Directory of Free LLM APIs: Compare 303+ Models
Showing 303 of 303 free LLM models
Discover and filter 303+ free LLM models across 31 providers. Find APIs by capability (vision, reasoning), rate limits, or no-credit-card requirements, and get the perfect free AI model for your project.
246 models verified via live API · latest update Sep 9, 2026 — how we verify
| Provider | Model | Score | Context | Modality | Rate Limit | Status |
|---|---|---|---|---|---|---|
| deepseek-v4-pro Verified deepseek-v4-pro | 94 | 1.0M | Session/weekly limits (unpublished) | Online | ||
| deepseek-v4-pro Verified deepseek-v4-pro | 94 | 1.0M | Session/weekly limits (unpublished) | Online | ||
| deepseek-v4-flash Verified deepseek-v4-flash | 93 | 1.0M | Session/weekly limits (unpublished) | Online | ||
| deepseek-v4-flash Verified deepseek-v4-flash | 93 | 1.0M | Session/weekly limits (unpublished) | Online | ||
| Kimi K3 Verified | 92 | 1.0M | Online | |||
| deepseek-ai/deepseek-v4-pro-0813 Verified deepseek-ai/deepseek-v4-pro-0813 | 92 | 1.0M | Up to 40 RPM | Online | ||
| deepseek-ai/deepseek-v4-pro Verified deepseek-v4-pro | 92 | 1.0M | Up to 40 RPM | Online | ||
| deepseek-ai/deepseek-v4-flash-0731 Verified deepseek-ai/deepseek-v4-flash-0731 | 90 | 1.3M | Up to 40 RPM | Online | ||
| deepseek-ai/deepseek-v4-flash Verified deepseek-v4-flash | 90 | 1.0M | Up to 40 RPM | Online | ||
| Gemini 3.8 Flash Verified Gemini 3.8 Flash | 83 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| agnes-2.0-flash Verified | 88 | 256K | 30 RPM | Online | ||
| 85 | 262K | 200 req/day (free tier) | Online | |||
| inclusionAI: Ling 3.0 Flash Fin (free) | 85 | 262K | 200 req/day (free tier) | Online | ||
| inclusionAI: Ling 3.0 Flash Fin (free) | 84 | 1.0M | 200 req/day (free tier) | Online | ||
| Qwen/Qwen3.8-Flash-Next Verified | 83 | 8K | Online | |||
| Gemini 3.7 Flash Verified Gemini 3.7 Flash | 89 | 1.0M | — | Online | ||
| Gemini 3.6 Flash Verified Gemini 3.6 Flash | 83 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| Qwen/Qwen3.8-27B Verified Qwen/Qwen3.8-27B | 83 | 8K | Online | |||
| Thinking Machines: Inkling (free) Verified | 82 | 1.0M | 200 req/day (free tier) | Online | ||
| GLM-5.1 Verified | 81 | 1.0M | Online | |||
| minimax-m3 Verified minimax-m3 | 81 | 512K | Session/weekly limits (unpublished) | Online | ||
| 80 | 262K | 200 req/hr | Online | |||
| DeepSeek V4 Flash 0731 Verified deepseek-v4-flash | 80 | 1.0M | Online | |||
| DeepSeek V4 Flash 0731 Verified deepseek-v4-flash | 80 | 1.0M | Online | |||
| minimaxai/minimax-m3 Verified minimaxai/minimax-m3 | 79 | 1.0M | Up to 40 RPM | Online | ||
| @cf/qwen/qwen3.8-27b Verified Qwen/Qwen3.8-27B | 78 | 8K | Online | |||
| deepseek-ai/DeepSeek-V4-Pro Verified deepseek-v4-pro | 78 | 8K | Online | |||
