterprise policy governance.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- code
Provider-level or mixed access
Auto-selected (GPT-5 mini, Claude Haiku/Sonnet, Gemini Flash line)
$0Shared pool, tool feature or unspecified model.
- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Kiro (AWS)
Rate-limited free · Account login
4 listings
Kiro (AWS)
Rate-limited free · Account login
Provider terms reported by Free Inference
Kiro offers 50 free credits/month for spec-driven agent workflows. Social account or AWS Builder ID required, no credit card required. Unused credits do not roll over to the next month.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- code
Named models
Qwen3 Coder Next
$0- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
DeepSeek 3.2
$0- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
MiniMax M2.1
$0- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Claude Sonnet 4.5
$0- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Trae (ByteDance)
Trial credits · Bundled in tool
1 listing
Trae (ByteDance)
Trial credits · Bundled in tool
Provider terms reported by Free Inference
Trae offers free inference. The free allowance includes 5,000 monthly autocompletions and a one-time $3 usage allowance. Usage is renewed monthly, and the credits are valid for 90 days. The free tier requires no credit card.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- code
Provider-level or mixed access
Frontier models (bundled, auto-selected)
$0 (trial credits)Shared pool, tool feature or unspecified model.
- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Bolt.new
Rate-limited free · Bundled in tool
1 listing
Bolt.new
Rate-limited free · Bundled in tool
Provider terms reported by Free Inference
Bolt offers 1,000,000 tokens per month with a 300,000 daily token cap, translating to bundled frontier model inference for full-stack web and code generation via the Standard agent alongside hosting for up to 333k requests. No credit card required to sign up. Daily tokens reset every 24 hours without rollover, monthly quotas reset on the 1st of each calendar month, and free plan tokens do not roll over.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- app/website
Provider-level or mixed access
Frontier models (bundled, auto-selected)
$0Shared pool, tool feature or unspecified model.
- Context
- Dynamic project context
- Requests/min
- Unspecified
- Tokens/min
- Unspecified
- Requests/day
- Unspecified
- Tokens/day
- 300,000 tokens/day (1,000,000 tokens/month)
Source model check
Lovable
Rate-limited free · Bundled in tool
1 listing
Lovable
Rate-limited free · Bundled in tool
Provider terms reported by Free Inference
Lovable provides a rate-limited free plan for developers building full-stack web applications. Users receive bundled access to frontier models including Fable 5.1 directly within the development workspace without upfront subscription cost. Access is managed through daily workspace credits and standard platform usage limits.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- app/website
Named models
Fable 5.1 (Frontier model)
$0- Context
- Not specified
- Requests/min
- Not specified
- Tokens/min
- Not specified
- Requests/day
- Not specified
- Tokens/day
- Not specified
Source model check
v0 (Vercel)
Rate-limited free · Bundled in tool
7 listings
v0 (Vercel)
Rate-limited free · Bundled in tool
Provider terms reported by Free Inference
v0 offers a free plan granting 7 messages per day with bundled frontier models, plus a one-time $5 credit bonus for new accounts. Translates to 7 full-stack code and UI generations daily (~210 requests per month). No credit card required to sign up and build. Quotas reset daily at 00:00 UTC with no rollover, and custom model selection is restricted to paid plans.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- app/website
Provider-level or mixed access
Frontier models (bundled, auto-selected)
$0Shared pool, tool feature or unspecified model.
- Context
- Text, code, and image/file input
- Requests/min
- unspecified
- Tokens/min
- unspecified
- Requests/day
- 7 requests/day
- Tokens/day
- unspecified
Source model check
Beam 1.0
$0Bundled access. The source says custom model selection requires a paid plan.
- Context
- 1M
- Requests/min
- unspecified
- Tokens/min
- unspecified
- Requests/day
- 7 requests/day
- Tokens/day
- unspecified
Source model check
Beam 1.0 (Free)
$0Bundled access. The source says custom model selection requires a paid plan.
- Context
- 1M
- Requests/min
- unspecified
- Tokens/min
- unspecified
- Requests/day
- 7 requests/day
- Tokens/day
- unspecified
Source model check
Glyph Cluster
$0Bundled access. The source says custom model selection requires a paid plan.
- Context
- 250K
- Requests/min
- unspecified
- Tokens/min
- unspecified
- Requests/day
- 7 requests/day
- Tokens/day
- unspecified
Source model check
Nemotron 3.5 Lightning Free
$0Bundled access. The source says custom model selection requires a paid plan.
- Context
- 1.0M
- Requests/min
- unspecified
- Tokens/min
- unspecified
- Requests/day
- 7 requests/day
- Tokens/day
- unspecified
Source model check
Ampersand v0.1
$0Bundled access. The source says custom model selection requires a paid plan.
- Context
- 1.0M
- Requests/min
- unspecified
- Tokens/min
- unspecified
- Requests/day
- 7 requests/day
- Tokens/day
- unspecified
Source model check
Flint
$0Bundled access. The source says custom model selection requires a paid plan.
