Directory of Free LLM APIs: Compare 350+ Models
Showing 350 of 350 free LLM models
Discover and filter 350+ free LLM models across 30 providers. Find APIs by capability (vision, reasoning), rate limits, or no-credit-card requirements, and get the perfect free AI model for your project.
258 models verified via live API · refreshed Jul 19, 2026 — how we verify
| Provider | Model | Score | Context | Modality | Rate Limit | Status |
|---|---|---|---|---|---|---|
| z-ai/glm-5.2 Verified | 96 | 1.0M | Up to 40 RPM | Online | ||
| MiniMax: MiniMax M3 Paid MiniMax: MiniMax M3 | 92 | 1.0M | 200 req/day (free tier) | Online | ||
| Tencent: Hy3 (free) Verified | 91 | 262K | 200 req/day (free tier) | Online | ||
| minimaxai/minimax-m3 Verified MiniMax: MiniMax M3 | 89 | 1.0M | Up to 40 RPM | Online | ||
| Nex AGI: Nex-N2-Pro Paid Nex AGI: Nex-N2-Pro | 89 | 262K | 200 req/day (free tier) | Online | ||
| Gemini 3.5 Flash Verified Gemini 3.5 Flash | 89 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| deepseek-ai/deepseek-v4-pro Verified deepseek-ai/deepseek-v4-pro | 87 | 1.0M | Up to 40 RPM | Online | ||
| NVIDIA: Nemotron 3 Ultra (free) Verified NVIDIA: Nemotron 3 Ultra (free) | 87 | 1.0M | 200 req/day (free tier) | Online | ||
| DeepSeek: DeepSeek V4 Flash | 86 | 1.0M | 200 req/day (free tier) | Online | ||
| MoonshotAI: Kimi K2.6 | 85 | 262K | 200 req/day (free tier) | Online | ||
| Z.ai: GLM 5.1 Paid | 84 | 203K | 200 req/day (free tier) | Online | ||
| deepseek-ai/deepseek-v4-flash Verified DeepSeek: DeepSeek V4 Flash | 84 | 1.0M | Up to 40 RPM | Online | ||
| moonshotai/kimi-k2.6 Verified MoonshotAI: Kimi K2.6 | 84 | 262K | Up to 40 RPM | Online | ||
| agnes-2.0-flash Verified | 81 | 256K | 30 RPM | Online | ||
| Qwen3.6-27B | 80 | 131K | 2 RPM (anonymous) | Online | ||
| 78 | 262K | 200 req/day (free tier) | Online | |||
| stepfun-ai/step-3.7-flash Verified | 77 | 256K | Up to 40 RPM | Online | ||
| minimaxai/minimax-m2.7 Verified MiniMax: MiniMax M3 | 77 | 205K | Up to 40 RPM | Online | ||
| Nemotron 3 Ultra 550B A55B Verified NVIDIA: Nemotron 3 Ultra (free) | 76 | 1.0M | Online | |||
| Google: Gemma 4 31B (free) Verified Google: Gemma 4 31B (free) | 74 | 262K | 200 req/day (free tier) | Online | ||
| MiniMax: MiniMax M3 | 73 | 205K | 200 req/day (free tier) | Online | ||
| Cohere: North Mini Code (free) Verified Cohere: North Mini Code (free) | 73 | 256K | 200 req/day (free tier) | Online | ||
| deepseek-ai/DeepSeek-V4-Pro Verified deepseek-ai/deepseek-v4-pro | 72 | 8K | Online | |||
| Google: Gemma 4 26B A4B (free) Verified Google: Gemma 4 26B A4B (free) | 72 | 262K | 200 req/day (free tier) | Online | ||
| 71 | 262K | 200 req/day (free tier) | Online | |||
| qwen/qwen3.5-397b-a17b Verified qwen/qwen3.5-397b-a17b | 71 | 262K | Up to 40 RPM | Online | ||
| qwen/qwen3.5-397b-a17b | 71 | 131K | 2 RPM (anonymous) | Online | ||
| qwen/qwen3.5-122b-a10b Verified qwen/qwen3.5-122b-a10b | 71 | 262K | Up to 40 RPM | Online | ||
| MiniMax-M2.5-highspeed Verified MiniMax: MiniMax M3 | 70 | 205K | See provider page | Online | ||
| MiniMax: MiniMax M3 | 70 | 196K | ~200 req/hr | Online | ||
| MiniMax-M2.7 | 70 | 128K | 20 RPM, 20 RPD, 200K TPD | Online | ||
| NVIDIA: Nemotron 3 Nano Omni (free) Verified NVIDIA: Nemotron 3 Nano Omni (free) | 70 | 256K | 200 req/day (free tier) | Online | ||
| NVIDIA: Nemotron 3 Super (free) Verified NVIDIA: Nemotron 3 Super (free) | 70 | 1.0M | 200 req/day (free tier) | Online | ||
