Free LLM API models

Every free model across 49 providers, in one place. Sort by context window, rate limits (RPM/TPM) or Artificial Analysis quality; filter by modality or provider. Free tiers change often — each row links back to the provider's page for the checked-on date.

822 models
Model Provider Family Modality Context RPM TPM AA
Claude Opus 4.8 BTL Runtime Claude text — — — 55.7
Claude Opus 4.8 Microsoft for Startups Claude text — — — 55.7
anthropic/claude-opus-4.8 Vercel AI Gateway Claude text — — — 55.7
GPT-5.5 BTL Runtime GPT text — — — 54.8
GPT-5.5 Microsoft for Startups GPT text — — — 54.8
gpt-5.5 OpenAI Codex for Open Source GPT text — — — 54.8
openai/gpt-5.5 Vercel AI Gateway GPT text — — — 54.8
GPT-5.4 Microsoft for Startups GPT text — — — 51.4
gpt-5.4 OpenAI Codex for Open Source GPT text — — — 51.4
openai/gpt-5.4 Vercel AI Gateway GPT text — — — 51.4
GLM 5.2 Baseten GLM text — — — 51.1
zai-org/GLM-5.2 Hugging Face Inference GLM text — — — 51.1
ZhipuAI/GLM-5.2 ModelScope API-Inference GLM text — — — 51.1
zai-org/GLM-5.2 Nebius AI Studio GLM text — — — 51.1
zai/glm-5.2 Vercel AI Gateway GLM text — — — 51.1
Gemini 3.5 Flash Google AI Studio / Gemini API Gemini text, image, audio, video 1M 10 250000 50.2
Gemini 3.5 Flash Google for Startups Cloud Program Gemini text — — — 50.2
google/gemini-3.5-flash Lightning AI Gemini text — — — 50.2
google/gemini-3.5-flash Vercel AI Gateway Gemini text — — — 50.2
Gemini 3.1 Pro BTL Runtime Gemini text — — — 46.5
Gemini 3.1 Pro Google for Startups Cloud Program Gemini text — — — 46.5
google/gemini-3.1-pro-preview Lightning AI Gemini text — — — 46.5
google/gemini-3.1-pro-preview Vercel AI Gateway Gemini text — — — 46.5
alibaba/qwen3.7-max Vercel AI Gateway Qwen text — — — 46
minimax-m3 Kimchi MiniMax text — — — 44.4
MiniMax/MiniMax-M3 ModelScope API-Inference MiniMax text — — — 44.4
minimax-m3 NVIDIA NIM MiniMax text — — — 44.4
minimax/minimax-m3 Vercel AI Gateway MiniMax text — — — 44.4
DeepSeek V4 Baseten DeepSeek text — — — 44.3
DeepSeek V4 Pro BTL Runtime DeepSeek text — — — 44.3
deepseek-v4-pro DeepSeek Platform DeepSeek text, code 1M — — 44.3
deepseek-ai/DeepSeek-V4-Pro Hugging Face Inference DeepSeek text — — — 44.3
lightning-ai/deepseek-v4-pro Lightning AI DeepSeek text — — — 44.3
DeepSeek-V4-Pro Microsoft for Startups DeepSeek text — — — 44.3
GPT-5.3-codex Microsoft for Startups GPT text — — — 44.3
deepseek-ai/DeepSeek-V4-Pro ModelScope API-Inference DeepSeek text — — — 44.3
deepseek-ai/DeepSeek-V4-Pro Nebius AI Studio DeepSeek text — — — 44.3
deepseek-v4-pro NVIDIA NIM DeepSeek text — — — 44.3
GPT-5.3-Codex OpenAI Codex Enterprise Credit Promo GPT text — — — 44.3
gpt-5.3-codex OpenAI Codex for Open Source GPT text — — — 44.3
