Directory of Free LLM APIs: Compare 301+ Models
Showing 301 of 301 free or trial LLM models
Discover and filter 301+ free or trial 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.
244 models verified via live API · latest update Sep 20, 2026 — how we verify
| Provider | Model | Score | Context | Modality | Rate Limit | Status |
|---|---|---|---|---|---|---|
| z-ai/glm-5.3 Verified | 97 | 1.3M | Up to 40 RPM | Online | ||
| z-ai/glm-5.3-flash Verified z-ai/glm-5.3-flash | 96 | 1.3M | Up to 40 RPM | Online | ||
| 95 | 262K | 200 req/day (free tier) | Online | |||
| Qwen: Qwen3.8 27B (free) Verified Qwen: Qwen3.8 27B (free) | 93 | 262K | 200 req/day (free tier) | Online | ||
| DeepSeek: DeepSeek V4 Flash 0731 (free) | 93 | 1.0M | 200 req/day (free tier) | Online | ||
| deepseek-v4-pro Verified deepseek-v4-pro | 93 | 1.0M | Session/weekly limits (unpublished) | Online | ||
| deepseek-v4-flash Verified deepseek-v4-flash | 91 | 1.0M | Session/weekly limits (unpublished) | Online | ||
| Kimi K3 Verified | 91 | 1.0M | Online | |||
| GLM-5.3-Flash Verified GLM-5.3-Flash | 90 | 1.0M | Online | |||
| deepseek-ai/deepseek-v4-flash-0731 Verified DeepSeek: DeepSeek V4 Flash 0731 (free) | 89 | 1.3M | Up to 40 RPM | Online | ||
| GLM-5.3 Verified GLM-5.3 | 88 | 1.0M | Online | |||
| Gemini 3.8 Flash Verified Gemini 3.8 Flash | 82 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| agnes-2.0-flash Verified | 87 | 256K | 30 RPM | Online | ||
| GLM-5.3-Flash Verified GLM-5.3-Flash | 87 | 1.0M | Online | |||
| Qwen/Qwen3.8-Flash-Next Verified | 87 | 8K | Online | |||
| Z.ai: GLM 5.2 (free) Verified | 86 | 33K | 200 req/day (free tier) | Online | ||
| Kimi K3 Verified Kimi K3 | 85 | 1.0M | Online | |||
| 85 | 262K | 200 req/day (free tier) | Online | |||
| inclusionAI: Ling 3.0 Flash Fin (free) | 84 | 262K | 200 req/day (free tier) | Online | ||
| inclusionAI: Ling 3.0 Flash Fin (free) | 83 | 1.0M | 200 req/day (free tier) | Online | ||
| Gemini 3.7 Flash Verified Gemini 3.7 Flash | 88 | 1.0M | — | Online | ||
| DeepSeek V4 Pro Verified deepseek-v4-pro | 82 | 1.0M | Online | |||
| Gemini 3.6 Flash Verified Gemini 3.6 Flash | 82 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| Qwen/Qwen3.8-27B Verified Qwen: Qwen3.8 27B (free) | 82 | 8K | Online | |||
| deepseek-ai/DeepSeek-V4-Pro Verified deepseek-v4-pro | 81 | 8K | Online | |||
| Thinking Machines: Inkling (free) Verified | 81 | 1.0M | 200 req/day (free tier) | Online | ||
| DeepSeek V4 Flash Verified deepseek-v4-flash | 81 | 1.0M | Online | |||
| deepseek-ai/DeepSeek-V4-Flash Verified deepseek-v4-flash | 80 | 8K | Online | |||
| minimax-m3 Verified minimax-m3 | 79 | 512K | Session/weekly limits (unpublished) | Online | ||
| 79 | 262K | 200 req/hr | Online | |||
| DeepSeek V4 Flash 0731 Verified deepseek-v4-flash | 79 | 1.0M | Online | |||