| deepseek-ai/DeepSeek-V4-Flash Verified DeepSeek: DeepSeek V4 Flash | 69 | 8K | Online | |||
| qwen/qwen3.6-27b Paid Qwen3.6-27B | 69 | 8K | Online | |||
| poolside/laguna-xs-2.1 Verified poolside/laguna-xs-2.1 | 68 | 262K | Up to 40 RPM | Online | ||
| 67 | 131K | ~200 req/hr | Online | |||
| Poolside: Laguna XS 2.1 (free) Verified | 67 | 262K | 200 req/day (free tier) | Online | ||
| Poolside: Laguna M.1 (free) Verified | 67 | 262K | 200 req/day (free tier) | Online | ||
| NVIDIA: Nemotron 3 Super (free) | 66 | 262K | ~200 req/hr | Online | ||
| @cf/google/gemma-4-26b-a4b-it Verified Google: Gemma 4 26B A4B (free) | 65 | 256K | 10K neurons/day (shared) | Online | ||
| stepfun-ai/step-3.5-flash Verified | 64 | 262K | Up to 40 RPM | Online | ||
| @cf/moonshotai/kimi-k2.7-code Verified MoonshotAI: Kimi K2.6 | 64 | 262K | 10K neurons/day (shared) | Online | ||
| Gemma 4 31B IT Verified Google: Gemma 4 31B (free) | 64 | 262K | Online | |||
| GLM-4.7-Flash Verified GLM-4.7-Flash | 63 | 200K | 1 concurrent request | Online | ||
| o4-mini | 62 | 200K | 10 RPM, 50 RPD | Online | ||
| Qwen3.5-9B | 62 | 131K | 2 RPM (anonymous) | Online | ||
| 01-ai/yi-large Verified | 61 | 131K | Up to 40 RPM | Online | ||
| meta/codellama-70b Verified | 61 | 131K | Up to 40 RPM | Online | ||
| nvidia/llama3-chatqa-1.5-70b Verified | 61 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-fin-70b-32k Verified | 61 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-med-70b Verified | 61 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-med-70b-32k Verified | 61 | 131K | Up to 40 RPM | Online | ||
| Gemini 3.1 Flash-Lite Verified Gemini 3.1 Flash-Lite | 61 | 1.0M | 30 RPM, 1,500 RPD | Online | ||
| 60 | 131K | ~200 req/hr | Online | |||
| Gemma 4 31B IT Verified Google: Gemma 4 31B (free) | 60 | 262K | Online | |||
| NVIDIA: Nemotron 3 Nano Omni (free) | 60 | 256K | Online | |||
| zai-glm-4.7 Verified zai-glm-4.7 | 60 | 128K | 10 RPM, 100 RPD, 1M TPD | Online | ||
| Nous: Hermes 3 405B Instruct (free) Verified | 59 | 131K | 200 req/day (free tier) | Online | ||
| 59 | 131K | See provider page | Online | |||
| 59 | 131K | See provider page | Online | |||
| 59 | 128K | 20 RPM, 20 RPD, 200K TPD | Online | |||
| Nemotron 3 Super 120B A12B Verified NVIDIA: Nemotron 3 Super (free) | 59 | 262K | Online | |||
| GLM-4.6V-Flash Verified GLM-4.6V-Flash | 59 | 128K | 1 concurrent request | Online | ||
| Qwen: Qwen3 Coder 480B A35B (free) Verified Qwen: Qwen3 Coder 480B A35B (free) | 59 | 1.0M | 200 req/day (free tier) | Online | ||
| gpt-4.1 | 59 | 1.0M | 10 RPM, 50 RPD | Online | ||
| Qwen/Qwen3.5-397B-A17B Verified qwen/qwen3.5-397b-a17b | 58 | 8K | Online | |||
| Qwen/Qwen3.5-122B-A10B Verified qwen/qwen3.5-122b-a10b | 58 | 8K | Online | |||
| OpenAI: gpt-oss-120b Paid OpenAI: gpt-oss-120b | 58 | 131K | 200 req/day (free tier) | Online | ||
| 57 | 256K | ~1 RPS, 500K TPM | Online | |||
| Gemma 4 26B A4B IT Verified Google: Gemma 4 26B A4B (free) | 57 | 262K | Online | |||
| Qwen: Qwen3 VL 235B A22B Instruct | 57 | 131K | 200 req/day (free tier) | Online | ||
| nvidia/llama-3.1-nemotron-ultra-253b-v1 | 57 | 131K | Up to 40 RPM | Online | ||
| NVIDIA: Nemotron 3.5 Content Safety (free) | 57 | 128K | 200 req/day (free tier) | Online | ||
| ibm/granite-34b-code-instruct Verified | 56 | 131K | Up to 40 RPM | Online | ||
| Qwen: Qwen3 Coder 30B A3B Instruct | 56 | 160K | 200 req/day (free tier) | Online | ||
