Jun Siang Cheah
98cc1ffc61
Verified every provider against its live API/docs. Updates the hardcoded sections that nothing refreshes automatically: - Cerebras: free tier is now gpt-oss-120b, zai-glm-4.7 and gemma-4-31b at 5 RPM / 30K TPM / 1M TPH / 1M TPD (was 30 RPM / 60K TPM / 14,400 RPD, and still listed Llama 3.1 8B, which is gone). - OpenCode Zen: corrected two model names and added the four free models that were missing. - Google AI Studio: Gemini 3.5 Flash was reading gemini-3-flash's quota. Added Gemini 3.6 Flash, Gemini 3.5 Flash-Lite, Gemma 4 31B and Gemma 4 26B A4B, which all have free-tier quota. - Mistral (La Plateforme): limits are set per-model and per-organization, not a flat 1 RPS / 500K TPM. Verified against the admin console. - Modal: the $5/month tier no longer exists; Starter is $30/month. - Alibaba Model Studio: note the 90-day validity and Singapore-only endpoint. - Scaleway: free tier also includes 60 minutes of audio transcription. - Vercel AI Gateway: note that the free tier covers a subset of models. Also fixes the dead Vertex AI block emitting an orphan </tbody></table> into the README by guarding the closing tag with the same condition as the opening one.
Free LLM API resources
This lists various services that provide free access or credits towards API-based LLM usage.
Note
Please don't abuse these services, else we might lose them.
Warning
This list explicitly excludes any services that are not legitimate (eg reverse engineers an existing chatbot)
Free Providers
OpenRouter
Limits:
20 requests/minute
50 requests/day
Up to 1000 requests/day with $10 lifetime topup
Models share a common quota.
- cohere/north-mini-code:free
- google/gemma-4-26b-a4b-it:free
- google/gemma-4-31b-it:free
- inclusionai/ling-3.0-flash:free
- nvidia/nemotron-3-nano-30b-a3b:free
- nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
- nvidia/nemotron-3-super-120b-a12b:free
- nvidia/nemotron-3-ultra-550b-a55b:free
- nvidia/nemotron-3.5-content-safety:free
- nvidia/nemotron-nano-12b-v2-vl:free
- nvidia/nemotron-nano-9b-v2:free
- openai/gpt-oss-20b:free
- poolside/laguna-m.1:free
- poolside/laguna-s-2.1:free
- poolside/laguna-xs-2.1:free
Google AI Studio
Data is used for training when used outside of the UK/CH/EEA/EU.
| Model Name | Model Limits |
|---|---|
| Gemini 3.6 Flash | 250,000 tokens/minute 20 requests/day 5 requests/minute |
| Gemini 3.5 Flash | 250,000 tokens/minute 20 requests/day 5 requests/minute |
| Gemini 3 Flash | 250,000 tokens/minute 20 requests/day 5 requests/minute |
| Gemini 3.5 Flash-Lite | 250,000 tokens/minute 500 requests/day 15 requests/minute |
| Gemini 3.1 Flash-Lite | 250,000 tokens/minute 500 requests/day 15 requests/minute |
| Gemini 2.5 Flash | 250,000 tokens/minute 20 requests/day 5 requests/minute |
| Gemini 2.5 Flash-Lite | 250,000 tokens/minute 20 requests/day 10 requests/minute |
| Gemini 3.1 Flash TTS | 10,000 tokens/minute 10 requests/day 3 requests/minute |
| Gemini 2.5 Flash TTS | 10,000 tokens/minute 10 requests/day 3 requests/minute |
| Gemini Robotics-ER 1.6 | 250,000 tokens/minute 20 requests/day 5 requests/minute |
| Gemini Robotics-ER 1.5 | 250,000 tokens/minute 20 requests/day 10 requests/minute |
| Gemma 4 31B Instruct | 16,000 tokens/minute 14,400 requests/day 30 requests/minute |
| Gemma 4 26B A4B Instruct | 16,000 tokens/minute 14,400 requests/day 30 requests/minute |
| Gemma 3 27B Instruct | 15,000 tokens/minute 14,400 requests/day 30 requests/minute |
| Gemma 3 12B Instruct | 15,000 tokens/minute 14,400 requests/day 30 requests/minute |
| Gemma 3 4B Instruct | 15,000 tokens/minute 14,400 requests/day 30 requests/minute |
| Gemma 3 1B Instruct | 15,000 tokens/minute 14,400 requests/day 30 requests/minute |
NVIDIA NIM
Phone number verification required. Models tend to be context window limited.