| GLM-5.1 Verified | 79 | 1.0M | Online | |||
| glm-5.3-flash Verified | 78 | 0 | See provider page | Online | ||
| @cf/qwen/qwen3.8-27b Verified Qwen: Qwen3.8 27B (free) | 77 | 8K | Online | |||
| Nex AGI: Nex-N2.5-Pro (free) Verified | 77 | 262K | 200 req/day (free tier) | Online | ||
| deepseek-ai/DeepSeek-V4-Pro-0813 Verified deepseek-ai/DeepSeek-V4-Pro-0813 | 77 | 8K | Online | |||
| DeepSeek V4.1 Flash Verified DeepSeek V4.1 Flash | 76 | 1.0M | Online | |||
| GLM-5.2 Verified GLM-5.2 | 76 | 1.0M | Online | |||
| NVIDIA: Nemotron 3 Ultra (free) Verified NVIDIA: Nemotron 3 Ultra (free) | 76 | 1.0M | 200 req/day (free tier) | Online | ||
| Gemini 3.5 Flash Verified Gemini 3.5 Flash | 76 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| deepseek-ai/DeepSeek-V4.1-Flash Verified DeepSeek V4.1 Flash | 75 | 8K | Online | |||
| NVIDIA: Nemotron 3 Ultra (free) | 74 | 1.0M | 200 req/hr | Online | ||
| moonshotai/kimi-k2.6 Verified moonshotai/kimi-k2.6 | 72 | 262K | Up to 40 RPM | Online | ||
| Gemini 3.5 Flash-Lite Verified Gemini 3.5 Flash-Lite | 71 | 1.0M | 30 RPM, 1,500 RPD | Online | ||
| 70 | 512K | 200 req/day (free tier) | Online | |||
| NVIDIA: Nemotron 3.5 Lightning (free) | 70 | 1.0M | 200 req/day (free tier) | Online | ||
| 70 | 262K | 200 req/hr | Online | |||
| Nemotron 3 Ultra 550B A55B Verified NVIDIA: Nemotron 3 Ultra (free) | 69 | 1.0M | Online | |||
| nemotron-3-ultra Verified | 69 | 262K | Session/weekly limits (unpublished) | Online | ||
| MiniMax-M3 Verified minimax-m3 | 69 | 1.0M | 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) | 68 | 262K | 200 req/day (free tier) | Online | ||
| NVIDIA: Nemotron 3.5 Lightning (free) | 68 | 1.0M | 200 req/hr | Online | ||
| Qwen3.6-27B | 67 | 131K | 2 RPM (anonymous) | Online | ||
| MiniMax-M3 Verified | 67 | 512K | Online | |||
| Deepseek-v4.1-Flash Verified | 67 | 0 | See provider page | Online | ||
| Poolside: Laguna XS 2.1 (free) Verified Poolside: Laguna S 2.1 (free) | 66 | 262K | 200 req/day (free tier) | Online | ||
| Solar Pro 4 Verified | 66 | 0 | See provider page | Online | ||
| Poolside: Laguna S 2.1 (free) | 66 | 262K | 200 req/hr | Online | ||
| GLM-5 Verified GLM-5 | 65 | 205K | Online | |||
| minimax-m2.7 Verified minimax-m2.7 | 65 | 180K | 10 RPM, 60 req/hr (anonymous) | Online | ||
| Cohere: North Mini Code (free) Verified Cohere: North Mini Code (free) | 65 | 256K | 200 req/day (free tier) | Online | ||
| Poolside: Laguna S 2.1 (free) | 64 | 262K | 200 req/hr | Online | ||
| NVIDIA: Nemotron 3 Nano Omni (free) Verified NVIDIA: Nemotron 3 Nano Omni (free) | 64 | 256K | 200 req/day (free tier) | Online | ||
| Google: Gemma 4 26B A4B (free) Verified Google: Gemma 4 26B A4B (free) | 64 | 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 | ||
| Kimi K2.6 Verified Kimi K2.6 | 63 | 262K | Online | |||
