Free LLM Models — Browse & Filter 136+ Models
Showing 136 of 136 free LLM models
Browse 136+ free LLM models from 25 providers. Filter by provider, modality, rate limit — find the perfect model for your project.
53 models verified via live API · refreshed Jun 19, 2026 — how we verify
| Provider | Model | Score | Context | Modality | Rate Limit | Status |
|---|---|---|---|---|---|---|
| | 101 | 1.0M | 200 req/day (free tier) | Online | ||
| | 97 | 262K | 200 req/day (free tier) | Online | ||
| minimaxai/minimax-m3 Verified | 95 | 1.0M | Up to 40 RPM | Online | ||
| | 94 | 203K | 200 req/day (free tier) | Online | ||
| moonshotai/kimi-k2.6 Verified | 91 | 262K | Up to 40 RPM | Online | ||
| Gemini 3.5 Flash | 90 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| DeepSeek: DeepSeek V4 Flash | 89 | 1.0M | 200 req/day (free tier) | Online | ||
| z-ai/glm-5.1 Verified | 88 | 203K | Up to 40 RPM | Online | ||
| | 88 | 262K | 200 req/day (free tier) | Online | ||
| NVIDIA: Nemotron 3 Ultra (free) Verified NVIDIA: Nemotron 3 Ultra (free) | 88 | 1.0M | 200 req/day (free tier) | Online | ||
| stepfun-ai/step-3.7-flash Verified | 87 | 256K | Up to 40 RPM | Online | ||
| deepseek-ai/deepseek-v4-pro Verified deepseek-ai/deepseek-v4-pro | 86 | 1.0M | Up to 40 RPM | Online | ||
| minimaxai/minimax-m2.7 Verified | 85 | 205K | Up to 40 RPM | Online | ||
| | 84 | 205K | 200 req/day (free tier) | Online | ||
| deepseek-ai/deepseek-v4-flash Verified DeepSeek: DeepSeek V4 Flash | 83 | 1.0M | Up to 40 RPM | Online | ||
| Qwen3.6-27B | 82 | 131K | 2 RPM (anonymous) | Online | ||
| 81 | 196K | ~200 req/hr | Online | |||
| | 80 | 262K | 200 req/day (free tier) | Online | ||
| Cohere: North Mini Code (free) Verified Cohere: North Mini Code (free) | 80 | 256K | 200 req/day (free tier) | Online | ||
| Nex AGI: Nex-N2-Pro (free) Verified Nex AGI: Nex-N2-Pro (free) | 78 | 262K | 200 req/day (free tier) | Online | ||
| 77 | 131K | ~200 req/hr | Online | |||
| Google: Gemma 4 31B (free) Verified Google: Gemma 4 31B (free) | 77 | 262K | 200 req/day (free tier) | Online | ||
| stepfun-ai/step-3.5-flash Verified | 74 | 262K | Up to 40 RPM | Online | ||
| Qwen/Qwen3.5-27B | 74 | 131K | 2,000 RPD total; <=500 RPD/model (dynamic) | Online | ||
| Google: Gemma 4 26B A4B (free) Verified Google: Gemma 4 26B A4B (free) | 74 | 262K | 200 req/day (free tier) | Online | ||
| Qwen3.5-9B | 73 | 131K | 2 RPM (anonymous) | Online | ||
| Qwen3.5-397B-A17B | 73 | 131K | 2 RPM (anonymous) | Online | ||
| NVIDIA: Nemotron 3 Nano Omni (free) Verified NVIDIA: Nemotron 3 Nano Omni (free) | 72 | 256K | 200 req/day (free tier) | Online | ||
| MiniMax-M2.7 | 72 | 128K | 20 RPM, 20 RPD, 200K TPD | Online | ||
| NVIDIA: Nemotron 3 Super (free) Verified NVIDIA: Nemotron 3 Super (free) | 72 | 1.0M | 200 req/day (free tier) | Online | ||
| Owl Alpha Verified | 70 | 1.0M | 200 req/day (free tier) | Online | ||
| qwen/qwen3.5-397b-a17b Verified Qwen3.5-397B-A17B | 70 | 256K | Up to 40 RPM | Online | ||
| qwen/qwen3.5-122b-a10b Verified qwen/qwen3.5-122b-a10b | 70 | 262K | Up to 40 RPM | Online | ||
| Poolside: Laguna XS.2 (free) Verified | 69 | 262K | 200 req/day (free tier) | Online | ||
| Poolside: Laguna M.1 (free) Verified | 69 | 262K | 200 req/day (free tier) | Online | ||
| Qwen/Qwen3.5-35B-A3B | 69 | 131K | 2,000 RPD total; <=500 RPD/model (dynamic) | Online | ||
| NVIDIA: Nemotron 3 Super (free) | 68 | 262K | ~200 req/hr | Online | ||