| Gemini Flash Latest Verified Gemini Flash Latest | 56 | 1.0M | Online | |||
| 55 | 8K | Online | ||||
| 55 | 256K | ~200 req/hr | Online | |||
| 55 | 256K | See provider page | Online | |||
| agnes-1.5-flash Verified | 55 | 256K | 30 RPM | Online | ||
| gpt-5 | 55 | 200K | 10 RPM, 50 RPD | Online | ||
| Qwen: Qwen3 Next 80B A3B Instruct (free) | 55 | 262K | 200 req/day (free tier) | Online | ||
| gemma-4-31B-it (Preview) | 55 | 128K | 20 RPM, 20 RPD, 200K TPD | Online | ||
| Qwen: Qwen3 VL 8B Thinking | 55 | 256K | 200 req/day (free tier) | Online | ||
| Qwen: Qwen3 235B A22B | 55 | 131K | 200 req/day (free tier) | Online | ||
| Gemini 3 Flash (Preview) Verified | 54 | 1.0M | Preview limits | Online | ||
| bigcode/starcoder2-15b Verified | 54 | 131K | Up to 40 RPM | Online | ||
| google/deplot Verified | 54 | 131K | Up to 40 RPM | Online | ||
| google/gemma-2b Verified | 54 | 131K | Up to 40 RPM | Online | ||
| google/recurrentgemma-2b Verified | 54 | 131K | Up to 40 RPM | Online | ||
| microsoft/kosmos-2 Verified | 54 | 131K | Up to 40 RPM | Online | ||
| microsoft/phi-3-vision-128k-instruct Verified | 54 | 131K | Up to 40 RPM | Online | ||
| microsoft/phi-3.5-moe-instruct Verified | 54 | 131K | Up to 40 RPM | Online | ||
| 54 | 131K | Up to 40 RPM | Online | |||
| mistralai/mixtral-8x22b-v0.1 Verified | 54 | 131K | Up to 40 RPM | Online | ||
| 54 | 131K | Up to 40 RPM | Online | |||
| nvidia/nemoretriever-parse Verified | 54 | 131K | Up to 40 RPM | Online | ||
| nvidia/nemotron-4-340b-instruct Verified | 54 | 131K | Up to 40 RPM | Online | ||
| nvidia/nemotron-4-340b-reward Verified | 54 | 131K | Up to 40 RPM | Online | ||
| nvidia/nemotron-parse Verified | 54 | 131K | Up to 40 RPM | Online | ||
| nvidia/neva-22b Verified | 54 | 131K | Up to 40 RPM | Online | ||
| nvidia/nvclip Verified | 54 | 131K | Up to 40 RPM | Online | ||
| nvidia/riva-translate-4b-instruct Verified | 54 | 131K | Up to 40 RPM | Online | ||
| nvidia/vila Verified | 54 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-creative-122b Verified | 54 | 131K | Up to 40 RPM | Online | ||
| nvidia/nemotron-3.5-content-safety Verified NVIDIA: Nemotron 3.5 Content Safety (free) | 54 | 128K | Up to 40 RPM | Online | ||
| Qwen: Qwen3 Coder 30B A3B Instruct | 54 | 262K | 2 RPM (anonymous) | Online | ||
| Google: Lyria 3 Pro Preview Verified Google: Lyria 3 Pro Preview | 54 | 1.0M | 200 req/day (free tier) | Online | ||
| Google: Lyria 3 Clip Preview Verified Google: Lyria 3 Clip Preview | 54 | 1.0M | 200 req/day (free tier) | Online | ||
| Qwen: Qwen3 VL 8B Instruct | 54 | 256K | 200 req/day (free tier) | Online | ||
| NVIDIA: Nemotron 3 Nano 30B A3B (free) | 54 | 256K | 200 req/day (free tier) | Online | ||
| GPT OSS 120B Paid | 53 | 131K | Online | |||
| GPT OSS 120B Verified | 53 | 131K | Online | |||
| @cf/openai/gpt-oss-120b Verified | 53 | 128K | 10K neurons/day (shared) | Online | ||
| Gemini 3.1 Flash Lite Verified Gemini 3.1 Flash-Lite | 53 | 1.0M | Online | |||
| gpt-oss-120b Verified gpt-oss-120b | 53 | 128K | 30 RPM, 14,400 RPD, 1M TPD | Online | ||
| Z.ai: GLM 4.5 Air Paid Z.ai: GLM 4.5 Air | 53 | 131K | 200 req/day (free tier) | Online | ||
| Qwen: Qwen3 235B A22B Thinking 2507 | 53 | 262K | 200 req/day (free tier) | Online | ||
| NVIDIA: Nemotron Nano 12B 2 VL (free) | 53 | 128K | 200 req/day (free tier) | Online | ||
| adept/fuyu-8b Verified | 52 | 131K | Up to 40 RPM | Online | ||