- Context
- 256K
- Requests/min
- unspecified
- Tokens/min
- unspecified
- Requests/day
- 7 requests/day
- Tokens/day
- unspecified
Source model check
Kaggle Notebooks
Rate-limited free · Account login
1 listing
Kaggle Notebooks
Rate-limited free · Account login
Provider terms reported by Free Inference
Kaggle offers 30 hours of free GPU accelerator quota (NVIDIA T4 x2 / P100) and 20 hours of TPU v3-8 compute per week, translating to running self-hosted open-weight model inference and fine-tuning across sessions lasting up to 12 hours. Phone verification is required to unlock accelerators and internet access; no credit card required. Compute quota resets weekly, and interactive sessions terminate after 20 to 60 minutes of idle time.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- notebook
Provider-level or mixed access
Open-weight models you load (GPU runtime)
$0Shared pool, tool feature or unspecified model.
- Context
- Model-dependent (16 GB P100 / 2x16 GB T4 VRAM, 29 GB RAM)
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- 30 GPU hours/week (resets weekly)
Source model check
Hugging Face Spaces
Rate-limited free · Account login
2 listings
Hugging Face Spaces
Rate-limited free · Account login
Provider terms reported by Free Inference
Hugging Face Spaces provides 5 minutes of daily ZeroGPU compute on dynamic NVIDIA RTX Pro 6000 Blackwell GPUs (48 GB to 96 GB VRAM) along with free hosting for up to 2 Gradio Spaces. This allows users to deploy and run inference on any compatible Hugging Face model across text, vision, audio, and multimodal tasks with execution limits of 60 to 120 seconds per function call. Access requires creating and logging into a free Hugging Face account with a verified email address, with no credit card required. The 5-minute GPU quota resets 24 hours after the first GPU usage, spaces auto-sleep when inactive, and hosting personal ZeroGPU demos requires an account older than 30 days in good standing.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- app/agent
Named models
GLM-4.7-Flash
$0- Context
- 195.3K
- Requests/min
- Rate-limited (queue-based)
- Tokens/min
- Not specified
- Requests/day
- Not specified
- Tokens/day
- 5 minutes GPU time / day
Source model check
Provider-level or mixed access
Any Hugging Face model you load (ZeroGPU)
$0Shared pool, tool feature or unspecified model.
- Context
- Model-dependent (up to 96 GB VRAM; 60s default / 120s max GPU duration per call)
- Requests/min
- Rate-limited (queue-based)
- Tokens/min
- Not specified
- Requests/day
- Not specified
- Tokens/day
- 5 minutes GPU time / day
Source model check
Cursor (Hobby)
Rate-limited free · Bundled in tool
1 listing
Cursor (Hobby)
Rate-limited free · Bundled in tool
Provider terms reported by Free Inference
Cursor provides a complimentary Hobby tier for developers evaluating AI-assisted code editing. Users access bundled agent and inline chat completions directly within the IDE without an upfront subscription. Free access is subject to monthly request allowances and rate limits defined in the editor settings.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- code
Provider-level or mixed access
Cursor Free Models (Agent/Chat)
$0Shared pool, tool feature or unspecified model.
- Context
- Not specified
- Requests/min
- Rate-limited
- Tokens/min
- Rate-limited
- Requests/day
- Rate-limited
- Tokens/day
- Rate-limited
Source model check
Windsurf
Rate-limited free · Bundled in tool
1 listing
Windsurf
Rate-limited free · Bundled in tool
Provider terms reported by Free Inference
Windsurf provides a free tier. Users receive a set amount of usage and standard features at no cost. The free tier operates on a rate-limited basis. Usage allowances reset periodically under standard usage conditions.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- code
Provider-level or mixed access
Standard Models
$0Shared pool, tool feature or unspecified model.
- Context
- Standard
- Requests/min
- Not specified
- Tokens/min
- Not specified
- Requests/day
- Not specified
- Tokens/day
- Not specified
Source model check
Devin (Free)
Rate-limited free · Bundled in tool
2 listings
Devin (Free)
Rate-limited free · Bundled in tool
Provider terms reported by Free Inference
Devin offers a Free plan with a light quota to code with agents, free use of SWE-2, unlimited inline edits, and unlimited Tab completions. Account login required, no credit card required. Runs bundled inside the Devin interface on SWE-2 and limited models.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- code
Named models
SWE-2 (Free)
$0- Context
- Not published
- Requests/min
- Light quota
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Provider-level or mixed access
Limited models (auto-selected)
$0Shared pool, tool feature or unspecified model.
- Context
- Not published
- Requests/min
- Light quota
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Qoder
Rate-limited free · Bundled in tool
1 listing
Qoder
Rate-limited free · Bundled in tool
Provider terms reported by Free Inference
Qoder offers free basic code autocompletions and limited Next-Edit-Suggestion (NES) runs. Account login required, no credit card required. Unlimited usage requires bringing your own API keys.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- code
Provider-level or mixed access
Frontier models + BYO key
$0Shared pool, tool feature or unspecified model.
- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Antigravity CLI (Google)
Rate-limited free · Account login
4 listings
Antigravity CLI (Google)
Rate-limited free · Account login
Provider terms reported by Free Inference
Antigravity CLI provides free developer inference for base and multimodal foundation models. Users run text, code, and reasoning tasks through local CLI and terminal workflows. Authentication is handled directly via Google account login without requiring a payment instrument, subject to dynamic request rate limits.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- code/agent
Named models
Gemini 3.8 Flash
$0- Context
- Standard
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
Gemini 3.7 Flash
$0- Context
- Standard
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
Gemini 3.6 Flash
$0- Context
- Standard
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
Gemini 3.1 Pro
$0- Context
- Standard
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
Google Colab
Rate-limited free · Account login
5 listings
Google Colab
Rate-limited free · Account login
Provider terms reported by Free Inference
Google Colab offers free access to hosted Jupyter notebook compute resources including shared GPUs/TPUs and integrated Gemini AI coding features, translating to interactive execution sessions of up to 12 hours with standard system memory. Google account login required (age 18+ for AI features), no credit card required. Resources and rate limits fluctuate dynamically, idle runtimes disconnect, and non-interactive background execution is disallowed.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- notebook
Named models
Lyria 3 Clip Preview
$0- Context
- 1M
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Lyria 3 Pro Preview
$0- Context
- 1M
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Gemma 4 31B IT
$0- Context
- 256K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Gemma 4 26B A4B IT
$0- Context
- 256K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Provider-level or mixed access
Gemini (AI features) + GPU for your code
$0Shared pool, tool feature or unspecified model.
- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Figma (Starter)
Rate-limited free · Bundled in tool
1 listing
Figma (Starter)
Rate-limited free · Bundled in tool
Provider terms reported by Free Inference
Figma Starter offers 150 free AI generation credits/day (up to 500/month). Figma account required, no credit card required. Inference runs bundled inside Figma design files for layer generation and text editing.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- design/prototype/site
Provider-level or mixed access
Figma AI, Make, agent
$0Shared pool, tool feature or unspecified model.
- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Canva (Free)
Rate-limited free · Bundled in tool
2 listings
Canva (Free)
Rate-limited free · Bundled in tool
Provider terms reported by Free Inference
Canva provides free users with a recurring monthly allowance of 20 generations across standard AI creative tools. Users access bundled Magic Media and text generation features directly within the design canvas without a paid plan. Free usage consumes a shared monthly credit pool and excludes premium enterprise AI tools.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- design
Provider-level or mixed access
Canva AI
$0Shared pool, tool feature or unspecified model.
- Context
- unknown
- Requests/min
- unknown
- Tokens/min
- unknown
- Requests/day
- 20 uses (monthly shared limit)
- Tokens/day
- unknown
Source model check
Magic Media
$0Shared pool, tool feature or unspecified model.
- Context
- unknown
- Requests/min
- unknown
- Tokens/min
- unknown
- Requests/day
- 20 uses (monthly shared limit)
- Tokens/day
- unknown
Source model check
Framer (Free)
Trial credits · Bundled in tool
1 listing
Framer (Free)
Trial credits · Bundled in tool
Provider terms reported by Free Inference
Framer offers 500 one-time AI trial credits on its Free plan for workspaces without active subscriptions to power Framer Agents, translating to approximately 1 to 3 page generation or design sessions. No credit card is required to sign up and use the free plan. Credits are a one-time trial allotment that does not reset monthly, and agent features pause once the credits are exhausted unless upgraded to a paid plan.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- website
Provider-level or mixed access
Framer Agents
$0 (trial credits)Shared pool, tool feature or unspecified model.
- Context
- Canvas-native web design, layout, styling, CMS, and copy generation
- Requests/min
- Not specified
- Tokens/min
- Not specified
- Requests/day
- Not specified
- Tokens/day
- 500 credits (one-time trial)
Source model check
Replit (Starter)
Rate-limited free · Bundled in tool
1 listing
Replit (Starter)
Rate-limited free · Bundled in tool
Provider terms reported by Free Inference
Replit provides a free Starter tier for developers prototyping and deploying cloud software. Users gain access to standard workspace environments with bundled AI assistance features. Accounts are created instantly with email or GitHub without entering billing details, subject to shared CPU and memory limits.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Access channel
- web
- Use listed by source
- app/website
Provider-level or mixed access
Frontier models (bundled, auto-selected)
$0Shared pool, tool feature or unspecified model.
- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Kilo Gateway
Rate-limited free · API key
28 listings
Kilo Gateway
Rate-limited free · API key
Provider terms reported by Free Inference
Kilo Gateway offers 7 free models with 64K–256K context, translating to 200 requests/hour per IP address. No credit card required. Model availability reflects upstream provider quotas.
- Source provider check
- · Live probe
- Timeout
- Not published
- API base URL
https://api.kilo.ai/v1- Access channel
- api
- Use listed by source
- code
Named models
cohere/north-mini-code:free
$0- Context
- 250K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
poolside/laguna-s-2.1:free
$0- Context
- 256K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
poolside/laguna-xs-2.1:free
$0- Context
- 256K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
liquid/lfm-2.5-2.6b:free
$0- Context
- 64K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
dots-studio/dots-3-note-preview:free
$0- Context
- 500K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3.5-lightning:free
$0- Context
- 1000000
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3.5-super-vl:free
$0- Context
- 1000000
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Reflection: Beam 1.0 (free)
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Crouton Alpha
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Stealth: Glyph Cluster (free)
$0- Context
- 250K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Lyria 3 Clip Preview
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Lyria 3 Pro Preview
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
LiquidAI: LFM3-1.7B (free)
$0- Context
- 256K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
NVIDIA: Nemotron 3 Nano Omni (free)
$0- Context
- 250K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
NVIDIA: Nemotron 3 Ultra (free)
$0- Context
- 1.0M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Body Builder (beta)
$0- Context
- 125K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Thinking Machines: Inkling 2 Small (free)
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Baidu: ERNIE-5.5-Flash-Preview (free)
$0- Context
- 1.0M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Glyph Cluster
$0- Context
- 250K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Ampersand v0.1
$0- Context
- 1.0M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Particle AI: Particle-1 (free)
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Apodex: Apodex 1.1 Mini (free)
$0- Context
- 256K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
inclusionAI: Ling 3.2 Flash (free)
$0- Context
- 1M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Recursive: Flint
$0- Context
- 256K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Provider-level or mixed access
Auto Free
$0Shared pool, tool feature or unspecified model.