| deepseek-ai/DeepSeek-V4-Pro-0813 Verified deepseek-ai/deepseek-v4-pro-0813 | 78 | 8K | Online | |||
| glm-5.3-flash Verified | 78 | 0 | See provider page | Online | ||
| Nex AGI: Nex-N2.5-Pro (free) Verified | 77 | 262K | 200 req/day (free tier) | Online | ||
| Gemini 3.5 Flash Verified Gemini 3.5 Flash | 77 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| NVIDIA: Nemotron 3 Ultra (free) Verified NVIDIA: Nemotron 3 Ultra (free) | 77 | 1.0M | 200 req/day (free tier) | Online | ||
| deepseek-ai/DeepSeek-V4-Flash Verified deepseek-v4-flash | 77 | 8K | Online | |||
| NVIDIA: Nemotron 3 Ultra (free) | 75 | 1.0M | 200 req/hr | Online | ||
| moonshotai/kimi-k2.6 Verified moonshotai/kimi-k2.6 | 74 | 262K | Up to 40 RPM | Online | ||
| Gemini 3.5 Flash-Lite Verified Gemini 3.5 Flash-Lite | 72 | 1.0M | 30 RPM, 1,500 RPD | Online | ||
| deepseek-v4-flash Verified deepseek-v4-flash | 72 | 0 | See provider page | Online | ||
| NVIDIA: Nemotron 3.5 Lightning (free) | 71 | 1.0M | 200 req/day (free tier) | Online | ||
| 71 | 512K | 200 req/day (free tier) | Online | |||
| nemotron-3-ultra Verified | 71 | 262K | Session/weekly limits (unpublished) | Online | ||
| 70 | 262K | 200 req/hr | Online | |||
| NVIDIA: Nemotron 3.5 Lightning (free) | 69 | 1.0M | 200 req/hr | Online | ||
| Nex AGI: Nex-N2.5-Mini (free) Verified | 69 | 262K | 200 req/day (free tier) | Online | ||
| Poolside: Laguna S 2.1 (free) Verified Poolside: Laguna S 2.1 (free) | 69 | 262K | 200 req/day (free tier) | Online | ||
| Qwen3.6-27B | 69 | 131K | 2 RPM (anonymous) | Online | ||
| MiniMax-M3 Verified | 69 | 512K | Online | |||
| Poolside: Laguna XS 2.1 (free) Verified Poolside: Laguna S 2.1 (free) | 67 | 262K | 200 req/day (free tier) | Online | ||
| Poolside: Laguna S 2.1 (free) | 67 | 262K | 200 req/hr | Online | ||
| Nemotron 3 Ultra 550B A55B Verified NVIDIA: Nemotron 3 Ultra (free) | 66 | 1.0M | Online | |||
| Tencent-Hunyuan/Hy3 Verified | 66 | 8K | Online | |||
| Cohere: North Mini Code (free) Verified Cohere: North Mini Code (free) | 66 | 256K | 200 req/day (free tier) | Online | ||
| minimax-m2.7 Verified minimax-m2.7 | 66 | 180K | 10 RPM, 60 req/hr (anonymous) | Online | ||
| Poolside: Laguna S 2.1 (free) | 65 | 262K | 200 req/hr | Online | ||
| NVIDIA: Nemotron 3 Nano Omni (free) Verified NVIDIA: Nemotron 3 Nano Omni (free) | 65 | 256K | 200 req/day (free tier) | Online | ||
| Google: Gemma 4 26B A4B (free) Verified Google: Gemma 4 26B A4B (free) | 65 | 262K | 200 req/day (free tier) | Online | ||
| Google: Gemma 4 31B (free) Verified Google: Gemma 4 31B (free) | 64 | 262K | 200 req/day (free tier) | Online | ||
| GLM-4.7-Flash Verified GLM-4.7-Flash | 64 | 200K | 1 concurrent request | Online | ||
| Cohere: North Mini Code (free) | 64 | 256K | 200 req/hr | Online | ||