| aisingapore/sea-lion-7b-instruct Verified | 52 | 131K | Up to 40 RPM | Online | ||
| 52 | 131K | Up to 40 RPM | Online | |||
| google/codegemma-1.1-7b Verified | 52 | 131K | Up to 40 RPM | Online | ||
| google/codegemma-7b Verified | 52 | 131K | Up to 40 RPM | Online | ||
| ibm/granite-3.0-8b-instruct Verified | 52 | 131K | Up to 40 RPM | Online | ||
| ibm/granite-8b-code-instruct Verified | 52 | 131K | Up to 40 RPM | Online | ||
| mistralai/mistral-7b-instruct-v0.3 Verified | 52 | 131K | Up to 40 RPM | Online | ||
| 52 | 131K | Up to 40 RPM | Online | |||
| nvidia/cosmos-reason2-8b Verified | 52 | 131K | Up to 40 RPM | Online | ||
| 52 | 131K | Up to 40 RPM | Online | |||
| zyphra/zamba2-7b-instruct Verified | 52 | 131K | Up to 40 RPM | Online | ||
| 52 | 256K | ~1 RPS, 500K TPM | Online | |||
| agnes-image-2.0-flash Verified | 52 | 4K | 30 RPM (1K) | Online | ||
| agnes-image-2.1-flash Verified | 52 | 4K | 30 RPM (1K) | Online | ||
| deepseek-ai/DeepSeek-V3.2 Verified deepseek-ai/DeepSeek-V3.2 | 52 | 8K | Online | |||
| Qwen: Qwen3 Next 80B A3B Thinking | 52 | 262K | 200 req/day (free tier) | Online | ||
| Gemini 2.5 Flash Verified Gemini 2.5 Flash | 52 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| Gemini 2.5 Pro Verified Gemini 2.5 Pro | 52 | 1.0M | 5 RPM, 50 RPD | Online | ||
| DeepSeek-V3.1 | 52 | 128K | 20 RPM, 20 RPD, 200K TPD | Online | ||
| Venice: Uncensored (free) Verified | 51 | 33K | 200 req/day (free tier) | Online | ||
| 51 | 8K | Online | ||||
| OpenAI: gpt-oss-20b (free) Verified OpenAI: gpt-oss-120b | 51 | 131K | 200 req/day (free tier) | Online | ||
| Llama-4-Scout-17B-16E | 51 | 512K | 15 RPM, 150 RPD | Online | ||
| Llama-4-Scout-17B-16E | 51 | 256K | 10 RPM, 50 RPD | Online | ||
| gpt-4o | 51 | 128K | 10 RPM, 50 RPD | Online | ||
| NVIDIA: Nemotron Nano 9B V2 (free) Verified NVIDIA: Nemotron Nano 9B V2 (free) | 51 | 128K | 200 req/day (free tier) | Online | ||
| 50 | 128K | 15 RPM, 150 RPD | Online | |||
| baai/bge-m3 Verified | 50 | 131K | Up to 40 RPM | Online | ||
| Nemotron 3 Ultra 550B A55B Verified | 50 | 1.0M | Online | |||
| Qwen: Qwen3 30B A3B Paid Qwen: Qwen3 30B A3B | 50 | 131K | 200 req/day (free tier) | Online | ||
| DeepSeek-R1 | 50 | 64K | 15 RPM, 150 RPD | Online | ||
| Qwen2.5-VL-72B-Instruct | 50 | 128K | 2 RPM (anonymous) | Online | ||
| Mistral-Small-3.2-24B-Instruct | 50 | 128K | 2 RPM (anonymous) | Online | ||
| Mistral-Nemo-Instruct-2407 | 50 | 128K | 2 RPM (anonymous) | Online | ||
| GLM-4.5-Flash Verified GLM-4.5-Flash | 50 | 128K | 1 concurrent request | Online | ||
| gpt-4.1-mini | 50 | 1.0M | 15 RPM, 150 RPD | Online | ||
| 49 | 256K | ~1 RPS, 500K TPM | Online | |||
| agnes-video-v2.0 Verified | 49 | 4K | 2 RPM | Online | ||
| 49 | 256K | ~1 RPS, 500K TPM | Online | |||
| Qwen: Qwen3 30B A3B Thinking 2507 | 49 | 131K | 200 req/day (free tier) | Online | ||
| nvidia/llama-3.3-nemotron-super-49b-v1.5 | 49 | 131K | Up to 40 RPM | Online | ||
| gpt-oss-20b | 49 | 128K | 2 RPM (anonymous) | Online | ||
| Qwen: Qwen3 32B Paid Qwen: Qwen3 32B | 48 | 131K | 200 req/day (free tier) | Online | ||
| Aion 2.0 | 48 | 128K | 15 RPM, 20K TPD | Online | ||
| Qwen: Qwen3 14B Paid Qwen: Qwen3 14B | 48 | 132K | 200 req/day (free tier) | Online | ||
| @cf/nvidia/nemotron-3-120b-a12b Verified | 47 | 8K | Online | |||
| @cf/baai/bge-large-en-v1.5 Verified | 47 | 8K | Online | |||
| 47 | 10.0M | 10K neurons/day (shared) | Online | |||
