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
  • Google AI Studio
  • NVIDIA NIM
  • Mistral (La Plateforme)
  • Mistral (Codestral)
  • HuggingFace Inference Providers
  • Cerebras
  • Groq
  • OVH AI Endpoints (Free Beta)
  • Together (Free)
  • Cohere
  • GitHub Models
  • Chutes
  • Cloudflare Workers AI
  • Google Cloud Vertex AI
• Providers with trial credits
  • Together
  • Fireworks
  • Unify
  • Baseten
  • Nebius
  • Novita
  • AI21
  • Upstage
  • NLP Cloud
  • Alibaba Cloud (International) Model Studio
  • Modal
  • Hyperbolic
  • SambaNova Cloud
  • Scaleway Generative APIs

Free Providers

OpenRouter

Limits:

20 requests/minute
50 requests/day
1000 requests/day with $10 credit balance

Models share a common quota.

• Bytedance UI Tars 72B
• DeepCoder 14B Preview
• DeepHermes 3 Llama 3 8B Preview
• DeepSeek R1
• DeepSeek R1 Distill Llama 70B
• DeepSeek R1 Distill Qwen 14B
• DeepSeek R1 Distill Qwen 32B
• DeepSeek R1 Zero
• DeepSeek V3
• DeepSeek V3 0324
• DeepSeek V3 Base
• Dolphin 3.0 Mistral 24B
• Dolphin 3.0 R1 Mistral 24B
• Featherless Qwerky 72B
• Gemma 2 9B Instruct
• Gemma 3 12B Instruct
• Gemma 3 1B Instruct
• Gemma 3 27B Instruct
• Gemma 3 4B Instruct
• Kimi VL A3B Thinking
• Llama 3.1 8B Instruct
• Llama 3.1 Nemotron Ultra 253B v1
• Llama 3.2 11B Vision Instruct
• Llama 3.2 1B Instruct
• Llama 3.2 3B Instruct
• Llama 3.3 70B Instruct
• Llama 3.3 Nemotron Super 49B v1
• Llama 4 Maverick
• Llama 4 Scout
• Mistral 7B Instruct
• Mistral Nemo
• Mistral Small 24B Instruct 2501
• Mistral Small 3.1 24B Instruct
• Molmo 7B D
• Moonlight-16B-A3B-Instruct
• OlympicCoder 32B
• QwQ 32B ArliAI RpR v1
• Qwen 2.5 72B Instruct
• Qwen 2.5 7B Instruct
• Qwen 2.5 VL 32B Instruct
• Qwen 2.5 VL 3B Instruct
• Qwen 2.5 VL 7B Instruct
• Qwen QwQ 32B
• Qwen QwQ 32B Preview
• Qwen2.5 Coder 32B Instruct
• Qwen2.5 VL 72B Instruct
• Reka Flash 3
• Rogue Rose 103B v0.2
• Shisa V2 Llama 3.3 70B
• Zephyr 7B Beta
• meta-llama/llama-3.1-405b:free
• microsoft/mai-ds-r1:free
• qwen/qwen3-14b:free
• qwen/qwen3-235b-a22b:free
• qwen/qwen3-30b-a3b:free
• qwen/qwen3-32b:free
• qwen/qwen3-8b:free
• thudm/glm-4-32b:free
• thudm/glm-4-9b:free
• thudm/glm-z1-32b:free
• thudm/glm-z1-9b:free
• tngtech/deepseek-r1t-chimera:free

Google AI Studio

Data is used for training when used outside of the UK/CH/EEA/EU.

