Free LLM API Hub
★

Free model index

Every model our verified providers expose on a free tier — 77 entries across 14 providers, pulled from each provider's own /models endpoint where possible. The same model can appear under more than one provider.

77 shown

ModelProviderFree typeModalities
@cf/deepseek-ai/deepseek-r1-distill-qwen-32bCloudflare Workers AIrenewing-quotatext, embeddings, image, audio
@cf/google/gemma-3-12b-itCloudflare Workers AIrenewing-quotatext, embeddings, image, audio
@cf/meta/llama-3.1-8b-instructCloudflare Workers AIrenewing-quotatext, embeddings, image, audio
@cf/meta/llama-3.3-70b-instruct-fp8-fastCloudflare Workers AIrenewing-quotatext, embeddings, image, audio
@cf/mistralai/mistral-small-3.1-24b-instructCloudflare Workers AIrenewing-quotatext, embeddings, image, audio
@cf/qwen/qwen2.5-coder-32b-instructCloudflare Workers AIrenewing-quotatext, embeddings, image, audio
01-ai/yi-largeNVIDIA NIMtrial-credittext
adept/fuyu-8bNVIDIA NIMtrial-credittext
ai21labs/jamba-1.5-large-instructNVIDIA NIMtrial-credittext
aisingapore/sea-lion-7b-instructNVIDIA NIMtrial-credittext
baai/bge-m3NVIDIA NIMtrial-credittext
bigcode/starcoder2-15bNVIDIA NIMtrial-credittext
cohere/cohere-command-aGitHub Modelsrenewing-quotatext
cohere/north-mini-code:freeOpenRouterrenewing-quotatext, vision
command-a-03-2025Cohererenewing-quotatext, embeddings, rerank
command-r-08-2024Cohererenewing-quotatext, embeddings, rerank
command-r-plus-08-2024Cohererenewing-quotatext, embeddings, rerank
command-r7b-12-2024Cohererenewing-quotatext, embeddings, rerank
databricks/dbrx-instructNVIDIA NIMtrial-credittext
deepseek-ai/deepseek-coder-6.7b-instructNVIDIA NIMtrial-credittext
deepseek-r1-distill-llama-70bScaleway Generative APIstrial-credittext, audio
DeepSeek-V3.1SambaNova Cloudrenewing-quotatext
deepseek-v4-flashOllama Cloudrenewing-quotatext, vision
deepseek-v4-proOllama Cloudrenewing-quotatext, vision
deepseek/deepseek-r1GitHub Modelsrenewing-quotatext
deepseek/deepseek-r1-0528GitHub Modelsrenewing-quotatext
embed-v4.0Cohererenewing-quotatext, embeddings, rerank
gemini-2.5-flashGoogle Gemini API (AI Studio)renewing-quotatext, vision, embeddings, audio
gemini-2.5-flash-liteGoogle Gemini API (AI Studio)renewing-quotatext, vision, embeddings, audio
gemini-2.5-proGoogle Gemini API (AI Studio)renewing-quotatext, vision, embeddings, audio
gemma-3-27b-itScaleway Generative APIstrial-credittext, audio
gemma-4-31bCerebrasrenewing-quotatext
gemma4:31bOllama Cloudrenewing-quotatext, vision
glm-4.5-flashZ.ai (Zhipu AI / GLM)perpetualtext, vision
glm-4.6v-flashZ.ai (Zhipu AI / GLM)perpetualtext, vision
glm-4.7-flashZ.ai (Zhipu AI / GLM)perpetualtext, vision
glm-5.1Ollama Cloudrenewing-quotatext, vision
glm-5.2Ollama Cloudrenewing-quotatext, vision
google/gemma-4-26b-a4b-it:freeOpenRouterrenewing-quotatext, vision
google/gemma-4-31b-it:freeOpenRouterrenewing-quotatext, vision
gpt-oss-120bCerebrasrenewing-quotatext
gpt-oss-120bSambaNova Cloudrenewing-quotatext
gpt-oss:120bOllama Cloudrenewing-quotatext, vision
gpt-oss:20bOllama Cloudrenewing-quotatext, vision
inclusionai/ling-3.0-flash:freeOpenRouterrenewing-quotatext, vision
kimi-k2.5Ollama Cloudrenewing-quotatext, vision
llama-3.1-8b-instantGroqrenewing-quotatext, audio
llama-3.3-70b-instructScaleway Generative APIstrial-credittext, audio
llama-3.3-70b-versatileGroqrenewing-quotatext, audio
LLM-Research/Llama-4-Maverick-17B-128E-InstructModelScope (API-Inference)renewing-quotatext, vision
MedAIBase/AntAngelMedModelScope (API-Inference)renewing-quotatext, vision
Meta-Llama-3.3-70B-InstructSambaNova Cloudrenewing-quotatext
meta/llama-3.2-11b-vision-instructGitHub Modelsrenewing-quotatext
meta/llama-3.2-90b-vision-instructGitHub Modelsrenewing-quotatext
microsoft/phi-4GitHub Modelsrenewing-quotatext
MiniMax/MiniMax-M1-80kModelScope (API-Inference)renewing-quotatext, vision
mistral-ai/codestral-2501GitHub Modelsrenewing-quotatext
mistral-small-3.2-24b-instruct-2506Scaleway Generative APIstrial-credittext, audio
MusePublic/Qwen-Image-EditModelScope (API-Inference)renewing-quotatext, vision
nvidia/nemotron-3-nano-30b-a3b:freeOpenRouterrenewing-quotatext, vision
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeOpenRouterrenewing-quotatext, vision
openai-fastPollinations.aiperpetualimage, text, audio
openai/gpt-4.1GitHub Modelsrenewing-quotatext
openai/gpt-oss-120bGroqrenewing-quotatext, audio
openai/gpt-oss-20bGroqrenewing-quotatext, audio
openai/gpt-oss-20b:freeOpenRouterrenewing-quotatext, vision
OpenGVLab/InternVL3_5-241B-A28BModelScope (API-Inference)renewing-quotatext, vision
PaddlePaddle/ERNIE-4.5-0.3B-PTModelScope (API-Inference)renewing-quotatext, vision
poolside/laguna-s-2.1:freeOpenRouterrenewing-quotatext, vision
Qwen/Qwen-Image-EditModelScope (API-Inference)renewing-quotatext, vision
qwen2.5-coder-32b-instructScaleway Generative APIstrial-credittext, audio
qwen3-235b-a22b-instruct-2507Scaleway Generative APIstrial-credittext, audio
rerank-v3.5Cohererenewing-quotatext, embeddings, rerank
Shanghai_AI_Laboratory/Intern-S1ModelScope (API-Inference)renewing-quotatext, vision
whisper-large-v3Groqrenewing-quotatext, audio
whisper-large-v3-turboGroqrenewing-quotatext, audio
zai-glm-4.7Cerebrasrenewing-quotatext

Model lists are a live sample and change often — always confirm against the provider. A provider missing here usually needs an API key to list its models; see how the list is refreshed.