- Context
- 250K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
OpenRouter Free Models Router
$0Shared pool, tool feature or unspecified model.
- Context
- 195.3K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Pareto Code Router
$0Shared pool, tool feature or unspecified model.
- Context
- 195.3K
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Auto Router
$0Shared pool, tool feature or unspecified model.
- Context
- 1.9M
- Requests/min
- 20
- Tokens/min
- Provider-dependent
- Requests/day
- 200/day
- Tokens/day
- Not published
Source model check
Nous Portal
Rate-limited free · API key
6 listings
Nous Portal
Rate-limited free · API key
Provider terms reported by Free Inference
Nous Portal offers 5 free Hermes and open-weight models, translating to 50 requests/minute and 500,000 tokens/minute. Free account registration required, no credit card required. Preview models may be adjusted during experimental rounds.
- Source provider check
- · Live probe
- Timeout
- Not published
- API base URL
https://inference-api.nousresearch.com/v1- Access channel
- api
- Use listed by source
- code
Named models
poolside/laguna-s-2.1:free
$0- Context
- 256K
- Requests/min
- 50
- Tokens/min
- 500K
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
poolside/laguna-xs-2.1:free
$0- Context
- 256K
- Requests/min
- 50
- Tokens/min
- 500K
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
stepfun/step-3.7-flash:free
$0- Context
- 128K
- Requests/min
- 50
- Tokens/min
- 500K
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
upstage/solar-mini4:free
$0- Context
- 64K
- Requests/min
- 50
- Tokens/min
- 500K
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
reflection/beam-1.0-501b-a23b:free
$0- Context
- 128K
- Requests/min
- 50
- Tokens/min
- 500K
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
ornith/ornith-1.5-122b:free
$0- Context
- 128K
- Requests/min
- 50
- Tokens/min
- 500K
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Cohere
Rate-limited free · API key
7 listings
Cohere
Rate-limited free · API key
Provider terms reported by Free Inference
Cohere provides free trial API keys for developers building with Command A and embedding models. Users register an account to instantly retrieve trial credentials without entering a payment method. Usage is bounded by trial rate limits of 20 requests per minute and 1,000 API calls per month.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.cohere.com/v1- Access channel
- web
- Use listed by source
- code
Named models
Command A+
Source cost · $0Provider-confirmed allowance ·
Up to 20 requests per minute for this model and 1,000 API calls per month across models on the trial key.
View verified access routeLimits reported by Free Inference
- Context
- N/A
- Requests/min
- 20
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
Command A Reasoning
Source cost · $0Provider-confirmed allowance ·
Up to 20 requests per minute for this model and 1,000 API calls per month across models on the trial key.
View verified access routeLimits reported by Free Inference
- Context
- N/A
- Requests/min
- 20
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
Command R+
Source cost · $0Provider-confirmed allowance ·
Up to 20 requests per minute for this model and 1,000 API calls per month across models on the trial key.
View verified access routeLimits reported by Free Inference
- Context
- N/A
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
Command R
Source cost · $0Provider-confirmed allowance ·
Up to 20 requests per minute for this model and 1,000 API calls per month across models on the trial key.
View verified access routeLimits reported by Free Inference
- Context
- N/A
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
Command R7B
Source cost · $0Provider-confirmed allowance ·
Up to 20 requests per minute for this model and 1,000 API calls per month across models on the trial key.
View verified access routeLimits reported by Free Inference
- Context
- N/A
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
North Small Translate
Source cost · $0Provider-confirmed allowance ·
Up to 1,000 API calls per month across models on the trial key.
View verified access routeLimits reported by Free Inference
- Context
- 32K
- Requests/min
- 20
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
North Mini Code
Source cost · $0Provider-confirmed allowance ·
Up to 20 requests per minute for this model and 1,000 API calls per month across models on the trial key.
View verified access routeLimits reported by Free Inference
- Context
- 250K
- Requests/min
- 20
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
Requesty
Rate-limited free · API key
13 listings
Requesty
Rate-limited free · API key
Provider terms reported by Free Inference
Requesty offers 3 free models with 128K context, translating to 200 requests/day per account. Email registration required, no credit card required. Quota resets daily at 00:00 UTC.