| poolside/laguna-xs-2.1 Verified Poolside: Laguna S 2.1 (free) | 64 | 262K | Up to 40 RPM | Online | ||
| LiquidAI: LFM2.5-2.6B (free) Verified | 64 | 66K | 200 req/day (free tier) | Online | ||
| GLM-4.7-Flash Verified GLM-4.7-Flash | 63 | 200K | 1 concurrent request | Online | ||
| NVIDIA: Nemotron 3 Nano Omni (free) | 63 | 256K | 200 req/hr | Online | ||
| Gemma 4 26B A4B Verified Gemma 4 26B A4B | 62 | 262K | — | Online | ||
| 61 | 64K | 200 req/hr | Online | |||
| Qwen3.5-397B-A17B | 61 | 131K | 2 RPM (anonymous) | Online | ||
| NVIDIA: Nemotron 3 Super (free) Verified NVIDIA: Nemotron 3 Super (free) | 60 | 262K | 200 req/day (free tier) | Online | ||
| 01-ai/yi-large Verified | 60 | 131K | Up to 40 RPM | Online | ||
| meta/codellama-70b Verified | 60 | 131K | Up to 40 RPM | Online | ||
| nvidia/llama3-chatqa-1.5-70b Verified | 60 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-fin-70b-32k Verified | 60 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-med-70b Verified | 60 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-med-70b-32k Verified | 60 | 131K | Up to 40 RPM | Online | ||
| @cf/moonshotai/kimi-k2.7-code Verified moonshotai/kimi-k2.6 | 59 | 262K | 10K neurons/day (shared) | Online | ||
| Muse Glimmer 30B Verified Muse Glimmer 30B | 59 | 131K | Online | |||
| @cf/google/gemma-4-26b-a4b-it Verified Google: Gemma 4 26B A4B (free) | 59 | 256K | 10K neurons/day (shared) | Online | ||
| NVIDIA: Nemotron 3 Super (free) | 58 | 262K | 200 req/hr | Online | ||
| stepfun-ai/Step-3.7-Flash Verified | 58 | 8K | Online | |||
| Nemotron 3 Super 120B A12B Verified | 58 | 262K | Online | |||
| Gemma 4 26B A4B IT Verified Google: Gemma 4 26B A4B (free) | 58 | 262K | Varies by model and account | Online | ||
| Nemotron 3 Ultra 550B A55B Verified | 58 | 1.0M | Online | |||
| Gemma 4 31B Verified Gemma 4 26B A4B | 57 | 262K | — | Online | ||
| Gemma 4 31B IT Verified Google: Gemma 4 31B (free) | 57 | 262K | Varies by model and account | Online | ||
| nvidia/llama-3.1-nemotron-ultra-253b-v1 | 56 | 131K | Up to 40 RPM | Online | ||
| ibm/granite-34b-code-instruct Verified | 55 | 131K | Up to 40 RPM | Online | ||
| LongCat-2.0 Verified | 55 | 0 | See provider page | Online | ||
| Qwen3.5-9B | 54 | 131K | 2 RPM (anonymous) | Online | ||
| GLM-4.6V-Flash Verified GLM-4.6V-Flash | 54 | 128K | 1 concurrent request | Online | ||
| NVIDIA: Nemotron 3 Nano Omni (free) | 54 | 256K | Online | |||
| agnes-1.5-flash Verified | 54 | 256K | 30 RPM | Online | ||
| Gemini 3.1 Flash-Lite Verified Gemini 3.1 Flash-Lite | 54 | 1.0M | 30 RPM, 1,500 RPD | Online | ||
| Gemma 4 31B IT Verified Google: Gemma 4 31B (free) | 54 | 262K | Online | |||
| Ling 3.0 Flash Fin Verified | 53 | 262K | Online | |||
| 53 | 131K | See provider page | Online | |||
| 53 | 131K | See provider page | Online | |||