| OpenAI: gpt-oss-120b (free) Verified | 67 | 131K | 200 req/day (free tier) | Online | ||
| Gemini 3.1 Flash-Lite | 67 | 1.0M | 30 RPM, 1,500 RPD | Online | ||
| Google: Gemma 4 26B A4B (free) | 66 | 256K | 10K neurons/day (shared) | Online | ||
| 65 | 256K | ~1 RPS, 500K TPM | Online | |||
| 64 | 128K | Session/weekly limits (unpublished) | Online | |||
| 64 | 128K | Session/weekly limits (unpublished) | Online | |||
| GLM-4.7-Flash | 64 | 200K | 1 concurrent request | Online | ||
| NVIDIA: Nemotron 3 Nano 30B A3B (free) | 63 | 256K | 200 req/day (free tier) | Online | ||
| 62 | 256K | ~200 req/hr | Online | |||
| 61 | 131K | ~200 req/hr | Online | |||
| OpenAI: gpt-oss-20b (free) Verified | 60 | 131K | 200 req/day (free tier) | Online | ||
| Nous: Hermes 3 405B Instruct (free) Verified | 60 | 131K | 200 req/day (free tier) | Online | ||
| o4-mini | 60 | 200K | 10 RPM, 50 RPD | Online | ||
| Qwen: Qwen3 Coder 480B A35B (free) Verified Qwen: Qwen3 Coder 480B A35B (free) | 60 | 1.0M | 200 req/day (free tier) | Online | ||
| 59 | 128K | Session/weekly limits (unpublished) | Online | |||
| 59 | 128K | Session/weekly limits (unpublished) | Online | |||
| | 59 | 131K | 200 req/day (free tier) | Online | ||
| 59 | 128K | 20 RPM, 20 RPD, 200K TPD | Online | |||
| 58 | 128K | 10 RPM, 100 RPD, 1M TPD | Online | |||
| Gemini 2.5 Pro | 58 | 2.0M | 5 RPM, 50 RPD | Online | ||
| NVIDIA: Nemotron 3.5 Content Safety (free) | 58 | 128K | 200 req/day (free tier) | Online | ||
| gpt-4.1 | 57 | 1.0M | 10 RPM, 50 RPD | Online | ||
| Google: Lyria 3 Pro Preview Verified Google: Lyria 3 Pro Preview | 57 | 1.0M | 200 req/day (free tier) | Online | ||
| Google: Lyria 3 Clip Preview Verified Google: Lyria 3 Clip Preview | 57 | 1.0M | 200 req/day (free tier) | Online | ||
| Qwen: Qwen3 Next 80B A3B Instruct (free) | 57 | 262K | 200 req/day (free tier) | Online | ||
| 56 | 128K | 10K neurons/day (shared) | Online | |||
| 55 | 256K | ~1 RPS, 500K TPM | Online | |||
| deepseek-r1-0528 | 55 | 131K | 30 RPM (120 with token) | Online | ||
| gpt-4.1-mini | 55 | 1.0M | 15 RPM, 150 RPD | Online | ||
| gpt-5 | 55 | 200K | 10 RPM, 50 RPD | Online | ||
| Qwen3-Coder-30B-A3B-Instruct | 55 | 262K | 2 RPM (anonymous) | Online | ||
| 54 | 512K | 15 RPM, 150 RPD | Online | |||
| NVIDIA: Nemotron Nano 12B 2 VL (free) | 54 | 128K | 200 req/day (free tier) | Online | ||
| gpt-oss-120b | 54 | 128K | 30 RPM, 14,400 RPD, 1M TPD | Online | ||
| 53 | 128K | 2 RPM (anonymous) | Online | |||
| 53 | 256K | 10 RPM, 50 RPD | Online | |||
| 53 | 262K | Session/weekly limits (unpublished) | Online | |||
| 53 | 33K | 200 req/day (free tier) | Online | |||
| 52 | 128K | Session/weekly limits (unpublished) | Online | |||
| Venice: Uncensored (free) Verified | 52 | 33K | 200 req/day (free tier) | Online | ||
| 52 | 256K | ~1 RPS, 500K TPM | Online | |||
| 52 | 131K | 10K neurons/day (shared) | Online | |||
| nvidia/nemotron-3.5-content-safety Verified NVIDIA: Nemotron 3.5 Content Safety (free) | 52 | 128K | Up to 40 RPM | Online | ||
| deepseek-v3-0324 | 52 | 131K | 30 RPM (120 with token) | Online | ||
| DeepSeek-V3.1 | 52 | 128K | 20 RPM, 20 RPD, 200K TPD | Online | ||
| NVIDIA: Nemotron Nano 9B V2 (free) Verified NVIDIA: Nemotron Nano 9B V2 (free) | 52 | 128K | 200 req/day (free tier) | Online | ||
| 51 | 131K | 30 RPM, 1,000 RPD | Online | |||
| 51 | 33K | 200 req/day (free tier) | Online | |||
| gpt-4o | 51 | 128K | 10 RPM, 50 RPD | Online | ||