- Source provider check
- · Live probe
- Timeout
- Not published
- API base URL
https://router.requesty.ai/v1- Access channel
- api
- Use listed by source
- code
Named models
nvidia/nemotron-3-super-120b-a12b
$0- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
google/gemma-4-31b-it
$0- Context
- 256K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
poolside/laguna-xs.2
$0- Context
- 256K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
Gemma 4 31B IT
$0- Context
- 256K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
ling-3.0-tiny
$0- Context
- 256K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
Muse Glimmer 30B
$0- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
Nemotron 3.5 Lightning 30B A3B
$0- Context
- 1M
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
leanstral-1-5
$0- Context
- 256K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
Nemotron 3 Ultra 550B A55B
$0- Context
- 1M
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
Nemotron 3 Nano Omni 30B A3B Reasoning
$0- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
leanstral-1-5@eu
$0- Context
- 256K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
Nemotron 3 Super 120B A12B
$0- Context
- 1M
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
Nemotron 3.5 Content Safety
$0- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- 200/day shared
- Tokens/day
- Not published
Source model check
OVHcloud AI Endpoints
Rate-limited free · API key
3 listings
OVHcloud AI Endpoints
Rate-limited free · API key
Provider terms reported by Free Inference
OVHcloud offers 10 free open-source models, translating to 2 requests/minute per IP keyless (or 400 requests/minute with a registered account). No credit card required for anonymous keyless access. Quota is enforced per client IP.
- Source provider check
- · Live probe
- Timeout
- Not published
- API base URL
https://endpoints.ai.cloud.ovh.net/v1- Access channel
- api
- Use listed by source
- code
Named models
Qwen3Guard-Gen-0.6B
$0- Context
- 32K
- Requests/min
- 2/min per IP
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Qwen3Guard-Gen-8B
$0- Context
- 32K
- Requests/min
- 2/min per IP
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Provider-level or mixed access
10 free models (anonymous keyless)
$0Shared pool, tool feature or unspecified model.
- Context
- Model-dependent
- Requests/min
- 2/min per IP
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
SiliconFlow
Trial credits · API key
1 listing
SiliconFlow
Trial credits · API key
Provider terms reported by Free Inference
SiliconFlow provides $200 in free trial credits upon developer account registration. Credits can be applied across speech, text, and multimodal open-source models through an OpenAI-compatible API. Users create an account to generate API keys with no credit card required, with credits remaining valid for 90 days.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.siliconflow.cn/v1- Access channel
- web
- Use listed by source
- code
Provider-level or mixed access
Speech models (unspecified)
$0 (trial credits)Shared pool, tool feature or unspecified model.
- Context
- 43,000 minutes or 700+ hours
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
DeepSeek Platform
Trial credits · API key
2 listings
DeepSeek Platform
Trial credits · API key
Provider terms reported by Free Inference
DeepSeek offers an initial free grant balance upon developer account registration. Users access production deepseek-chat and deepseek-reasoner endpoints via OpenAI-compatible APIs without immediate paid top-ups. The platform automatically exhausts the granted balance first before requiring paid credits or subscription upgrades.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.deepseek.com/v1- Access channel
- web
- Use listed by source
- code
Named models
deepseek-chat
$0 (5M signup tokens)- Context
- 64K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- 5M tokens grant
Source model check
deepseek-reasoner
$0 (5M signup tokens)- Context
- 64K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- 5M tokens grant
Source model check
Braintrust
Trial credits · API key
13 listings
Braintrust
Trial credits · API key
Provider terms reported by Free Inference
Braintrust offers $10/month recurring model credit on Starter across 13 built-in models (including GPT-6 series, DeepSeek V4.1, GLM-5.3, and Jev). Work email required, no credit card required. Model credit resets monthly with no rollover.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.braintrust.dev/v1/proxy- Access channel
- web
- Use listed by source
- code
Named models
deepseek-v4.1-flash
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
deepseek-v4-flash-0731
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
glm-5.3-flash
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
glm-5.2
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
kimi-k3
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
jev
$0 ($10/mo model credits)- Context
- 256K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
gpt-6-luna
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
gpt-6-sol
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
gpt-6.1-sol
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
gpt-6-astra
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
gpt-5.6-luna
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
gpt-5.6-terra
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
gpt-5.6-sol
$0 ($10/mo model credits)- Context
- 128K
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Deepgram
Trial credits · API key
4 listings
Deepgram
Trial credits · API key
Provider terms reported by Free Inference
Deepgram provides $200 in free trial credits upon registration, unlocking public speech-to-text and text-to-speech models including Nova-3, Flux, and Aura. Developers register an account to obtain an API key with no credit card required upfront. The allowance yields roughly 700 hours of audio transcription, subject to a 90-day expiry window and standard streaming concurrency caps.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.deepgram.com/v1- Access channel
- web
- Use listed by source
- code
Named models
nova-3
Source cost · $0 (trial credits)Provider-confirmed allowance ·
$200 in free signup credit shared across Deepgram services.
View verified access routeLimits reported by Free Inference
- Context
- N/A
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
nova-2
Source cost · $0 (trial credits)Provider-confirmed allowance ·
$200 in free signup credit shared across Deepgram services.