| @cf/zai-org/glm-4.7-flash Verified | 53 | 131K | 10K neurons/day (shared) | Online | ||
| Gemma 4 31B IT Verified | 53 | 262K | Online | |||
| @cf/openai/gpt-oss-120b Verified | 53 | 128K | 10K neurons/day (shared) | Online | ||
| bigcode/starcoder2-15b Verified | 53 | 131K | Up to 40 RPM | Online | ||
| google/deplot Verified | 53 | 131K | Up to 40 RPM | Online | ||
| google/gemma-2b Verified | 53 | 131K | Up to 40 RPM | Online | ||
| google/recurrentgemma-2b Verified | 53 | 131K | Up to 40 RPM | Online | ||
| microsoft/kosmos-2 Verified | 53 | 131K | Up to 40 RPM | Online | ||
| microsoft/phi-3-vision-128k-instruct Verified | 53 | 131K | Up to 40 RPM | Online | ||
| microsoft/phi-3.5-moe-instruct Verified | 53 | 131K | Up to 40 RPM | Online | ||
| mistralai/mixtral-8x22b-v0.1 Verified | 53 | 131K | Up to 40 RPM | Online | ||
| 53 | 131K | Up to 40 RPM | Online | |||
| nvidia/nemotron-4-340b-instruct Verified | 53 | 131K | Up to 40 RPM | Online | ||
| nvidia/nemotron-4-340b-reward Verified | 53 | 131K | Up to 40 RPM | Online | ||
| nvidia/nemotron-parse Verified | 53 | 131K | Up to 40 RPM | Online | ||
| nvidia/neva-22b Verified | 53 | 131K | Up to 40 RPM | Online | ||
| nvidia/nvclip Verified | 53 | 131K | Up to 40 RPM | Online | ||
| nvidia/riva-translate-4b-instruct Verified | 53 | 131K | Up to 40 RPM | Online | ||
| nvidia/vila Verified | 53 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-creative-122b Verified | 53 | 131K | Up to 40 RPM | Online | ||
| GLM-4.6V-Flash Verified GLM-4.6V-Flash | 52 | 128K | 1 concurrent request | Online | ||
| NVIDIA: Nemotron 3.5 Content Safety (free) | 52 | 128K | 200 req/day (free tier) | Online | ||
| google/diffusiongemma-26b-a4b-it Verified | 52 | 8K | Online | |||
| 51 | 256K | See provider page | Online | |||
| gpt-oss:120b Verified gpt-oss:120b | 51 | 128K | Session/weekly limits (unpublished) | Online | ||
| adept/fuyu-8b Verified | 51 | 131K | Up to 40 RPM | Online | ||
| aisingapore/sea-lion-7b-instruct Verified | 51 | 131K | Up to 40 RPM | Online | ||
| 51 | 131K | Up to 40 RPM | Online | |||
| google/codegemma-1.1-7b Verified | 51 | 131K | Up to 40 RPM | Online | ||
| google/codegemma-7b Verified | 51 | 131K | Up to 40 RPM | Online | ||
| ibm/granite-3.0-8b-instruct Verified | 51 | 131K | Up to 40 RPM | Online | ||
| ibm/granite-8b-code-instruct Verified | 51 | 131K | Up to 40 RPM | Online | ||
| 51 | 131K | Up to 40 RPM | Online | |||
| 51 | 131K | Up to 40 RPM | Online | |||
| zyphra/zamba2-7b-instruct Verified | 51 | 131K | Up to 40 RPM | Online | ||
| agnes-image-2.0-flash Verified | 51 | 4K | 30 RPM (1K) | Online | ||
| agnes-image-2.1-flash Verified | 51 | 4K | 30 RPM (1K) | Online | ||
| 51 | 256K | ~1 RPS, 500K TPM | Online | |||
| Gemma 4 31B IT Verified | 50 | 262K | Online | |||