Model Name	Model Limits
Gemini 2.5 Pro (Experimental)	1,000,000 tokens/day 250,000 tokens/minute 25 requests/day 5 requests/minute
Gemini 2.5 Flash (Preview)	250,000 tokens/minute 500 requests/day 10 requests/minute
Gemini 2.0 Flash	1,000,000 tokens/minute 1,500 requests/day 15 requests/minute
Gemini 2.0 Flash-Lite	1,000,000 tokens/minute 1,500 requests/day 30 requests/minute
Gemini 2.0 Flash (Experimental)	4,000,000 tokens/minute 1,500 requests/day 10 requests/minute
Gemini 1.5 Flash	1,000,000 tokens/minute 1,500 requests/day 15 requests/minute
Gemini 1.5 Flash-8B	1,000,000 tokens/minute 1,500 requests/day 15 requests/minute
Gemini 1.5 Pro	32,000 tokens/minute 50 requests/day 2 requests/minute
LearnLM 1.5 Pro (Experimental)	1,500 requests/day 15 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
text-embedding-004	150 batch requests/minute 1,500 requests/minute 100 content/batch Shared Quota
embedding-001

NVIDIA NIM

Phone number verification required. Models tend to be context window limited.

Limits: 40 requests/minute

• Various open models

Mistral (La Plateforme)

• Free tier (Experiment plan) requires opting into data training
• Requires phone number verification.

Limits (per-model): 1 request/second, 500,000 tokens/minute, 1,000,000,000 tokens/month

• Open and Proprietary Mistral models

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

Cerebras

Free tier restricted to 8K context.

Model Name	Model Limits
Llama 4 Scout	30 requests/minute 60,000 tokens/minute 900 requests/hour 1,000,000 tokens/hour 14,400 requests/day 1,000,000 tokens/day
Llama 3.1 8B	30 requests/minute 60,000 tokens/minute 900 requests/hour 1,000,000 tokens/hour 14,400 requests/day 1,000,000 tokens/day
Llama 3.3 70B	30 requests/minute 60,000 tokens/minute 900 requests/hour 1,000,000 tokens/hour 14,400 requests/day 1,000,000 tokens/day

Groq

Model Name	Model Limits
Allam 2 7B	7,000 requests/day 6,000 tokens/minute
DeepSeek R1 Distill Llama 70B	1,000 requests/day 6,000 tokens/minute
Distil Whisper Large v3	7,200 audio-seconds/minute 2,000 requests/day
Gemma 2 9B Instruct	14,400 requests/day 15,000 tokens/minute
Groq compound-beta	200 requests/day 70,000 tokens/minute
Groq compound-beta-mini	200 requests/day 70,000 tokens/minute
Llama 3 70B	14,400 requests/day 6,000 tokens/minute
Llama 3 8B	14,400 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
Llama 4 Maverick 17B 128E Instruct	1,000 requests/day 6,000 tokens/minute
Llama 4 Scout Instruct	1,000 requests/day 30,000 tokens/minute
Llama Guard 3 8B	14,400 requests/day 15,000 tokens/minute
Mistral Saba 24B	1,000 requests/day 6,000 tokens/minute
Qwen QwQ 32B	1,000 requests/day 6,000 tokens/minute
Whisper Large v3	7,200 audio-seconds/minute 2,000 requests/day
Whisper Large v3 Turbo	7,200 audio-seconds/minute 2,000 requests/day

OVH AI Endpoints (Free Beta)

Model Name	Model Limits
DeepSeek R1 Distill Llama 70B	12 requests/minute
Llama 3.1 70B Instruct	12 requests/minute
Llama 3.1 8B Instruct	12 requests/minute
Llama 3.3 70B Instruct	12 requests/minute
Llava Next Mistral 7B	12 requests/minute
Mamba Codestral 7B v0.1	12 requests/minute
Mistral 7B Instruct v0.3	12 requests/minute
Mistral Nemo 2407	12 requests/minute
Mixtral 8x7B Instruct v0.1	12 requests/minute
Qwen 2.5 VL 72B Instruct	12 requests/minute
Qwen2.5 Coder 32B Instruct	12 requests/minute

Together (Free)

Limits: Up to 60 requests/minute

• Llama 3.2 11B Vision Instruct
• Llama 3.3 70B Instruct
• DeepSeek R1 Distil Llama 70B

Cohere

Limits:

20 requests/minute
1,000 requests/month

Models share a common quota.

• Command-A
• Command-R7B
• Command-R+
• Command-R
• Aya Expanse 8B
• Aya Expanse 32B
• Aya Vision 8B
• Aya Vision 32B

GitHub Models

Extremely restrictive input/output token limits.