View verified access routeLimits reported by Free Inference
- Context
- N/A
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
flux
$0 (trial credits)- Context
- N/A
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
aura
$0 (trial credits)- Context
- N/A
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
AssemblyAI
Trial credits · API key
1 listing
AssemblyAI
Trial credits · API key
Provider terms reported by Free Inference
New accounts receive $50 in credits, valid for 90 days, usable across four speech models, and requiring no credit card.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.assemblyai.com/v2- Access channel
- web
- Use listed by source
- code
Provider-level or mixed access
Unknown
$0 (trial credits)Shared pool, tool feature or unspecified model.
- Context
- Unknown
- Requests/min
- Unknown
- Tokens/min
- Unknown
- Requests/day
- Unknown
- Tokens/day
- 43000 minutes
Source model check
Dots Studio
Trial credits · API key
1 listing
Dots Studio
Trial credits · API key
Provider terms reported by Free Inference
Dots Studio provides a developer trial credit system for querying its proprietary reasoning preview models. Developers access the dots-3-note-preview model via direct API key integration without upfront billing. Requests are constrained by a 524,288 token context window limit and trial usage quotas.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://api.dots.ai/v1- Access channel
- web
- Use listed by source
- code
Named models
dots-3-note-preview
$0 (trial credits)- Context
- 524288
- Requests/min
- N/A
- Tokens/min
- N/A
- Requests/day
- N/A
- Tokens/day
- N/A
Source model check
Liquid AI
Trial credits · API key
1 listing
Liquid AI
Trial credits · API key
Provider terms reported by Free Inference
Liquid AI provides promotional developer API credits upon registration in the Liquid developer console. Users evaluate liquid foundation models via OpenAI-compatible completion endpoints. Access is provisioned upon account creation at console.liquid.ai without upfront card requirements, subject to promotional credit balance limits.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://console.liquid.ai/- Access channel
- web
- Use listed by source
- code
Provider-level or mixed access
Liquid AI Free Model
$0 (trial)Shared pool, tool feature or unspecified model.
- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Speka
Permanent $0 · API key
27 listings
Speka
Permanent $0 · API key
Provider terms reported by Free Inference
Speka provides a recurring $1.00 monthly credit allowance that resets on the first of each month. Developers query all open catalog models (DeepSeek, Llama 3.2) via an OpenAI-compatible endpoint with a single API key created at signup without a credit card. Usage is capped at 10 RPM and billed at standard per-token rates, returning HTTP 402 once exhausted until the next monthly refresh.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- API base URL
https://speka.me/v1- Access channel
- web
- Use listed by source
- code
Named models
deepseek-ai/deepseek-v4-flash
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
deepseek-ai/deepseek-v4-pro
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
meta/llama-3.1-8b-instruct
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
meta/llama-3.2-3b-instruct
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
meta/llama-3.2-11b-vision-instruct
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
meta/llama-3.2-90b-vision-instruct
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
meta/llama-3.3-70b-instruct
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
mistralai/mistral-nemotron
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
mistralai/mistral-medium-3.5-128b
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
mistralai/mistral-large-4-1t-a52b
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3-nano-30b-a3b
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3-super-120b-a12b
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3-ultra-550b-a55b
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3.5-bolt-e4b
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3.5-lightning-30b-a3b
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
nvidia/nemotron-3-embed-1b
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
nvidia/nemotron-nano-9b-v2
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
nvidia/nemotron-nano-12b-v2-vl
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
nvidia/llama-3.3-nemotron-super-49b-v1.5
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
openai/gpt-oss-20b
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
openai/gpt-oss-120b
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
poolside/laguna-xs-2.1
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
stepfun-ai/step-3.7-flash
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
stepfun-ai/step-5-preview
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
minimaxai/minimax-m3
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
z-ai/glm-5.2
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
black-forest-labs/flux.1-dev
$0 (monthly credit allowance)- Context
- Model-dependent
- Requests/min
- Published on portal
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Alibaba DashScope (Bailian)
Trial / Free tokens · API key
21 listings
Alibaba DashScope (Bailian)
Trial / Free tokens · API key
Provider terms reported by Free Inference
Alibaba Cloud Model Studio (Bailian/DashScope) provides free token allotments upon account activation across its Qwen and DeepSeek model fleet. Developers access high-throughput OpenAI-compatible endpoints with up to 1M token context windows. API keys are generated in the Model Studio console after account registration, with promotional free tokens valid during designated trial windows.