| nvidia/cosmos-reason2-8b Verified | 50 | 131K | Up to 40 RPM | Online | ||
| Nemotron 3 Super 120B A12B Verified NVIDIA: Nemotron 3 Super (free) | 50 | 262K | Online | |||
| Google: Lyria 3 Pro Preview Verified Google: Lyria 3 Pro Preview | 50 | 1.0M | 200 req/day (free tier) | Online | ||
| Google: Lyria 3 Clip Preview Verified Google: Lyria 3 Clip Preview | 50 | 1.0M | 200 req/day (free tier) | Online | ||
| Qwen3-Coder-30B-A3B-Instruct | 49 | 262K | 2 RPM (anonymous) | Online | ||
| Qwen/Qwen3.5-397B-A17B Verified Qwen3.5-397B-A17B | 49 | 8K | Online | |||
| mistralai/codestral-22b-instruct-v0.1 | 49 | 131K | Up to 40 RPM | Online | ||
| groq/compound Verified | 49 | 131K | 30 RPM, 250 RPD | Online | ||
| nvidia/nemotron-3.5-content-safety Verified NVIDIA: Nemotron 3.5 Content Safety (free) | 49 | 128K | Up to 40 RPM | Online | ||
| 49 | 256K | ~1 RPS, 500K TPM | Online | |||
| mistral-Nemo-Instruct-2407 Verified mistral-Nemo-Instruct-2407 | 48 | 128K | 10 RPM, 60 req/hr (anonymous) | Online | ||
| agnes-video-v2.0 Verified | 48 | 4K | 2 RPM | Online | ||
| Gemini 2.5 Pro Verified Gemini 2.5 Pro | 48 | 1.0M | 5 RPM, 50 RPD | Online | ||
| Qwen2.5-VL-72B-Instruct | 48 | 128K | 2 RPM (anonymous) | Online | ||
| Mistral-Small-3.2-24B-Instruct | 48 | 128K | 2 RPM (anonymous) | Online | ||
| mistralai/mistral-nemotron Verified | 48 | 8K | Online | |||
| Qwen/Qwen3.5-122B-A10B Verified Qwen/Qwen3.5-122B-A10B | 48 | 8K | Online | |||
| 47 | 128K | ~1 RPS, 500K TPM | Online | |||
| Gemini 2.5 Flash Verified Gemini 2.5 Flash | 47 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| @cf/nvidia/nemotron-3-120b-a12b Verified | 47 | 8K | Online | |||
| @cf/baai/bge-large-en-v1.5 Verified | 47 | 8K | Online | |||
| MiMo-V2.5 Verified | 47 | 1.0M | Online | |||
| mistralai/mistral-7b-instruct-v0.3 Verified | 47 | 131K | Up to 40 RPM | Online | ||
| groq/compound-mini Verified | 47 | 131K | 30 RPM, 250 RPD | Online | ||
| gpt-oss:20b Verified gpt-oss:20b | 47 | 131K | Session/weekly limits (unpublished) | Online | ||
| Gemini 3.1 Flash Lite Verified Gemini 3.1 Flash-Lite | 47 | 1.0M | Online | |||
| GLM-4.5-Flash (retirement announced) Verified GLM-4.5-Flash (retirement announced) | 47 | 128K | 1 concurrent request | Online | ||
| 47 | 256K | 20 RPM | Online | |||
| 47 | 256K | 20 RPM | Online | |||
| Gemini 3.1 Flash Lite Verified Gemini 3.1 Flash-Lite | 46 | 1.0M | Online | |||
| 46 | 128K | 20 RPM | Online | |||
| 46 | 128K | 20 RPM | Online | |||
| 46 | 128K | 20 RPM | Online | |||
| 46 | 128K | 20 RPM | Online | |||
| 46 | 128K | 20 RPM | Online | |||
| Mixtral 8x7B Verified | 46 | 33K | Unlimited for free models | Online | ||
| GLM-4.5-Flash Verified GLM-4.5-Flash | 46 | 128K | 1 concurrent request | Online | ||
| GLM-4.5-Flash Verified GLM-4.5-Flash | 46 | 128K | 1 concurrent request | Online | ||