Limits: Dependent on Copilot subscription tier (Free/Pro/Pro+/Business/Enterprise)

• AI21 Jamba 1.5 Large
• AI21 Jamba 1.5 Mini
• Codestral 25.01
• Cohere Command A
• Cohere Command R
• Cohere Command R 08-2024
• Cohere Command R+
• Cohere Command R+ 08-2024
• Cohere Embed 4
• Cohere Embed v3 English
• Cohere Embed v3 Multilingual
• DeepSeek-R1
• DeepSeek-V3-0324
• JAIS 30b Chat
• 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
• MAI-DS-R1
• Meta-Llama-3-70B-Instruct
• Meta-Llama-3-8B-Instruct
• Meta-Llama-3.1-405B-Instruct
• Meta-Llama-3.1-70B-Instruct
• Meta-Llama-3.1-8B-Instruct
• Ministral 3B
• Mistral Large (2407)
• Mistral Large 24.11
• Mistral Nemo
• Mistral Small
• 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 o1
• OpenAI o1-mini
• OpenAI o1-preview
• OpenAI o3
• OpenAI o3-mini
• OpenAI o4-mini
• Phi-3-medium instruct (128k)
• Phi-3-medium instruct (4k)
• Phi-3-mini instruct (128k)
• Phi-3-mini instruct (4k)
• Phi-3-small instruct (128k)
• Phi-3-small instruct (8k)
• Phi-3.5-MoE instruct (128k)
• Phi-3.5-mini instruct (128k)
• Phi-3.5-vision instruct (128k)
• Phi-4
• Phi-4-mini-instruct
• Phi-4-multimodal-instruct

Chutes

Distributed, decentralized crypto-based compute. Data is sent to individual hosts.

• DeepCoder 14B Preview
• DeepSeek R1
• DeepSeek R1-Zero
• DeepSeek V3
• DeepSeek V3 0324
• DeepSeek V3 Base
• Dolphin 3.0 Mistral 24B
• Dolphin 3.0 R1 Mistral 24B
• Llama 3.1 Nemotron Ultra 253B v1
• Llama 4 Maverick 17B 128E Instruct FP8
• Llama 4 Scout 17B 16E Instruct
• Mistral Small 3.1 24B Instruct 2503
• QwQ 32B ArliAI RpR v1
• Qwen 2.5 VL 32B Instruct
• Shisa V2 Llama 3.3 70B
• chutesai/llama-3.1-405b-fp8
• microsoft/mai-ds-r1-fp8
• thudm/glm-4-32b-0414
• thudm/glm-z1-32b-0414
• tngtech/deepseek-r1t-chimera

Cloudflare Workers AI

Limits: 10,000 neurons/day

• DeepSeek R1 Distill Qwen 32B
• Deepseek Coder 6.7B Base (AWQ)
• Deepseek Coder 6.7B Instruct (AWQ)
• Deepseek Math 7B Instruct
• Discolm German 7B v1 (AWQ)
• Falcom 7B Instruct
• Gemma 2B Instruct (LoRA)
• Gemma 3 12B Instruct
• Gemma 7B Instruct
• Gemma 7B Instruct (LoRA)
• Hermes 2 Pro Mistral 7B
• Llama 2 13B Chat (AWQ)
• Llama 2 7B Chat (FP16)
• Llama 2 7B Chat (INT8)
• Llama 2 7B Chat (LoRA)
• Llama 3 8B Instruct
• Llama 3 8B Instruct
• Llama 3 8B Instruct (AWQ)
• Llama 3.1 8B Instruct
• Llama 3.1 8B Instruct (AWQ)
• 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
• LlamaGuard 7B (AWQ)
• Mistral 7B Instruct v0.1
• Mistral 7B Instruct v0.1 (AWQ)
• Mistral 7B Instruct v0.2
• Mistral 7B Instruct v0.2 (LoRA)
• Mistral Small 3.1 24B Instruct
• Neural Chat 7B v3.1 (AWQ)
• OpenChat 3.5 0106
• OpenHermes 2.5 Mistral 7B (AWQ)
• Phi-2
• Qwen 1.5 0.5B Chat
• Qwen 1.5 1.8B Chat
• Qwen 1.5 14B Chat (AWQ)
• Qwen 1.5 7B Chat (AWQ)
• Qwen 2.5 Coder 32B Instruct
• Qwen QwQ 32B
• SQLCoder 7B 2
• Starling LM 7B Beta
• TinyLlama 1.1B Chat v1.0
• Una Cybertron 7B v2 (BF16)
• Zephyr 7B Beta (AWQ)