- Source provider check
- · Provider documentation
- Timeout
- 300s
- API base URL
https://dashscope.aliyuncs.com/compatible-mode/v1- Access channel
- web
- Use listed by source
- code
Named models
Qwen3.7 Plus
$0 (promo free tokens)- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
DeepSeek V4.1 Flash 1017
$0 (promo free tokens)- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
GLM-5.3
$0 (promo free tokens)- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Qwen3.6 Plus
$0 (promo free tokens)- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Wan2.7 Image
$0 (promo free tokens)- Context
- 8K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
HappyHorse 1.1 Reference-to-Video
$0 (promo free tokens)- Context
- Model-dependent
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Qwen3.6 Flash
$0 (promo free tokens)- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Qwen3.7 Max
$0 (promo free tokens)- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
DeepSeek V4 Pro
$0 (promo free tokens)- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
MiniMax-M2.5
$0 (promo free tokens)- Context
- 192K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Kimi K2.6
$0 (promo free tokens)- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Kimi K2.5
$0 (promo free tokens)- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Kimi K2.7 Code
$0 (promo free tokens)- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
HappyHorse 1.1 Text-to-Video
$0 (promo free tokens)- Context
- Model-dependent
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Qwen Image 2.0
$0 (promo free tokens)- Context
- 8K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Wan2.7 Image Pro
$0 (promo free tokens)- Context
- 8K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
HappyHorse 1.1 Image-to-Video
$0 (promo free tokens)- Context
- Model-dependent
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
DeepSeek V4 Pro 0813
$0 (promo free tokens)- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Qwen3.8 Flash
$0 (promo free tokens)- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Qwen3.8 Max
$0 (promo free tokens)- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
Qwen Image 2.0 Pro
$0 (promo free tokens)- Context
- 8K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- Free tier token grant
- Tokens/day
- Not published
Source model check
ModelScope
Rate-limited free · API key
7 listings
ModelScope
Rate-limited free · API key
Provider terms reported by Free Inference
ModelScope (Alibaba's open-source model community) offers free hosted inference for community and Qwen open-weights models. Users query standard OpenAI-compatible completion endpoints with context windows up to 262K tokens. Access is activated by creating a ModelScope account to retrieve an API access token, subject to fair-share community queuing and rate limits.
- Source provider check
- · API check
- Timeout
- 180s
- API base URL
https://api-inference.modelscope.cn/v1- Access channel
- web
- Use listed by source
- code
Named models
Qwen3 30B A3B Thinking 2507
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 500
- Tokens/day
- Not published
Source model check
Qwen3 235B A22B Instruct 2507
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 500
- Tokens/day
- Not published
Source model check
Qwen3 30B A3B Instruct 2507
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 500
- Tokens/day
- Not published
Source model check
Qwen3-235B-A22B-Thinking-2507
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 500
- Tokens/day
- Not published
Source model check
Qwen3 Coder 30B A3B Instruct
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 500
- Tokens/day
- Not published
Source model check
GLM-4.5
$0- Context
- 128K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 500
- Tokens/day
- Not published
Source model check
GLM-4.6
$0- Context
- 198K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 500
- Tokens/day
- Not published
Source model check
AMD Developer Cloud
Free Developer Tier · API key
10 listings
AMD Developer Cloud
Free Developer Tier · API key
Provider terms reported by Free Inference
AMD Developer Cloud provides free inference access to open frontier models running on AMD Instinct ROCm GPU clusters. Developers query OpenAI-compatible chat endpoints supporting DeepSeek, Qwen, and MiniCPM variants. Access is provisioned by registering an AMD Developer account to reach the API console, subject to cluster capacity and fair-use developer quotas.
- Source provider check
- · API check
- Timeout
- 120s
- API base URL
https://cloud.amd.com/api/v1- Access channel
- web
- Use listed by source
- code
Named models
MiniCPM5-2B
$0- Context
- 128K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Qwen3.8 Flash Next
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
DeepSeek V4 Flash 0731
$0- Context
- 1M
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
MiniCPM-V 4.7 1B
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
MiniCPM-V 4.7 35B-A3B
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Qwen3.8 27B
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
MiMo-V2.6-Flash
$0- Context
- 1M
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
DeepSeek V4.1 Flash
$0- Context
- 1M
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Gemma 4 31B IT
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
GLM-5.3-Flash
$0- Context
- 256K
- Requests/min
- 30
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
InferX
Free Developer Tier · API key
12 listings
InferX
Free Developer Tier · API key
Provider terms reported by Free Inference
InferX provides zero-cost inference endpoints for open models including Qwen 3.6, Gemma 4, and DeepSeek variants. Developers access low-latency OpenAI-compatible completions with streaming and structured output support. Keys are provisioned instantly upon user sign-in without upfront payment, subject to community prototyping rate limits.
- Source provider check
- · API check
- Timeout
- 120s
- API base URL
https://model.inferx.net/endpoints/v1- Access channel
- web
- Use listed by source
- code
Named models
Qwen3.6 35B A3B FP8
$0- Context
- 255.9K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
deepseek-v4-flash
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
Ornith-1.0-35B-FP8
$0- Context
- 255.9K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
Qwen3.6 27B FP8
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
mimo-v25
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
Qwen3 Coder Next FP8
$0- Context
- 250.1K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
Agents-A1
$0- Context
- 255.9K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
Devstral-2-123B-Instruct-2512-int4-AutoRound
$0- Context
- 125K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
Qwen3-Embedding-8B
$0- Context
- 32K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
Qwen3.6-35B-A3B-fp8-no-thinking
$0- Context
- 255.9K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
Gemma 4 31B IT FP8
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
Qwen3-Coder-Next-FP8-no-thinking
$0- Context
- 253.9K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 2,000
- Tokens/day
- Not published
Source model check
Kimi For Coding (Moonshot AI)
Free Developer Tier · API key
6 listings
Kimi For Coding (Moonshot AI)
Free Developer Tier · API key
Provider terms reported by Free Inference
Moonshot AI provides free developer inference for Kimi K3 and coding models with context windows up to 1M tokens. Developers query OpenAI-compatible coding endpoints supporting deep reasoning and agentic workflows. Credentials are retrieved via the Kimi coding portal, subject to community rate limits and peak-period concurrency throttling.