| 46 | 131K | 10K neurons/day (shared) | Online | |||
| @cf/mistralai/mistral-small-3.1-24b-instruct | 46 | 128K | 10K neurons/day (shared) | Online | ||
| ibm/granite-3.0-3b-a800m-instruct Verified | 46 | 131K | Up to 40 RPM | Online | ||
| 46 | 32K | 2 RPM (anonymous) | Online | |||
| 45 | 128K | 20 RPM | Online | |||
| stepfun-ai/Step-3.5-Flash Verified | 45 | 8K | Online | |||
| DeepSeek V4 Flash Verified | 45 | 1.0M | Online | |||
| early-access/EA-29B-A4B Verified | 45 | 8K | Online | |||
| nvidia/nemotron-nano-3-30b-a3b Verified nvidia/llama-3.1-nemotron-ultra-253b-v1 | 45 | 131K | Up to 40 RPM | Online | ||
| Mistral 7B Verified | 44 | 33K | See provider page | Online | ||
| 44 | 33K | See provider page | Online | |||
| Free Models Router Verified | 44 | 200K | 200 req/day (free tier) | Online | ||
| 44 | 8K | 20 RPM | Online | |||
| Gemini 2.5 Flash-Lite Verified Gemini 2.5 Flash-Lite | 44 | 1.0M | 30 RPM, 1,500 RPD | Online | ||
| 44 | 131K | See provider page | Online | |||
| 44 | 128K | 15 RPM, 20K TPD | Online | |||
| 44 | 128K | 15 RPM, 20K TPD | Online | |||
| 43 | 16K | 20 RPM | Online | |||
| 43 | 256K | ~1 RPS, 500K TPM | Online | |||
| 43 | 8K | Online | ||||
| nvidia/ising-calibration-1.5-31b Verified | 43 | 8K | Online | |||
| nvidia/riva-translate-4b-instruct-v2 Verified | 43 | 8K | Online | |||
| 43 | 8K | Online | ||||
| mistralai/mistral-large-2-instruct Verified | 43 | 131K | Up to 40 RPM | Online | ||
| 43 | 8K | Online | ||||
| 43 | 8K | Online | ||||
| 43 | 8K | Online | ||||
| Solar Pro 4 Verified | 43 | 0 | See provider page | Online | ||
| DeepSeek-R1 | 43 | 131K | Community-powered, no hard cap | Online | ||
| Qwen3-32B | 43 | 131K | 2 RPM (anonymous) | Online | ||
| nvidia/llama-3.1-nemotron-ultra-253b-v1 | 43 | 131K | Up to 40 RPM | Online | ||
| 42 | 33K | See provider page | Online | |||
| GLM-4.7-FlashX Verified | 42 | 200K | Online | |||
| 42 | 128K | 15 RPM, 20K TPD | Online | |||
| ai21labs/jamba-1.5-large-instruct Verified | 42 | 131K | Up to 40 RPM | Online | ||
| Meta-Llama-3_3-70B-Instruct Verified Meta-Llama-3_3-70B-Instruct | 42 | 131K | 2 RPM (anonymous) | Online | ||
| databricks/dbrx-instruct Verified | 41 | 131K | Up to 40 RPM | Online | ||
| meta/llama2-70b Verified | 41 | 131K | Up to 40 RPM | Online | ||
| whisper-large-v3 Verified | 41 | 131K | 20 RPM, 2,000 RPD | Online | ||
| whisper-large-v3-turbo Verified | 41 | 131K | 20 RPM, 2,000 RPD | Online | ||
| 41 | 32K | 15 RPM, 20K TPD | Online | |||
| meta/llama-3.2-11b-vision-instruct Verified meta/llama-3.2-11b-vision-instruct | 41 | 131K | Up to 40 RPM | Online | ||
| 41 | 33K | See provider page | Online | |||
| nvidia/llama-nemotron-embed-vl-1b-v2 Verified nvidia/llama-3.1-nemotron-ultra-253b-v1 | 41 | 131K | Up to 40 RPM | Online | ||