gpt-5.3-codex-spark OpenAI Codex for Open Source GPT text — — — 44.3
deepseek/deepseek-v4-pro Vercel AI Gateway DeepSeek text — — — 44.3
openai/gpt-5.3-codex Vercel AI Gateway GPT text — — — 44.3
Kimi K2.6 Baseten Kimi text — — — 42.8
@cf/moonshotai/kimi-k2.6 Cloudflare Workers AI Kimi text — — — 42.8
moonshotai/Kimi-K2.6 Hugging Face Inference Kimi text — — — 42.8
kimi-k2.6 Kimchi Kimi text — — — 42.8
moonshotai/Kimi-K2.6 Nebius AI Studio Kimi text — — — 42.8
kimi-k2.6 NVIDIA NIM Kimi text — — — 42.8
moonshotai/kimi-k2.6 Vercel AI Gateway Kimi text — — — 42.8
Claude Opus 4.7 AWS Bedrock Credits Claude text — — — 42.7
anthropic/claude-opus-4.7 Vercel AI Gateway Claude text — — — 42.7
GPT-5.2 Microsoft for Startups GPT text — — — 42.2
gpt-5.2 OpenAI Codex for Open Source GPT text — — — 42.2
xiaomi/mimo-v2.5-pro Vercel AI Gateway MiMo text — — — 42.2
Kimi K2.7 Code Baseten Kimi text — — — 42
Kimi K2.7 Code BTL Runtime Kimi text — — — 42
moonshotai/Kimi-K2.7-Code Hugging Face Inference Kimi text — — — 42
moonshotai/kimi-k2.7-code Vercel AI Gateway Kimi text — — — 42
deepseek-v4-flash DeepSeek Platform DeepSeek text, code 1M — — 40.3
deepseek-ai/DeepSeek-V4-Flash Hugging Face Inference DeepSeek text — — — 40.3
DeepSeek-V4-Flash Microsoft for Startups DeepSeek text — — — 40.3
deepseek-ai/DeepSeek-V4-Flash ModelScope API-Inference DeepSeek text — — — 40.3
deepseek-v4-flash NVIDIA NIM DeepSeek text — — — 40.3
deepseek/deepseek-v4-flash Vercel AI Gateway DeepSeek text — — — 40.3
GLM 5.1 Baseten GLM text — — — 40.2
ZhipuAI/GLM-5.1 ModelScope API-Inference GLM text — — — 40.2
zai-org/GLM-5.1 Nebius AI Studio GLM text — — — 40.2
glm-5.1 NVIDIA NIM GLM text — — — 40.2
openai/gpt-5.4-mini-2026-03-17 Lightning AI GPT text — — — 40
GPT-5.4 mini Microsoft for Startups GPT text — — — 40
gpt-5.4-mini OpenAI Codex for Open Source GPT text — — — 40
openai/gpt-5.4-mini Vercel AI Gateway GPT text — — — 40
GLM 5 Baseten GLM text — — — 39.5
Gemini 3 Pro Google for Startups Cloud Program Gemini text — — — 39.5
ZhipuAI/GLM-5 ModelScope API-Inference GLM text — — — 39.5
zai-org/GLM-5 Nebius AI Studio GLM text — — — 39.5
zai/glm-5 Vercel AI Gateway GLM text — — — 39.5
alibaba/qwen3.7-plus Vercel AI Gateway Qwen text — — — 39
GPT-5.1 Microsoft for Startups GPT text — — — 38.9
openai/gpt-5.4-nano-2026-03-17 Lightning AI GPT text — — — 38.2
GPT-5.4 nano Microsoft for Startups GPT text — — — 38.2
Kimi K2.5 Baseten Kimi text — — — 38.1
@cf/moonshotai/kimi-k2.5 Cloudflare Workers AI Kimi text — — — 38.1
kimi-k2.5 Kimchi Kimi text — — — 38.1
minimax-m2.7 Kimchi MiniMax text — — — 38.1
MiniMax/MiniMax-M2.7 ModelScope API-Inference MiniMax text — — — 38.1