| Free Models Router Verified | 47 | 200K | 200 req/day (free tier) | Online | ||
| mistralai/mistral-medium-3.5-128b Verified | 47 | 8K | Online | |||
| ibm/granite-3.0-3b-a800m-instruct Verified | 47 | 131K | Up to 40 RPM | Online | ||
| Mixtral 8x7B Verified | 47 | 33K | Unlimited for free models | Online | ||
| GPT OSS 20B Paid | 47 | 131K | Online | |||
| nvidia/nemotron-nano-3-30b-a3b Verified nvidia/llama-3.1-nemotron-ultra-253b-v1 | 47 | 131K | Up to 40 RPM | Online | ||
| Meta: Llama 3.3 70B Instruct (free) Verified Meta: Llama 3.3 70B Instruct (free) | 47 | 131K | 200 req/day (free tier) | Online | ||
| Llama 3.3 Nemotron Super 49B v1 Verified | 46 | 131K | Online | |||
| GPT OSS 20B Verified | 46 | 131K | Online | |||
| GLM-4.7-FlashX Verified | 46 | 200K | Online | |||
| Qwen: Qwen3 8B Paid Qwen: Qwen3 8B | 46 | 131K | 200 req/day (free tier) | Online | ||
| @cf/mistralai/mistral-small-3.1-24b-instruct | 46 | 128K | 10K neurons/day (shared) | Online | ||
| DeepSeek V4 Flash Verified | 45 | 1.0M | Online | |||
| mistralai/mistral-large-2-instruct Verified | 45 | 131K | Up to 40 RPM | Online | ||
| 45 | 131K | See provider page | Online | |||
| Nemotron Mini 4B Instruct Verified | 45 | 128K | Online | |||
| nvidia/llama-nemotron-embed-1b-v2 Verified nvidia/llama-3.1-nemotron-ultra-253b-v1 | 45 | 131K | Up to 40 RPM | Online | ||
| nvidia/llama-nemotron-embed-vl-1b-v2 Verified nvidia/llama-3.1-nemotron-ultra-253b-v1 | 45 | 131K | Up to 40 RPM | Online | ||
| DeepSeek-R1 | 45 | 131K | Community-powered, no hard cap | Online | ||
| Meta: Llama 3.3 70B Instruct (free) | 45 | 131K | 30 RPM, 1,000 RPD | Online | ||
| Meta: Llama 3.3 70B Instruct (free) | 45 | 131K | 15 RPM, 150 RPD | Online | ||
| meta/llama-3.1-70b-instruct Verified meta/llama-3.1-70b-instruct | 45 | 131K | Up to 40 RPM | Online | ||
| 44 | 32K | Credit-metered | Online | |||
| 44 | 256K | 20 RPM | Online | |||
| Mistral 7B Verified | 44 | 33K | See provider page | Online | ||
| 44 | 33K | See provider page | Online | |||
| GLM-5.2 Verified | 44 | 1.0M | Online | |||
| bytedance/seed-oss-36b-instruct Verified | 44 | 8K | Online | |||
| google/diffusiongemma-26b-a4b-it Verified | 44 | 8K | Online | |||
| google/gemma-2-2b-it Verified | 44 | 8K | Online | |||
| google/gemma-3n-e2b-it Verified | 44 | 8K | Online | |||
| meta/llama-3.2-90b-vision-instruct Verified | 44 | 8K | Online | |||
| 44 | 8K | Online | ||||
| mistralai/mistral-nemotron Verified | 44 | 8K | Online | |||
| mistralai/mistral-small-4-119b-2603 Verified | 44 | 8K | Online | |||
| nvidia/gliner-pii Verified | 44 | 8K | Online | |||
| nvidia/ising-calibration-1-35b-a3b Verified | 44 | 8K | Online | |||
| 44 | 8K | Online | ||||
| sarvamai/sarvam-m Verified | 44 | 8K | Online | |||
| mistralai/mixtral-8x7b-instruct-v0.1 Verified | 44 | 8K | Online | |||
| 44 | 128K | Credit-metered | Online | |||
| 44 | 33K | See provider page | Online | |||
| 44 | 128K | 20 RPM | Online | |||
| 44 | 128K | 20 RPM | Online | |||
| 44 | 128K | 20 RPM | Online | |||
| MiniMax-M3 Verified | 44 | 512K | Online | |||
| whisper-large-v3 Verified | 44 | 131K | 20 RPM, 2,000 RPD | Online | ||
| whisper-large-v3-turbo Verified | 44 | 131K | 20 RPM, 2,000 RPD | Online | ||
| 44 | 131K | 30 RPM, 60K TPM | Online | |||
| nvidia/llama-3.1-nemotron-ultra-253b-v1 | 44 | 131K | Up to 40 RPM | Online | ||
| Nemotron 3 Nano 30B A3B Verified NVIDIA: Nemotron 3 Nano 30B A3B (free) | 44 | 262K | Online | |||