| 41 | 256K | ~1 RPS, 500K TPM | Online | |||
| @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | 40 | 80K | 10K neurons/day (shared) | Online | ||
| @cf/baai/bge-m3 Verified | 40 | 8K | Online | |||
| @cf/google/gemma-2b-it-lora Verified | 40 | 8K | Online | |||
| MedAIBase/AntAngelMed Verified | 40 | 8K | Online | |||
| MusePublic/Qwen-Image-Edit Verified | 40 | 8K | Online | |||
| OpenGVLab/InternVL3_5-241B-A28B Verified | 40 | 8K | Online | |||
| PaddlePaddle/ERNIE-4.5-21B-A3B-PT Verified | 40 | 8K | Online | |||
| PaddlePaddle/ERNIE-4.5-300B-A47B-PT Verified | 40 | 8K | Online | |||
| PaddlePaddle/ERNIE-4.5-VL-28B-A3B-PT Verified | 40 | 8K | Online | |||
| Qwen/Qwen-Image-Edit 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 | |||
| Shanghai_AI_Laboratory/Intern-S1 Verified | 40 | 8K | Online | |||
| 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 | |||
| nvidia/embed-qa-4 Verified | 40 | 131K | Up to 40 RPM | Online | ||
| 40 | 131K | Up to 40 RPM | Online | |||
| nvidia/llama-3.2-nv-embedqa-1b-v1 Verified | 40 | 131K | Up to 40 RPM | Online | ||
| nvidia/nemotron-3-embed-1b Verified | 40 | 131K | Up to 40 RPM | Online | ||
| nvidia/nv-embedqa-mistral-7b-v2 Verified | 40 | 131K | Up to 40 RPM | Online | ||
| snowflake/arctic-embed-l Verified | 40 | 131K | Up to 40 RPM | Online | ||
| Qwen2.5-7B-Instruct | 40 | 131K | Credit-metered | Online | ||
| 40 | 131K | $25/month free credits, resets monthly | Online | |||
| 39 | 256K | ~1 RPS, 500K TPM | Online | |||
| Phi-4 | 39 | 131K | See provider page | Online | ||
| Llama 3.1 70B | 39 | 131K | Community-powered, no hard cap | Online | ||
| 39 | 8K | Online | ||||
| 39 | 8K | Online | ||||
| 39 | 8K | Online | ||||
| @cf/google/gemma-7b-it-lora Verified | 39 | 8K | Online | |||
| Qwen/Qwen3-235B-A22B-Instruct-2507 Verified Qwen/Qwen3-235B-A22B-Instruct-2507 | 39 | 8K | Online | |||
| GLM-4.5-Air Verified GLM-4.5-Air | 39 | 131K | Online | |||
| Codestral (latest) Verified | 38 | 256K | Online | |||
| Meta-Llama-3_3-70B-Instruct | 38 | 24K | 10K neurons/day (shared) | Online | ||
| 38 | 256K | ~1 RPS, 500K TPM | Online | |||
| big-pickle Verified | 38 | N/A | Online | |||
| meituan-longcat/LongCat-Flash-Lite Verified | 38 | 8K | Online | |||
| Mistral Large (24.11) | 38 | 131K | See provider page | Online | ||
| GPT OSS 20B Verified | 37 | 131K | Online | |||
| Llama 3.1 70B | 37 | 131K | Unlimited for free models | Online | ||
| Qwen/Qwen3-Coder-30B-A3B-Instruct Verified Qwen3-Coder-30B-A3B-Instruct | 37 | 8K | Online | |||
| Llama 3.1 70B | 37 | 131K | See provider page | Online | ||
| Nemotron 3 Nano 30B A3B Verified | 37 | 262K | Online | |||
| Nemotron 3.5 Lightning 30B A3B Verified | 37 | 262K | Online | |||
| Qwen/Qwen3-235B-A22B Verified Qwen/Qwen3-235B-A22B | 37 | 8K | Online | |||