moonshotai/Kimi-K2.5 ModelScope API-Inference Kimi text — — — 38.1
moonshotai/Kimi-K2.5 Nebius AI Studio Kimi text — — — 38.1
minimax-m2.7 NVIDIA NIM MiniMax text — — — 38.1
MiniMax-M2.7 SambaNova Cloud MiniMax text — — — 38.1
Claude Opus 4.6 AWS Bedrock Credits Claude text — — — 37.8
NVIDIA Nemotron 3 Ultra Baseten Nemotron text — — — 37.8
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 Hugging Face Inference Nemotron text — — — 37.8
nemotron-3-ultra-fp4 Kimchi Nemotron text — — — 37.8
lightning-ai/nvidia-nemotron-3-ultra-550b-a55b Lightning AI Nemotron text — — — 37.8
nvidia/Nemotron-3-Ultra-550b-a55b Nebius AI Studio Nemotron text — — — 37.8
nemotron-3-ultra-550b-a55b NVIDIA NIM Nemotron text — — — 37.8
NVIDIA: Nemotron 3 Ultra (free) OpenRouter NVIDIA text — — — 37.8
anthropic/claude-opus-4.6 Vercel AI Gateway Claude text — — — 37.8
nvidia/nemotron-3-ultra-550b-a55b Vercel AI Gateway Nemotron text — — — 37.8
xai/grok-4.3 Vercel AI Gateway Grok text — — — 37.6
Qwen3.6-27B OVHcloud AI Endpoints Qwen text — — — 37
alibaba/qwen3.6-27b Vercel AI Gateway Qwen text — — — 37
Claude Sonnet 4.6 AWS Bedrock Credits Claude text — — — 35.9
Claude Sonnet 4.6 Microsoft for Startups Claude text — — — 35.9
anthropic/claude-sonnet-4.6 Vercel AI Gateway Claude text — — — 35.9
Claude Opus 4.5 AWS Bedrock Credits Claude text — — — 34.7
Claude Opus 4.5 Microsoft for Startups Claude text — — — 34.7
GPT-5.1-codex-max Microsoft for Startups GPT text — — — 34.7
Qwen3.5-27B Alibaba Cloud Model Studio Qwen text — — — 33.8
GLM 4.7 Baseten GLM text — — — 33.8
Z.ai GLM 4.7 (zai-glm-4.7) Cerebras Inference GLM text, code 131.1K 30 60000 33.8
@cf/zai-org/glm-4.7-flash Cloudflare Workers AI GLM text — — — 33.8
Qwen/Qwen3.5-27B ModelScope API-Inference Qwen text — — — 33.8
ZhipuAI/GLM-4.7-Flash ModelScope API-Inference GLM text — — — 33.8
glm-4.7 Ollama Cloud GLM text — — — 33.8
GLM-4.7-Flash Zhipu BigModel GLM Flash GLM text — — — 33.8
GLM-4.7 Zhipu ZCode GLM text — — — 33.8
GLM-4.7-Flash Zhipu ZCode GLM text — — — 33.8
Hy3 Preview NaraRouter Tencent text — — — 33.6
Grok 4 Microsoft for Startups Grok text — — — 33.3
o3-pro Microsoft for Startups GPT text — — — 32.5
Qwen3.5-122B-A10B Alibaba Cloud Model Studio Qwen text — — — 32.3
Qwen/Qwen3.5-122B-A10B ModelScope API-Inference Qwen text — — — 32.3
qwen3.5-122b-a10b NVIDIA NIM Qwen text — — — 32.3
Qwen3.5-122B-A10B Together AI Startup Accelerator Qwen text — — — 32.3
Qwen3.5-397B-A17B Alibaba Cloud Model Studio Qwen text — — — 32
Qwen/Qwen3.5-397B-A17B Hugging Face Inference Qwen text — — — 32
Qwen/Qwen3.5-397B-A17B ModelScope API-Inference Qwen text — — — 32
Qwen/Qwen3.5-397B-A17B Nebius AI Studio Qwen text — — — 32
qwen3.5-397b-a17b NVIDIA NIM Qwen text — — — 32