| poolside/laguna-xs-2.1 Verified Poolside: Laguna S 2.1 (free) | 63 | 262K | Up to 40 RPM | Online | ||
| Cohere: North Mini Code (free) | 63 | 256K | 200 req/hr | Online | ||
| Qwen3.6 Plus Verified Qwen3.6 Plus | 63 | 1.0M | Online | |||
| LiquidAI: LFM2.5-2.6B (free) Verified | 63 | 66K | 200 req/day (free tier) | Online | ||
| Muse Glimmer 30B Verified Muse Glimmer 30B | 63 | 131K | Online | |||
| NVIDIA: Nemotron 3 Nano Omni (free) | 62 | 256K | 200 req/hr | Online | ||
| Qwen3.8 Flash Verified Qwen3.8 Flash | 62 | 1.0M | Online | |||
| GLM-4.7-Flash Verified GLM-4.7-Flash | 62 | 200K | 1 concurrent request | Online | ||
| DeepSeek V4 Flash Vision Exp Verified DeepSeek V4 Flash Vision Exp | 62 | 1.0M | Online | |||
| Nemotron 3 Super 120B A12B Verified | 61 | 262K | Online | |||
| stepfun-ai/Step-3.7-Flash Verified | 61 | 8K | Online | |||
| GLM-5.1 Verified GLM-5.1 | 61 | 200K | Online | |||
| MiniMax-M2.5 Verified MiniMax-M2.5 | 61 | 205K | Online | |||
| 61 | 64K | 200 req/hr | Online | |||
| Nemotron 3 Ultra 550B A55B Verified | 60 | 1.0M | Online | |||
| Qwen3.5-397B-A17B | 60 | 131K | 2 RPM (anonymous) | Online | ||
| 01-ai/yi-large Verified | 59 | 131K | Up to 40 RPM | Online | ||
| meta/codellama-70b Verified | 59 | 131K | Up to 40 RPM | Online | ||
| nvidia/llama3-chatqa-1.5-70b Verified | 59 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-fin-70b-32k Verified | 59 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-med-70b Verified | 59 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-med-70b-32k Verified | 59 | 131K | Up to 40 RPM | Online | ||
| NVIDIA: Nemotron 3 Super (free) Verified NVIDIA: Nemotron 3 Super (free) | 59 | 262K | 200 req/day (free tier) | Online | ||
| @cf/moonshotai/kimi-k2.7-code Verified moonshotai/kimi-k2.6 | 59 | 262K | 10K neurons/day (shared) | Online | ||
| @cf/google/gemma-4-26b-a4b-it Verified Google: Gemma 4 26B A4B (free) | 58 | 256K | 10K neurons/day (shared) | Online | ||
| NVIDIA: Nemotron 3 Nano Omni (free) | 58 | 256K | Online | |||
| Gemma 4 31B IT Verified Google: Gemma 4 31B (free) | 57 | 262K | Online | |||
| NVIDIA: Nemotron 3 Super (free) | 57 | 262K | 200 req/hr | Online | ||
| Ling 3.0 Flash Fin Verified | 57 | 262K | Online | |||
| Gemma 4 26B A4B IT Verified Google: Gemma 4 26B A4B (free) | 56 | 262K | Varies by model and account | Online | ||
| Gemma 4 31B IT Verified Google: Gemma 4 31B (free) | 56 | 262K | Varies by model and account | Online | ||
| MiniMax-M2.7 Verified minimax-m2.7 | 56 | 205K | Online | |||
| Gemma 4 31B IT Verified | 56 | 262K | Online | |||
| nvidia/llama-3.1-nemotron-ultra-253b-v1 | 55 | 131K | Up to 40 RPM | Online | ||
| ibm/granite-34b-code-instruct Verified | 55 | 131K | Up to 40 RPM | Online | ||
| Kimi K2.5 Verified Kimi K2.5 | 55 | 262K | Online | |||