| Meta-Llama-3_3-70B-Instruct Verified Meta: Llama 3.3 70B Instruct (free) | 44 | 131K | 2 RPM (anonymous) | Online | ||
| Meta: Llama 3.2 3B Instruct (free) Verified Meta: Llama 3.2 3B Instruct (free) | 44 | 131K | 200 req/day (free tier) | Online | ||
| Phi-4 | 44 | 131K | See provider page | Online | ||
| 43 | 8K | Online | ||||
| 43 | 8K | Online | ||||
| 43 | 8K | Online | ||||
| stepfun-ai/Step-3.5-Flash Verified | 43 | 8K | Online | |||
| stepfun-ai/Step-3.7-Flash Verified | 43 | 8K | Online | |||
| 43 | 128K | 15 RPM, 20K TPD | Online | |||
| Kimi K2.5 Verified | 43 | 262K | Online | |||
| 43 | 131K | 200 req/day (free tier) | Online | |||
| GLM-5.1 Verified | 43 | 200K | Online | |||
| GLM-5.1 Verified | 43 | 200K | Online | |||
| 43 | 32K | Credit-metered | Online | |||
| @cf/zai-org/glm-4.7-flash Verified | 43 | 8K | Online | |||
| @cf/qwen/qwq-32b Verified | 43 | 8K | Online | |||
| upstage/solar-10.7b-instruct Verified | 43 | 8K | Online | |||
| MiMo-V2.5 Verified | 43 | 1.0M | Online | |||
| qwen/qwen3-next-80b-a3b-instruct Verified Qwen: Qwen3 Next 80B A3B Instruct (free) | 43 | 8K | Online | |||
| Mistral-Nemo-Instruct-2407 | 43 | 128K | ~1 RPS, 500K TPM | Online | ||
| llama-3.1-8b-instant Paid llama-3.1-8b-instant | 43 | 131K | 30 RPM, 1,000 RPD | Online | ||
| meta/llama-3.2-11b-vision-instruct Verified meta/llama-3.2-11b-vision-instruct | 43 | 131K | Up to 40 RPM | Online | ||
| 42 | 33K | See provider page | Online | |||
| ai21labs/jamba-1.5-large-instruct Verified | 42 | 131K | Up to 40 RPM | Online | ||
| groq/compound Verified | 42 | 8K | Online | |||
| Gemini Flash-Lite Latest Verified | 42 | 1.0M | Online | |||
| gemini-robotics-er-1.6-preview Verified | 42 | 131K | Online | |||
| Gemma 4 31B IT Verified | 42 | 262K | Online | |||
| Nemotron Nano 12B v2 VL Verified NVIDIA: Nemotron Nano 12B 2 VL (free) | 42 | 128K | Online | |||
| meta/llama-3.2-3b-instruct Verified Meta: Llama 3.2 3B Instruct (free) | 42 | 131K | Up to 40 RPM | Online | ||
| llama-3.1-8b-instant | 42 | 131K | 2 RPM (anonymous) | Online | ||
| Qwen/Qwen3-235B-A22B-Instruct-2507 Verified Qwen/Qwen3-235B-A22B-Instruct-2507 | 42 | 8K | Online | |||
| GLM-4.5-Air Verified GLM-4.5-Air | 42 | 131K | Online | |||
| nvidia/embed-qa-4 Verified | 41 | 131K | Up to 40 RPM | Online | ||
| 41 | 131K | Up to 40 RPM | Online | |||
| nvidia/llama-3.2-nv-embedqa-1b-v1 Verified | 41 | 131K | Up to 40 RPM | Online | ||
| nvidia/nemotron-3-embed-1b Verified | 41 | 131K | Up to 40 RPM | Online | ||
| nvidia/nv-embedqa-e5-v5 Verified | 41 | 131K | Up to 40 RPM | Online | ||
| nvidia/nv-embedqa-mistral-7b-v2 Verified | 41 | 131K | Up to 40 RPM | Online | ||
| snowflake/arctic-embed-l Verified | 41 | 131K | Up to 40 RPM | Online | ||
| allam-2-7b Verified | 41 | 8K | Online | |||
| groq/compound-mini Verified | 41 | 8K | Online | |||
| 41 | 32K | 15 RPM, 20K TPD | Online | |||
| databricks/dbrx-instruct Verified | 41 | 131K | Up to 40 RPM | Online | ||
| meta/llama2-70b Verified | 41 | 131K | Up to 40 RPM | Online | ||
| 41 | 8K | Online | ||||
| MedAIBase/AntAngelMed Verified | 41 | 8K | Online | |||
| MiniMax/MiniMax-M1-80k Verified | 41 | 8K | Online | |||
| MusePublic/Qwen-Image-Edit Verified | 41 | 8K | Online | |||
| OpenGVLab/InternVL3_5-241B-A28B Verified | 41 | 8K | Online | |||
| PaddlePaddle/ERNIE-4.5-21B-A3B-PT Verified | 41 | 8K | Online | |||