Qwen3.5-397B-A17B OVHcloud AI Endpoints Qwen text — — — 32
qwen3.5-397b-a17b Scaleway Qwen text — — — 32
Qwen3.6-35B-A3B iFlytek 讯飞星辰 MaaS — Free Qwen 3.6 Qwen text — — — 31.6
qwen3.6-35b-a3b Scaleway Qwen text — — — 31.6
openai/o3 Lightning AI GPT text — — — 30.4
o3 Microsoft for Startups GPT text — — — 30.4
Mistral Medium 3.5 Mistral AI — text — — — 29.9
Mistral Medium 3.5 Mistral La Plateforme API Mistral text, code, vision 262.1K — — 29.9
Mistral Medium 3.5 NaraRouter Mistral text — — — 29.9
mistral-medium-3.5-128b NVIDIA NIM Mistral text — — — 29.9
mistral-medium-3.5-128b Scaleway Mistral text — — — 29.9
step-3.7-flash NVIDIA NIM Step (StepFun) text — — — 29.7
Qwen3.5-35B-A3B Alibaba Cloud Model Studio Qwen text — — — 29.3
Qwen3.5-35B-A3B iFlytek 讯飞星辰 MaaS — Free Qwen 3.6 Qwen text — — — 29.3
Qwen/Qwen3.5-35B-A3B ModelScope API-Inference Qwen text — — — 29.3
cohere/command-a Vercel AI Gateway Cohere text — — — 29.3
Gemini 3 Flash Preview deprecated Google AI Studio / Gemini API Gemini text, image, audio, video 1M 10 250000 27.4
Gemini 3 Flash Google for Startups Cloud Program Gemini text — — — 27.4
google/gemini-3-flash-preview Lightning AI Gemini text — — — 27.4
Gemini 2.5 Pro Google for Startups Cloud Program Gemini text — — — 27
Gemini 2.5 Pro TTS Google for Startups Cloud Program Gemini text — — — 27
google/gemini-2.5-pro Lightning AI Gemini text — — — 27
@cf/google/gemma-4-26b-a4b-it Cloudflare Workers AI Gemma text — — — 25.7
Google: Gemma 4 26B A4B (free) OpenRouter Google text — — — 25.7
gemma-4-26b-a4b-it Scaleway Gemma text — — — 25.7
Gemini 3.1 Flash-Lite Google AI Studio / Gemini API Gemini text, image, audio, video 1M 15 250000 25
Gemini 3.1 Flash-Lite Google for Startups Cloud Program Gemini text — — — 25
google/gemini-3.1-flash-lite-preview Lightning AI Gemini text — — — 25
google/gemini-3.1-flash-lite Vercel AI Gateway Gemini text — — — 25
deepseek-ai/DeepSeek-V3.2-Exp Hugging Face Inference DeepSeek text — — — 24.7
DeepSeek V3.2 Inference.net API — text — — — 24.7
DeepSeek-V3.2 Microsoft for Startups DeepSeek text — — — 24.7
deepseek-ai/DeepSeek-V3.2 ModelScope API-Inference DeepSeek text — — — 24.7
deepseek-ai/DeepSeek-V3.2 Nebius AI Studio DeepSeek text — — — 24.7
Qwen3-Max (qwen3-max-2025-09-23, non-thinking) Alibaba Cloud Model Studio Qwen text — — — 24
Qwen3-Max (qwen3-max-2026-01-23, Thinking) Alibaba Cloud Model Studio Qwen text — — — 24
GPT OSS 120B Baseten GPT text — — — 23.8
OpenAI GPT OSS 120B (gpt-oss-120b) Cerebras Inference GPT text, code 131.1K 30 60000 23.8
@cf/openai/gpt-oss-120b Cloudflare Workers AI GPT text — — — 23.8
openai/gpt-oss-120b GroqCloud GPT text, code 131.1K 30 8000 23.8