| 55 | 131K | See provider page | Online | |||
| 55 | 131K | See provider page | Online | |||
| google/diffusiongemma-26b-a4b-it Verified | 55 | 8K | Online | |||
| Qwen3.5-9B | 54 | 131K | 2 RPM (anonymous) | Online | ||
| agnes-1.5-flash Verified | 54 | 256K | 30 RPM | Online | ||
| Qwen3.5 Plus Verified | 53 | 1.0M | Online | |||
| Nemotron 3 Super 120B A12B Verified NVIDIA: Nemotron 3 Super (free) | 53 | 262K | 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 | 52 | 1.0M | 30 RPM, 1,500 RPD | Online | ||
| @cf/zai-org/glm-4.7-flash Verified | 52 | 131K | 10K neurons/day (shared) | Online | ||
| bigcode/starcoder2-15b Verified | 52 | 131K | Up to 40 RPM | Online | ||
| google/deplot Verified | 52 | 131K | Up to 40 RPM | Online | ||
| google/gemma-2b Verified | 52 | 131K | Up to 40 RPM | Online | ||
| google/recurrentgemma-2b Verified | 52 | 131K | Up to 40 RPM | Online | ||
| microsoft/kosmos-2 Verified | 52 | 131K | Up to 40 RPM | Online | ||
| microsoft/phi-3-vision-128k-instruct Verified | 52 | 131K | Up to 40 RPM | Online | ||
| microsoft/phi-3.5-moe-instruct Verified | 52 | 131K | Up to 40 RPM | Online | ||
| mistralai/mixtral-8x22b-v0.1 Verified | 52 | 131K | Up to 40 RPM | Online | ||
| 52 | 131K | Up to 40 RPM | Online | |||
| nvidia/nemotron-4-340b-instruct Verified | 52 | 131K | Up to 40 RPM | Online | ||
| nvidia/nemotron-4-340b-reward Verified | 52 | 131K | Up to 40 RPM | Online | ||
| nvidia/nemotron-parse Verified | 52 | 131K | Up to 40 RPM | Online | ||
| nvidia/neva-22b Verified | 52 | 131K | Up to 40 RPM | Online | ||
| nvidia/nvclip Verified | 52 | 131K | Up to 40 RPM | Online | ||
| nvidia/riva-translate-4b-instruct Verified | 52 | 131K | Up to 40 RPM | Online | ||
| nvidia/vila Verified | 52 | 131K | Up to 40 RPM | Online | ||
| writer/palmyra-creative-122b Verified | 52 | 131K | Up to 40 RPM | Online | ||
| Qwen/Qwen3.5-397B-A17B Verified Qwen3.5-397B-A17B | 52 | 8K | Online | |||
| @cf/nvidia/nemotron-3-120b-a12b Verified | 52 | 8K | Online | |||
| @cf/baai/bge-large-en-v1.5 Verified | 52 | 8K | Online | |||
| 51 | 256K | See provider page | Online | |||
| nex-agi/Nex-N2.5-Pro Verified | 51 | 8K | 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 | ||
| 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 | ||
| NVIDIA: Nemotron 3.5 Content Safety (free) | 51 | 128K | 200 req/day (free tier) | Online | ||
| GLM-4.6V-Flash Verified GLM-4.6V-Flash | 51 | 128K | 1 concurrent request | Online | ||
| Qwen/Qwen3.5-122B-A10B Verified Qwen/Qwen3.5-122B-A10B | 51 | 8K | Online | |||
| 51 | 256K | ~1 RPS, 500K TPM | Online | |||
| groq/compound Verified | 50 | 131K | 30 RPM, 250 RPD | Online | ||
| Gemma 4 31B IT Verified | 50 | 262K | Online | |||
| gpt-oss:120b Verified gpt-oss:120b | 50 | 128K | Session/weekly limits (unpublished) | Online | ||