Limits: 40 requests/minute
Mistral (La Plateforme)
- Free tier (Experiment plan) requires opting into data training
- Requires phone number verification.
Limits: Set per-model and per-organization — check your limits page. As of July 2026 a new free account sees anywhere from 25,000 to 20,000,000 tokens/minute and 0.03 to 12.5 requests/second depending on the model.
Mistral (Codestral)
- Currently free to use
- Monthly subscription based
- Requires phone number verification
Limits: 30 requests/minute, 2,000 requests/day
- Codestral
HuggingFace Inference Providers
HuggingFace Serverless Inference limited to models smaller than 10GB. Some popular models are supported even if they exceed 10GB.
Limits: $0.10/month in credits
- Various open models across supported providers
Vercel AI Gateway
Routes to various supported providers.
The free tier covers a subset of the model catalogue, with per-model rate limits.
Limits: $5/month
OpenCode Zen
AI gateway with curated models.
Free models may use data for improvement.
- Big Pickle
- DeepSeek V4 Flash Free
- MiMo-V2.5 Free
- Laguna S 2.1 Free
- Ling-3.0-flash Free
- North Mini Code Free
- Nemotron 3 Ultra Free
Cerebras
| Model Name | Model Limits |
|---|---|
| gpt-oss-120b | 5 requests/minute 30,000 tokens/minute 1,000,000 tokens/hour 1,000,000 tokens/day |
| zai-glm-4.7 | 5 requests/minute 30,000 tokens/minute 1,000,000 tokens/hour 1,000,000 tokens/day |
| gemma-4-31b | 5 requests/minute 30,000 tokens/minute 1,000,000 tokens/hour 1,000,000 tokens/day |
Groq
| Model Name | Model Limits |
|---|---|
| Allam 2 7B | 7,000 requests/day 6,000 tokens/minute |
| Llama 3.1 8B | 14,400 requests/day 6,000 tokens/minute |
| Llama 3.3 70B | 1,000 requests/day 12,000 tokens/minute |
| Whisper Large v3 | 2,000 requests/day |
| Whisper Large v3 Turbo | 2,000 requests/day |
| canopylabs/orpheus-arabic-saudi | |
| canopylabs/orpheus-v1-english | |
| groq/compound | 250 requests/day 70,000 tokens/minute |
| groq/compound-mini | 250 requests/day 70,000 tokens/minute |
| meta-llama/llama-prompt-guard-2-22m | |
| meta-llama/llama-prompt-guard-2-86m | |
| openai/gpt-oss-120b | 1,000 requests/day 8,000 tokens/minute |
| openai/gpt-oss-20b | 1,000 requests/day 8,000 tokens/minute |
| openai/gpt-oss-safeguard-20b | 1,000 requests/day 8,000 tokens/minute |
| qwen/qwen3.6-27b | 1,000 requests/day 8,000 tokens/minute |
Cohere
Limits:
20 requests/minute
1,000 requests/month
Models share a common monthly quota.
- c4ai-aya-expanse-32b
- c4ai-aya-vision-32b
- command-a-03-2025
- command-a-plus-05-2026
- command-a-reasoning-08-2025
- command-a-translate-08-2025
- command-a-vision-07-2025
- command-r-08-2024
- command-r-plus-08-2024
- command-r7b-12-2024
- command-r7b-arabic-02-2025
GitHub Models
Extremely restrictive input/output token limits.