Google Cloud Vertex AI

Very stringent payment verification for Google Cloud.

Model Name	Model Limits
Gemini 2.5 Pro (Experimental)	10 requests/minute Shared Quota
Gemini 2.0 Flash (Experimental)
Gemini 2.0 Flash Thinking (Experimental)
Gemini 2.0 Pro (Experimental)
Llama 4 Maverick Instruct	60 requests/minute Free during preview
Llama 4 Scout Instruct	60 requests/minute Free during preview
Llama 3.3 70B Instruct	30 requests/minute Free during preview
Llama 3.2 90B Vision Instruct	30 requests/minute Free during preview
Llama 3.1 70B Instruct	60 requests/minute Free during preview
Llama 3.1 8B Instruct	60 requests/minute Free during preview

Providers with trial credits

Together

Credits: $1 when you add a payment method

Models: Various open models

Fireworks

Credits: $1

Models: Various open models

Unify

Credits: $5 when you add a payment method

Models: Routes to other providers, various open models and proprietary models (OpenAI, Gemini, Anthropic, Mistral, Perplexity, etc)

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, $10 for 3 months for LLMs with referral code + GitHub account connection

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: Token/time-limited trials on a per-model basis

Models: Various open and proprietary Qwen models

Modal

Credits: $5/month upon sign up, $30/month with payment method added

Models: Any supported model - pay by compute time

Hyperbolic

Credits: $1

Models:

• DeepSeek V3
• DeepSeek V3 0324
• Hermes 3 Llama 3.1 70B
• Llama 3 70B Instruct
• Llama 3.1 405B Base
• Llama 3.1 405B Base (FP8)
• Llama 3.1 405B Instruct
• Llama 3.1 70B Instruct
• Llama 3.1 8B Instruct
• Llama 3.2 3B Instruct
• Llama 3.3 70B Instruct
• Pixtral 12B (2409)
• Qwen QwQ 32B
• Qwen QwQ 32B Preview
• Qwen2.5 72B Instruct
• Qwen2.5 Coder 32B Instruct
• Qwen2.5 VL 72B Instruct
• Qwen2.5 VL 7B Instruct

SambaNova Cloud

Credits: $5 for 3 months

Models:

• E5-Mistral-7B-Instruct
• Llama 3.1 405B
• Llama 3.1 8B
• Llama 3.2 1B
• Llama 3.2 3B
• Llama 3.3 70B
• Llama-4-Maverick-17B-128E-Instruct
• Llama-4-Scout-17B-16E-Instruct
• Llama-Guard-3-8B
• Qwen/QwQ-32B
• Qwen/Qwen2-Audio-7B-Instruct
• deepseek-ai/DeepSeek-R1
• deepseek-ai/DeepSeek-R1-Distill-Llama-70B
• deepseek-ai/DeepSeek-V3-0324

Scaleway Generative APIs

Credits: 1,000,000 free tokens

Models:

• BGE-Multilingual-Gemma2
• DeepSeek R1 Distill Llama 70B
• DeepSeek R1 Distill Llama 8B
• Gemma 3 27B Instruct
• Llama 3.1 70B Instruct
• Llama 3.1 8B Instruct
• Llama 3.3 70B Instruct
• Mistral Nemo 2407
• Mistral Small 3.1 24B Instruct 2503
• Pixtral 12B (2409)
• Qwen2.5 Coder 32B Instruct
• sentence-t5-xxl