| Qwen/Qwen3-VL-235B-A22B-Instruct Verified Qwen/Qwen3-VL-235B-A22B-Instruct | 36 | 8K | Online | |||
| Qwen/Qwen3-VL-8B-Thinking Verified Qwen/Qwen3-VL-8B-Thinking | 36 | 8K | Online | |||
| meta/llama-guard-4-12b Verified meta/llama-guard-4-12b | 36 | 164K | Up to 40 RPM | Online | ||
| laguna-s-2.1:free Verified | 36 | 0 | See provider page | Online | ||
| Muse Spark 1.3 Contributor Verified | 36 | 0 | See provider page | Online | ||
| allam-2-7b Verified | 35 | 8K | Online | |||
| 35 | 131K | Credit-metered | Online | |||
| Qwen/Qwen3-Next-80B-A3B-Instruct Verified Qwen/Qwen3-Next-80B-A3B-Instruct | 35 | 8K | Online | |||
| 35 | 128K | Online | ||||
| Qwen/Qwen3-VL-8B-Instruct Verified Qwen/Qwen3-VL-8B-Instruct | 34 | 8K | Online | |||
| Qwen/Qwen3-Next-80B-A3B-Thinking Verified Qwen/Qwen3-Next-80B-A3B-Thinking | 34 | 8K | Online | |||
| Qwen/Qwen3-235B-A22B-Thinking-2507 Verified Qwen/Qwen3-235B-A22B-Thinking-2507 | 34 | 8K | Online | |||
| MiniMax/MiniMax-M1-80k Verified | 34 | 8K | Online | |||
| Meta-Llama-3.1-8B-Instruct Verified Meta-Llama-3.1-8B-Instruct | 33 | 128K | Credit-metered | Online | ||
| PaddlePaddle/ERNIE-4.5-0.3B-PT Verified | 33 | 8K | Online | |||
| Mistral Large (24.11) | 33 | 8K | Online | |||
| meta/llama-3.2-90b-vision-instruct Verified | 33 | 8K | Online | |||
| gemma-3-4b-it | 33 | 131K | Credit-metered | Online | ||
| mistralai/Mistral-Large-Instruct-2407 | 33 | 8K | Online | |||
| @cf/qwen/qwen3-30b-a3b-fp8 Verified @cf/qwen/qwen3-30b-a3b-fp8 | 33 | 8K | Online | |||
| Qwen/Qwen3-30B-A3B Verified @cf/qwen/qwen3-30b-a3b-fp8 | 33 | 8K | Online | |||
| @cf/qwen/qwq-32b Verified | 32 | 8K | Online | |||
| 31 | 131K | $25/month free credits, resets monthly | Online | |||
| Qwen/Qwen3-30B-A3B-Thinking-2507 Verified Qwen/Qwen3-30B-A3B-Thinking-2507 | 31 | 8K | Online | |||
| 30 | 8K | Online | ||||
| 30 | 8K | Online | ||||
| Qwen/Qwen3-14B Verified Qwen/Qwen3-14B | 30 | 8K | Online | |||
| Qwen/Qwen3-4B Verified | 30 | 8K | Online | |||
| @cf/qwen/qwen2.5-coder-32b-instruct Verified @cf/qwen/qwen2.5-coder-32b-instruct | 30 | 8K | Online | |||
| @cf/meta/llama-3.2-3b-instruct Verified @cf/meta/llama-3.2-3b-instruct | 29 | 8K | Online | |||
| Qwen/Qwen3-8B Verified Qwen/Qwen3-8B | 29 | 8K | Online | |||
| @cf/meta/llama-3.1-8b-instruct-fp8 Verified Meta-Llama-3.1-8B-Instruct | 28 | 8K | Online | |||
| @cf/meta/llama-guard-3-8b Verified | 28 | 8K | Online | |||
| @cf/qwen/qwen3-embedding-0.6b Verified | 28 | 8K | Online | |||
| @cf/pfnet/plamo-embedding-1b Verified | 28 | 8K | Online | |||
| @cf/google/embeddinggemma-300m Verified | 28 | 8K | Online | |||
| @cf/meta/llama-3.2-1b-instruct Verified @cf/meta/llama-3.2-1b-instruct | 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 303 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.