- Source provider check
- · Provider documentation
- Timeout
- 180s
- API base URL
https://api.kimi.ai/coding/v1- Access channel
- web
- Use listed by source
- code
Named models
Kimi K3.1 Pro Highspeed
$0- Context
- 1M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Kimi K3-256K
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Kimi K3.1 Pro
$0- Context
- 1M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Kimi K3
$0- Context
- 1M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
kimi-for-coding
$0- Context
- 1M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Kimi For Coding HighSpeed
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
SCNet
Free Developer Tier · API key
12 listings
SCNet
Free Developer Tier · API key
Provider terms reported by Free Inference
SCNet provides national high-performance computing open inference tokens for domestic LLMs including Qwen 3.8 and DeepSeek V4 Flash. Developers access OpenAI-compatible chat endpoints with up to 1M token context windows. Registration on the SCNet developer portal provisions API keys upon identity verification, subject to national computing quota rules.
- Source provider check
- · Provider documentation
- Timeout
- 180s
- API base URL
https://api.scnet.cn/v1- Access channel
- web
- Use listed by source
- code
Named models
Kimi K2.7 Code
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Qwen3.8 Flash
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
MiniMax-M2.5
$0- Context
- 200K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
DeepSeek V4 Flash
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
DeepSeek V4 Pro 0813
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
GLM-5.3
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
MiniMax-M3
$0- Context
- 1M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
MiniMax-M2.7
$0- Context
- 200K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Qwen3.8 Max
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
DeepSeek V4 Pro
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Kimi K2.6
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Kimi K2.5
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
AIHubMix
Promo free · API key
16 listings
AIHubMix
Promo free · API key
Provider terms reported by Free Inference
AIHubMix provides a suite of zero-cost promotional models including GLM-4.7 Flash, Nemotron 3 Ultra, and Qwen 3.8 Max. Developers query OpenAI-compatible completion endpoints with long context support up to 1M tokens. Free API credentials are generated upon account signup without credit cards, subject to promotional token availability and rate limits.
- Source provider check
- · API check
- Timeout
- 120s
- API base URL
https://api.aihubmix.com/v1- Access channel
- web
- Use listed by source
- code
Named models
GLM-4.7-Flash (free)
$0- Context
- 195.3K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Nemotron 3 Ultra 550B A55B (free)
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Nemotron 3.5 Content Safety (free)
$0- Context
- 125K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Qwen3.8 Max (free)
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
GLM-5.2 (Coding, free)
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Ling 3.0 Flash (free)
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Coding MiniMax M2.7 (Free)
$0- Context
- 200K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Nemotron 3.5 Lightning 30B A3B (free)
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
GLM-5.3 (Coding, free)
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Qwen3.8 Flash (free)
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Nemotron 3 Nano Omni 30B A3B Reasoning (free)
$0- Context
- 250K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Coding GLM 5.1 (free)
$0- Context
- 195.3K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
GLM-5.3-Flash (Coding, free)
$0- Context
- 1.0M
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Nemotron 3 Super 120B A12B (free)
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Gemma 4 31B IT (free)
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Gemma 4 26B A4B IT (free)
$0- Context
- 256K
- Requests/min
- 60
- Tokens/min
- Not published
- Requests/day
- 1,000
- Tokens/day
- Not published
Source model check
Secondary providers
Poe
Rate-limited free · Account login
1 listing
Poe
Rate-limited free · Account login
Provider terms reported by Free Inference
Free daily points reset every 24h with no rollover; the number is unpublished. Frontier models resold; login required, no card.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Use listed by source
- agent/bot
Provider-level or mixed access
Frontier models (resale, auto-selected)
$0Listed by Free Inference as a secondary provider.
- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Dify Cloud (Sandbox)
Trial credits · Account login
1 listing
Dify Cloud (Sandbox)
Trial credits · Account login
Provider terms reported by Free Inference
Sandbox: 200 message credits (one-off), 5 apps, 1 member. Provider models via Dify credits, then BYO key; no card.
- Source provider check
- · Provider documentation
- Timeout
- Not published
- Use listed by source
- agent/app
Provider-level or mixed access
OpenAI, Anthropic, Gemini, xAI, Tongyi (via Dify credits)
$0 (trial credits)Listed by Free Inference as a secondary provider.
- Context
- Not published
- Requests/min
- Not published
- Tokens/min
- Not published
- Requests/day
- Not published
- Tokens/day
- Not published
Source model check
Recent source changes
- Source commit
Flint added at Kilo Gateway and v0
Free Inference added Recursive: Flint at Kilo Gateway and Flint at v0, both listed with 256K context. v0’s notes still say custom model selection requires a paid plan.
View source diff - Source commit
Hy4 flash and Ling 3.2 Flash listings added
OpenCode Zen gained Hy4 flash Free, and OpenRouter gained a row labeled Ling 3.2 Flash (free). The source lists 1M context for both.
View source diff - Source commit
Three credit amounts restored in the source
Deepgram and SiliconFlow provider notes again list $200 trial credits. Speka’s notes again list the recurring $1 monthly allowance.
View source diff
Catalog data by Surendran Balachandran and Free Inference contributors. Raw source data · MIT license