| Gemini 2.5 Flash | 51 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| Aion 2.0 | 51 | 128K | 15 RPM, 20K TPD | Online | ||
| 50 | 10.0M | 10K neurons/day (shared) | Online | |||
| Meta: Llama 3.3 70B Instruct (free) Verified Meta: Llama 3.3 70B Instruct (free) | 50 | 131K | 200 req/day (free tier) | Online | ||
| nvidia/llama-3.3-nemotron-super-49b-v1.5 | 50 | 131K | Up to 40 RPM | Online | ||
| Free Models Router Verified | 49 | 200K | 200 req/day (free tier) | Online | ||
| 49 | 128K | 1 concurrent request | Online | |||
| 49 | 262K | 10K neurons/day (shared) | Online | |||
| 49 | 256K | ~1 RPS, 500K TPM | Online | |||
| Qwen2.5-VL-72B-Instruct | 49 | 128K | 2 RPM (anonymous) | Online | ||
| Mistral-Small-3.2-24B-Instruct | 49 | 128K | 2 RPM (anonymous) | Online | ||
| gemini-2.5-flash-lite | 49 | 131K | 30 RPM (120 with token) | Online | ||
| gpt-oss-20b | 49 | 128K | 2 RPM (anonymous) | Online | ||
| Meta: Llama 3.2 3B Instruct (free) Verified Meta: Llama 3.2 3B Instruct (free) | 49 | 131K | 200 req/day (free tier) | Online | ||
| mistral-small-3.1-24b | 48 | 32K | 30 RPM (120 with token) | Online | ||
| 47 | 128K | ~1 RPS, 500K TPM | Online | |||
| 47 | 128K | 20 RPM, 20 RPD, 200K TPD | Online | |||
| Meta: Llama 3.3 70B Instruct (free) | 47 | 131K | 2 RPM (anonymous) | Online | ||
| qwen2.5-coder-32b | 47 | 131K | 30 RPM (120 with token) | Online | ||
| gpt-4o-mini | 47 | 131K | 30 RPM (120 with token) | Online | ||
| qwen3-32b | 47 | 131K | 30 RPM, 1,000 RPD | Online | ||
| 46 | 128K | 15 RPM, 150 RPD | Online | |||
| 46 | 131K | See provider page | Online | |||
| Meta: Llama 3.3 70B Instruct (free) | 46 | 131K | 15 RPM, 150 RPD | Online | ||
| DeepSeek-R1 | 46 | 64K | 15 RPM, 150 RPD | Online | ||
| 45 | 32K | Credit-metered | Online | |||
| Meta: Llama 3.3 70B Instruct (free) | 45 | 131K | 30 RPM, 1,000 RPD | Online | ||
| mistral-small-3.1-24b | 45 | 128K | 10K neurons/day (shared) | Online | ||
| @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | 45 | 32K | 10K neurons/day (shared) | Online | ||
| 44 | 256K | 20 RPM | Online | |||
| | 44 | 131K | 200 req/day (free tier) | Online | ||
| 44 | 131K | 30 RPM, 60K TPM | Online | |||
| 44 | 128K | Credit-metered | Online | |||
| 44 | 128K | 20 RPM | Online | |||
| 44 | 128K | 20 RPM | Online | |||
| 44 | 128K | 20 RPM | Online | |||
| 44 | 128K | ~1 RPS, 500K TPM | Online | |||
| 44 | 128K | 15 RPM, 20K TPD | Online | |||
| Llama-3.1-8B-Instruct | 44 | 131K | 2 RPM (anonymous) | Online | ||
| 43 | 32K | Credit-metered | Online | |||
| meta/llama-3.2-3b-instruct Verified Meta: Llama 3.2 3B Instruct (free) | 43 | 131K | Up to 40 RPM | Online | ||
| meta/llama-3.1-70b-instruct Verified meta/llama-3.1-70b-instruct | 43 | 131K | Up to 40 RPM | Online | ||
| Meta: Llama 3.3 70B Instruct (free) | 42 | 131K | 10K neurons/day (shared) | Online | ||
| Llama-3.1-8B-Instruct | 42 | 131K | 30 RPM, 1,000 RPD | Online | ||
| 41 | 32K | 15 RPM, 20K TPD | Online | |||
| Qwen2.5-7B-Instruct | 40 | 131K | Credit-metered | Online | ||
| meta/llama-3.2-11b-vision-instruct Verified meta/llama-3.2-11b-vision-instruct | 40 | 131K | Up to 40 RPM | Online | ||
| meta/llama-3.2-1b-instruct Verified meta/llama-3.2-1b-instruct | 38 | 131K | Up to 40 RPM | Online | ||
| Llama-3.1-8B-Instruct | 36 | 128K | Credit-metered | Online | ||
| meta/llama-guard-4-12b Verified meta/llama-guard-4-12b | 34 | 164K | Up to 40 RPM | Online |
How to Use Free LLM API Resources
- 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 →