| PaddlePaddle/ERNIE-4.5-300B-A47B-PT Verified | 41 | 8K | Online | |||
| PaddlePaddle/ERNIE-4.5-VL-28B-A3B-PT Verified | 41 | 8K | Online | |||
| Qwen/Qwen-Image-Edit Verified | 41 | 8K | Online | |||
| Qwen/Qwen3-4B Verified | 41 | 8K | Online | |||
| Shanghai_AI_Laboratory/Intern-S1 Verified | 41 | 8K | Online | |||
| 41 | 8K | Online | ||||
| Tencent-Hunyuan/Hy3 Verified | 41 | 8K | Online | |||
| Qwen/Qwen3-VL-235B-A22B-Instruct Verified Qwen: Qwen3 VL 235B A22B Instruct | 41 | 8K | Online | |||
| meta/llama-3.1-70b-instruct | 41 | 131K | See provider page | Online | ||
| @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | 41 | 32K | 10K neurons/day (shared) | Online | ||
| meta/llama-3.2-1b-instruct Verified meta/llama-3.2-1b-instruct | 41 | 131K | Up to 40 RPM | Online | ||
| North Mini Code Verified | 40 | 256K | Online | |||
| 40 | 131K | $25/month free credits, resets monthly | Online | |||
| @cf/baai/bge-m3 Verified | 40 | 8K | Online | |||
| @cf/google/gemma-2b-it-lora Verified | 40 | 8K | Online | |||
| @cf/moonshotai/kimi-k2.6 Verified | 40 | 8K | Online | |||
| @cf/ibm-granite/granite-4.0-h-micro Verified | 40 | 8K | Online | |||
| @cf/baai/bge-small-en-v1.5 Verified | 40 | 8K | Online | |||
| @cf/zai-org/glm-5.2 Verified | 40 | 8K | Online | |||
| @cf/baai/bge-base-en-v1.5 Verified | 40 | 8K | Online | |||
| 40 | 8K | Online | ||||
| @cf/openai/gpt-oss-20b Verified | 40 | 8K | Online | |||
| @cf/moondream/moondream3.1-9B-A2B Verified | 40 | 8K | Online | |||
| Codestral (latest) Verified | 40 | 256K | Online | |||
| Qwen/Qwen3-Coder-30B-A3B-Instruct Verified Qwen: Qwen3 Coder 30B A3B Instruct | 40 | 8K | Online | |||
| Meta: Llama 3.3 70B Instruct (free) | 40 | 131K | 10K neurons/day (shared) | Online | ||
| meta/llama-3.1-70b-instruct | 40 | 131K | Community-powered, no hard cap | Online | ||
| mistralai/ministral-14b-instruct-2512 | 40 | 8K | Online | |||
| Qwen2.5-7B-Instruct | 40 | 131K | Credit-metered | Online | ||
| Gemini 2.5 Flash-Lite Verified Gemini 2.5 Flash-Lite | 40 | 1.0M | Online | |||
| Pixtral Large | 40 | 128K | ~1 RPS, 500K TPM | Online | ||
| Mistral Large (24.11) | 40 | 131K | See provider page | Online | ||
| meituan-longcat/LongCat-Flash-Lite Verified | 39 | 8K | Online | |||
| 39 | 8K | Online | ||||
| 39 | 8K | Online | ||||
| 39 | 8K | Online | ||||
| @cf/google/gemma-7b-it-lora Verified | 39 | 8K | Online | |||
| 39 | 131K | Online | ||||
| big-pickle Verified | 39 | N/A | Online | |||
| Qwen/Qwen3-Next-80B-A3B-Instruct Verified Qwen: Qwen3 Next 80B A3B Instruct (free) | 39 | 8K | Online | |||
| Qwen/Qwen3-VL-8B-Thinking Verified Qwen: Qwen3 VL 8B Thinking | 39 | 8K | Online | |||
| Qwen/Qwen3-235B-A22B Verified Qwen: Qwen3 235B A22B | 39 | 8K | Online | |||
| meta/llama-3.1-70b-instruct | 39 | 131K | Unlimited for free models | Online | ||
| @cf/qwen/qwen2.5-coder-32b-instruct Verified @cf/qwen/qwen2.5-coder-32b-instruct | 39 | 8K | Online | |||
| Qwen/Qwen3-VL-8B-Instruct Verified Qwen: Qwen3 VL 8B Instruct | 38 | 8K | Online | |||
| 37 | 8K | Online | ||||
| nvidia/nvidia-nemotron-nano-9b-v2 Verified | 37 | 8K | Online | |||
| nvidia/llama-3.1-nemotron-nano-8b-v1 Verified | 37 | 8K | Online | |||
| nvidia/nv-embed-v1 Verified | 37 | 131K | Up to 40 RPM | Online | ||
| nvidia/nv-embedcode-7b-v1 Verified | 37 | 131K | Up to 40 RPM | Online | ||
| Hy3 preview Verified | 37 | 256K | Online | |||