| MiMo-V2.5 Verified | 49 | 1.0M | Online | |||
| Qwen3-Coder-30B-A3B-Instruct | 49 | 262K | 2 RPM (anonymous) | Online | ||
| nvidia/cosmos-reason2-8b Verified | 49 | 131K | Up to 40 RPM | Online | ||
| groq/compound-mini Verified | 49 | 131K | 30 RPM, 250 RPD | Online | ||
| mistral-Nemo-Instruct-2407 Verified mistral-Nemo-Instruct-2407 | 49 | 128K | 10 RPM, 60 req/hr (anonymous) | Online | ||
| Google: Lyria 3 Pro Preview Verified Google: Lyria 3 Pro Preview | 49 | 1.0M | 200 req/day (free tier) | Online | ||
| Google: Lyria 3 Clip Preview Verified Google: Lyria 3 Clip Preview | 49 | 1.0M | 200 req/day (free tier) | Online | ||
| mistralai/codestral-22b-instruct-v0.1 | 48 | 131K | Up to 40 RPM | Online | ||
| agnes-video-v2.0 Verified | 48 | 4K | 2 RPM | Online | ||
| stepfun-ai/Step-3.5-Flash Verified | 48 | 8K | Online | |||
| Qwen2.5-VL-72B-Instruct | 48 | 128K | 2 RPM (anonymous) | Online | ||
| Mistral-Small-3.2-24B-Instruct | 48 | 128K | 2 RPM (anonymous) | Online | ||
| 48 | 256K | ~1 RPS, 500K TPM | Online | |||
| nvidia/nemotron-3.5-content-safety Verified NVIDIA: Nemotron 3.5 Content Safety (free) | 48 | 128K | Up to 40 RPM | Online | ||
| mistralai/mistral-nemotron Verified | 47 | 8K | Online | |||
| 47 | 8K | Online | ||||
| nvidia/ising-calibration-1.5-31b Verified | 47 | 8K | Online | |||
| nvidia/riva-translate-4b-instruct-v2 Verified | 47 | 8K | Online | |||
| 47 | 8K | Online | ||||
| nvidia/nemotron-parse-2.0 Verified | 47 | 8K | Online | |||
| 47 | 128K | ~1 RPS, 500K TPM | Online | |||
| 47 | 8K | Online | ||||
| 47 | 8K | Online | ||||
| 47 | 8K | Online | ||||
| mistralai/mistral-7b-instruct-v0.3 Verified | 47 | 131K | Up to 40 RPM | Online | ||
| Gemini 2.5 Pro Verified Gemini 2.5 Pro | 47 | 1.0M | 5 RPM, 50 RPD | Online | ||
| Gemini 2.5 Flash Verified Gemini 2.5 Flash | 47 | 1.0M | 15 RPM, 1,500 RPD | Online | ||
| 47 | 256K | 20 RPM | Online | |||
| 47 | 256K | 20 RPM | 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 | 46 | 1.0M | Online | |||
| GLM-4.7-FlashX Verified | 46 | 200K | 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 | ||
| 46 | 131K | 10K neurons/day (shared) | Online | |||
| @cf/mistralai/mistral-small-3.1-24b-instruct | 46 | 128K | 10K neurons/day (shared) | Online | ||
| 46 | 32K | 2 RPM (anonymous) | Online | |||
| ibm/granite-3.0-3b-a800m-instruct Verified | 45 | 131K | Up to 40 RPM | Online | ||
| GLM-4.5-Flash Verified GLM-4.5-Flash | 45 | 128K | 1 concurrent request | Online | ||
| 45 | 128K | 20 RPM | Online | |||
| @cf/baai/bge-m3 Verified | 45 | 8K | Online | |||
| @cf/google/gemma-2b-it-lora Verified | 45 | 8K | Online | |||
| @cf/ibm-granite/granite-4.0-h-micro Verified | 45 | 8K | Online | |||
| @cf/baai/bge-small-en-v1.5 Verified | 45 | 8K | Online | |||
| @cf/baai/bge-base-en-v1.5 Verified | 45 | 8K | Online | |||