Limits: Dependent on Copilot subscription tier (Free/Pro/Pro+/Business/Enterprise)
- Codestral 25.01
- Cohere Command A
- DeepSeek-R1
- DeepSeek-R1-0528
- DeepSeek-V3-0324
- Llama 4 Maverick 17B 128E Instruct FP8
- Llama 4 Scout 17B 16E Instruct
- Llama-3.2-11B-Vision-Instruct
- Llama-3.2-90B-Vision-Instruct
- Llama-3.3-70B-Instruct
- Meta-Llama-3.1-405B-Instruct
- Meta-Llama-3.1-8B-Instruct
- Ministral 3B
- Mistral Medium 3 (25.05)
- Mistral Small 3.1
- OpenAI GPT-4.1
- OpenAI GPT-4.1-mini
- OpenAI GPT-4.1-nano
- OpenAI GPT-4o
- OpenAI GPT-4o mini
- OpenAI Text Embedding 3 (large)
- OpenAI Text Embedding 3 (small)
- OpenAI gpt-5
- OpenAI gpt-5-chat (preview)
- OpenAI gpt-5-mini
- OpenAI gpt-5-nano
- OpenAI o1
- OpenAI o1-mini
- OpenAI o1-preview
- OpenAI o3
- OpenAI o3-mini
- OpenAI o4-mini
- Phi-4
- Phi-4-mini-instruct
- Phi-4-mini-reasoning
- Phi-4-multimodal-instruct
- Phi-4-reasoning
Cloudflare Workers AI
Limits: 10,000 neurons/day
- @cf/aisingapore/gemma-sea-lion-v4-27b-it
- @cf/google/gemma-4-26b-a4b-it
- @cf/ibm-granite/granite-4.0-h-micro
- @cf/moonshotai/kimi-k2.6
- @cf/moonshotai/kimi-k2.7-code
- @cf/nvidia/nemotron-3-120b-a12b
- @cf/openai/gpt-oss-120b
- @cf/openai/gpt-oss-20b
- @cf/qwen/qwen3-30b-a3b-fp8
- @cf/zai-org/glm-4.7-flash
- @cf/zai-org/glm-5.2
- DeepSeek R1 Distill Qwen 32B
- Gemma 2B Instruct (LoRA)
- Gemma 7B Instruct (LoRA)
- Llama 2 7B Chat (LoRA)
- Llama 3.1 8B Instruct (FP8)
- Llama 3.2 11B Vision Instruct
- Llama 3.2 1B Instruct
- Llama 3.2 3B Instruct
- Llama 3.3 70B Instruct (FP8)
- Llama 4 Scout Instruct
- Llama Guard 3 8B
- Mistral 7B Instruct v0.2 (LoRA)
- Mistral Small 3.1 24B Instruct
- Qwen 2.5 Coder 32B Instruct
- Qwen QwQ 32B
Providers with trial credits
Fireworks
Credits: $1
Models: Various open models
Baseten
Credits: $30
Models: Any supported model - pay by compute time
Nebius
Credits: $1
Models: Various open models
Novita
Credits: $0.5 for 1 year
Models: Various open models
AI21
Credits: $10 for 3 months
Models: Jamba family of models
Upstage
Credits: $10 for 3 months
Models: Solar Pro/Mini
NLP Cloud
Credits: $15
Requirements: Phone number verification
Models: Various open models
Alibaba Cloud (International) Model Studio
Credits: 1 million tokens/model, valid for 90 days (Singapore endpoint only)
Models: Various open and proprietary Qwen models
Modal
Credits: $30/month on the Starter plan
Models: Any supported model - pay by compute time
Inference.net
Credits: $1, $25 on responding to email survey
Models: Various open models
Hyperbolic
Credits: $1
Models:
- DeepSeek V3 0324
- Llama 3.3 70B Instruct
- deepseek-ai/deepseek-r1-0528
- qwen/qwen3-coder-480b-a35b-instruct
SambaNova Cloud
Credits: $5 for 3 months
Models:
- deepseek-v3.1
- deepseek-v3.2
- gemma-4-31b-it
- gpt-oss-120b
- meta-llama-3.3-70b-instruct
- minimax-m2.7
Scaleway Generative APIs
Credits: 1,000,000 free tokens, plus 60 minutes of audio transcription
Models:
- BGE-Multilingual-Gemma2
- Gemma 3 27B Instruct
- Llama 3.3 70B Instruct
- Pixtral 12B (2409)
- Whisper Large v3
- devstral-2-123b-instruct-2512
- gemma-4-26b-a4b-it
- glm-5.2
- gpt-oss-120b
- holo2-30b-a3b
- mistral-medium-3.5-128b
- mistral-small-3.2-24b-instruct-2506
- qwen3-235b-a22b-instruct-2507
- qwen3-coder-30b-a3b-instruct
- qwen3-embedding-8b
- qwen3.5-397b-a17b
- qwen3.6-35b-a3b
- voxtral-small-24b-2507