| Qwen/Qwen3-235B-A22B-Thinking-2507 Verified Qwen: Qwen3 235B A22B Thinking 2507 | 37 | 8K | Online | |||
| meta/llama-guard-4-12b Verified meta/llama-guard-4-12b | 37 | 164K | Up to 40 RPM | Online | ||
| Qwen/Qwen3-Next-80B-A3B-Thinking Verified Qwen: Qwen3 Next 80B A3B Thinking | 36 | 8K | Online | |||
| Llama-3.3-70B-Instruct Verified Meta: Llama 3.3 70B Instruct (free) | 36 | 128K | Online | |||
| Qwen/Qwen3-30B-A3B Verified Qwen: Qwen3 30B A3B | 35 | 8K | Online | |||
| mistralai/Mistral-Large-Instruct-2407 | 35 | 8K | Online | |||
| PaddlePaddle/ERNIE-4.5-0.3B-PT Verified | 34 | 8K | Online | |||
| 34 | 128K | Online | ||||
| @cf/qwen/qwen3-30b-a3b-fp8 Verified Qwen: Qwen3 30B A3B | 34 | 8K | Online | |||
| Qwen/Qwen3-30B-A3B-Thinking-2507 Verified Qwen: Qwen3 30B A3B Thinking 2507 | 34 | 8K | Online | |||
| Meta-Llama-3.1-8B-Instruct Verified llama-3.1-8b-instant | 34 | 128K | Credit-metered | Online | ||
| Qwen/Qwen3-32B Verified Qwen: Qwen3 32B | 33 | 8K | Online | |||
| 32 | 131K | $25/month free credits, resets monthly | Online | |||
| 32 | 8K | Online | ||||
| 32 | 8K | Online | ||||
| Qwen/Qwen3-14B Verified Qwen: Qwen3 14B | 32 | 8K | Online | |||
| meta/llama-3.1-8b-instruct Verified llama-3.1-8b-instant | 32 | 8K | Online | |||
| google/gemma-3n-e4b-it Verified google/gemma-3n-e4b-it | 32 | 8K | Online | |||
| 30 | 8K | Online | ||||
| 30 | 8K | Online | ||||
| Qwen/Qwen3-8B Verified Qwen: Qwen3 8B | 30 | 8K | Online | |||
| @cf/meta/llama-3.2-3b-instruct Verified Meta: Llama 3.2 3B Instruct (free) | 29 | 8K | Online | |||
| @cf/meta/llama-3.1-8b-instruct-fp8 Verified llama-3.1-8b-instant | 28 | 8K | Online | |||
| @cf/meta/llama-3.2-1b-instruct Verified meta/llama-3.2-1b-instruct | 28 | 8K | Online | |||
| @cf/meta/llama-guard-3-8b Verified | 27 | 8K | Online | |||
| @cf/qwen/qwen3-embedding-0.6b Verified | 27 | 8K | Online | |||
| @cf/pfnet/plamo-embedding-1b Verified | 27 | 8K | Online | |||
| @cf/google/embeddinggemma-300m Verified | 27 | 8K | Online |
How to Get Started with Free LLM APIs
- Pick a free LLM model — Click any model name to see details, rate limits, and API key signup link.
- Get your API key — Sign up on the provider's website (most require no credit card).
- Copy the config — Go to the Config Generator, pick your tool and backend, copy the ready-to-use snippet.
- Test it — Use the Playground to test your API key before integrating.
New to LLM terminology? Check the 📖 Glossary — 22 terms explained in plain English →
FAQ: Common questions about free LLM APIs →About This Free LLM API Directory
Finding reliable free LLM API resources online can be frustrating. Many developers traditionally rely on static GitHub repositories to find endpoints. While those lists are a good starting point, they often become outdated quickly, leaving you with dead links, expired API keys, and unverified rate limits.
That's why we built this dynamic, auto-updating directory. If you are looking for a reliable alternative to GitHub free LLM API lists, this page tracks over 350 free LLM models online in real-time. Whether you need a free API key for text generation, vision, or coding tasks, you can compare context windows, capabilities, and strict rate limit data side-by-side.
Our goal is to be the most accurate and comprehensive list of free AI APIs for developers. Use the filters above to find providers that don't require credit cards or phone verification, and grab your free API keys to start building immediately.