| 45 | 8K | Online | ||||
| @cf/openai/gpt-oss-20b Verified | 45 | 8K | Online | |||
| @cf/moondream/moondream3.1-9B-A2B Verified | 45 | 8K | Online | |||
| Mistral 7B Verified | 44 | 33K | See provider page | Online | ||
| 44 | 33K | See provider page | Online | |||
| MedAIBase/AntAngelMed Verified | 44 | 8K | Online | |||
| MusePublic/Qwen-Image-Edit Verified | 44 | 8K | Online | |||
| OpenGVLab/InternVL3_5-241B-A28B Verified | 44 | 8K | Online | |||
| PaddlePaddle/ERNIE-4.5-21B-A3B-PT Verified | 44 | 8K | Online | |||
| PaddlePaddle/ERNIE-4.5-300B-A47B-PT Verified | 44 | 8K | Online | |||
| PaddlePaddle/ERNIE-4.5-VL-28B-A3B-PT Verified | 44 | 8K | Online | |||
| Qwen/Qwen-Image-Edit Verified | 44 | 8K | Online | |||
| Shanghai_AI_Laboratory/Intern-S1 Verified | 44 | 8K | Online | |||
| 44 | 8K | Online | ||||
| early-access/EA-29B-A4B Verified | 44 | 8K | Online | |||
| nvidia/nemotron-nano-3-30b-a3b Verified nvidia/llama-3.1-nemotron-ultra-253b-v1 | 44 | 131K | Up to 40 RPM | Online | ||
| 44 | 8K | 20 RPM | Online | |||
| 44 | 131K | See provider page | Online | |||
| Free Models Router Verified | 44 | 200K | 200 req/day (free tier) | Online | ||
| 44 | 128K | 15 RPM, 20K TPD | Online | |||
| 44 | 128K | 15 RPM, 20K TPD | Online | |||
| Gemini 2.5 Flash-Lite Verified Gemini 2.5 Flash-Lite | 44 | 1.0M | 30 RPM, 1,500 RPD | Online | ||
| 43 | 16K | 20 RPM | Online | |||
| 43 | 8K | Online | ||||
| 43 | 8K | Online | ||||
| @cf/google/gemma-7b-it-lora Verified | 43 | 8K | Online | |||
| Codestral (latest) Verified | 43 | 256K | Online | |||
| whisper-large-v3 Verified | 43 | 131K | 20 RPM, 2,000 RPD | Online | ||
| whisper-large-v3-turbo Verified | 43 | 131K | 20 RPM, 2,000 RPD | Online | ||
| mistralai/mistral-large-2-instruct Verified | 43 | 131K | Up to 40 RPM | Online | ||
| 43 | 8K | Online | ||||
| nex-agi/Nex-N2.5-mini Verified | 43 | 8K | Online | |||
| DeepSeek-R1 | 43 | 131K | Community-powered, no hard cap | Online | ||
| Qwen3-32B | 43 | 131K | 2 RPM (anonymous) | Online | ||
| 42 | 256K | ~1 RPS, 500K TPM | Online | |||
| nvidia/llama-3.1-nemotron-ultra-253b-v1 | 42 | 131K | Up to 40 RPM | Online | ||
| 42 | 33K | See provider page | Online | |||
| 42 | 128K | 15 RPM, 20K TPD | Online | |||
| GLM-4.5-Air Verified GLM-4.5-Air | 42 | 131K | Online | |||
| GPT OSS 20B Verified | 42 | 131K | 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 | ||
| meituan-longcat/LongCat-Flash-Lite Verified | 42 | 8K | Online | |||
| databricks/dbrx-instruct Verified | 41 | 131K | Up to 40 RPM | Online | ||
| meta/llama2-70b Verified | 41 | 131K | Up to 40 RPM | Online | ||
| big-pickle Verified | 41 | N/A | Online | |||
| 41 | 32K | 15 RPM, 20K TPD | Online | |||
| allam-2-7b Verified | 41 | 8K | 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 | |||
| Nemotron 3 Nano 30B A3B Verified | 41 | 262K | Online | |||
| nvidia/llama-nemotron-embed-vl-1b-v2 Verified nvidia/llama-3.1-nemotron-ultra-253b-v1 | 40 | 131K | Up to 40 RPM | Online | ||
| @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | 40 | 80K | 10K neurons/day (shared) | Online | ||
| Ministral 3 14B | 40 | 256K | ~1 RPS, 500K TPM | Online | ||
| Qwen2.5-7B-Instruct | 40 | 131K | Credit-metered | Online | ||
| @cf/moonshotai/kimi-k2.6 Verified | 40 | 8K | Online | |||
| @cf/zai-org/glm-5.2 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 | ||
| Nemotron 3.5 Lightning 30B A3B Verified | 40 | 262K | Online | |||
| 40 | 131K | $25/month free credits, resets monthly | Online | |||
| Phi-4 | 39 | 131K | See provider page | Online | ||
| 39 | 256K | ~1 RPS, 500K TPM | Online | |||
| Llama 3.1 70B | 39 | 131K | Community-powered, no hard cap | Online | ||
| Meta-Llama-3_3-70B-Instruct | 38 | 24K | 10K neurons/day (shared) | Online | ||
| Mistral Large (24.11) | 38 | 131K | See provider page | Online | ||
| Ministral 3 14B | 38 | 256K | ~1 RPS, 500K TPM | Online | ||
| MiniMax/MiniMax-M1-80k Verified | 38 | 8K | Online | |||
| Llama 3.1 70B | 37 | 131K | Unlimited for free models | Online | ||
| PaddlePaddle/ERNIE-4.5-0.3B-PT Verified | 37 | 8K | Online | |||
| @cf/qwen/qwen3-30b-a3b-fp8 Verified @cf/qwen/qwen3-30b-a3b-fp8 | 37 | 8K | Online | |||
| mistralai/Mistral-Large-Instruct-2407 | 37 | 8K | Online | |||
| @cf/qwen/qwq-32b Verified | 37 | 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 | ||
| 35 | 131K | Credit-metered | Online | |||
| 35 | 8K | Online | ||||
| @cf/qwen/qwen2.5-coder-32b-instruct Verified @cf/qwen/qwen2.5-coder-32b-instruct | 35 | 8K | Online | |||
| 34 | 128K | Online | ||||
| @cf/meta/llama-3.2-3b-instruct Verified @cf/meta/llama-3.2-3b-instruct | 34 | 8K | Online | |||
| Meta-Llama-3.1-8B-Instruct Verified Meta-Llama-3.1-8B-Instruct | 34 | 128K | Credit-metered | Online | ||
| gemma-3-4b-it | 33 | 131K | Credit-metered | Online | ||
| @cf/meta/llama-3.1-8b-instruct-fp8 Verified Meta-Llama-3.1-8B-Instruct | 33 | 8K | Online | |||
| Mistral Large (24.11) | 33 | 8K | Online | |||
| meta/llama-3.2-90b-vision-instruct Verified | 33 | 8K | Online | |||
| @cf/meta/llama-guard-3-8b Verified | 32 | 8K | Online | |||
| @cf/qwen/qwen3-embedding-0.6b Verified | 32 | 8K | Online | |||
| @cf/pfnet/plamo-embedding-1b Verified | 32 | 8K | Online | |||
| @cf/google/embeddinggemma-300m Verified | 32 | 8K | Online | |||
| @cf/meta/llama-3.2-1b-instruct Verified @cf/meta/llama-3.2-1b-instruct | 32 | 8K | Online | |||
| 31 | 131K | $25/month free credits, resets monthly | Online | |||
| 31 | 131K | See provider page | Online | |||
| 30 | 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 301 free or trial 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.