openai/gpt-oss-120b Hugging Face Inference GPT text — — — 23.8
gpt-oss-120b Inference.net GPT text — — — 23.8
lightning-ai/gpt-oss-120b Lightning AI GPT-OSS text — — — 23.8
gpt-oss-120b Microsoft for Startups GPT text — — — 23.8
openai/gpt-oss-120b Nebius AI Studio GPT text — — — 23.8
GPT OSS 120B Nscale Serverless Inference GPT text — — — 23.8
gpt-oss-120b NVIDIA NIM GPT (OpenAI open) text — — — 23.8
gpt-oss-120b OpenAI for Startups GPT text — — — 23.8
OpenAI: gpt-oss-120b (free) OpenRouter OpenAI text — — — 23.8
gpt-oss-120b OVHcloud AI Endpoints GPT text — — — 23.8
gpt-oss-120b SambaNova Cloud GPT text — — — 23.8
gpt-oss-120b Scaleway GPT text — — — 23.8
zai-org/GLM-4.6 Hugging Face Inference GLM text — — — 23
qwen3-235b LLM7.io Qwen text — — — 22
grok-code-fast-1 Microsoft for Startups Grok text — — — 21.6
deepseek-ai/DeepSeek-V3.1-Terminus Hugging Face Inference DeepSeek text — — — 21.1
deepseek-ai/DeepSeek-V3.1 Nebius AI Studio DeepSeek text — — — 21.1
DeepSeek-V3.1 SambaNova Cloud DeepSeek text — — — 21.1
Mistral Small 4 Mistral AI — text — — — 20.8
Mistral Small 4 Mistral La Plateforme API Mistral text, code, vision 131.1K — — 20.8
mistral-small-4-119b-2603 NVIDIA NIM Mistral text — — — 20.8
DeepSeek-R1 GitHub Models DeepSeek text — — — 20.1
deepseek-ai/DeepSeek-R1 Hugging Face Inference DeepSeek text — — — 20.1
DeepSeek R1 Inference.net DeepSeek text — — — 20.1
DeepSeek R1 0528 Inference.net DeepSeek text — — — 20.1
gpt-4.1 GitHub Models GPT text — — — 19.4
moonshotai/Kimi-K2-Instruct Hugging Face Inference Kimi text — — — 19.4
moonshotai/Kimi-K2-Thinking Hugging Face Inference Kimi text — — — 19.4
openai/gpt-4.1 Lightning AI GPT text — — — 19.4
GPT-4.1 Microsoft for Startups GPT text — — — 19.4
openai/o3-mini Lightning AI GPT text — — — 19
zai-org/GLM-4.5-Air Hugging Face Inference GLM text — — — 16.5
gpt-4.1-mini GitHub Models GPT text — — — 16.3
GPT-4.1 mini Microsoft for Startups GPT text — — — 16.3
Mistral Large 3 (675B) AWS Bedrock Credits Mistral text — — — 16.2
Mistral Large 3 Microsoft for Startups Mistral text — — — 16.2
Mistral Large 3 Mistral AI — text — — — 16.2
Mistral Large 3 Mistral La Plateforme API Mistral text, code, vision 262.1K — — 16.2
Mistral Large NaraRouter Mistral text — — — 16.2
mistral-large-3-675b-instruct-2512 NVIDIA NIM Mistral text — — — 16.2
mistral/mistral-large-3 Vercel AI Gateway Mistral text — — — 16.2
Qwen3-8B SiliconFlow Qwen text — — — 15
@cf/openai/gpt-oss-20b Cloudflare Workers AI GPT text — — — 14.9
openai/gpt-oss-20b GroqCloud GPT text, code 131.1K 30 8000 14.9
openai/gpt-oss-20b Hugging Face Inference GPT text — — — 14.9
gpt-oss-20b Inference.net GPT text — — — 14.9
lightning-ai/gpt-oss-20b Lightning AI GPT-OSS text — — — 14.9
lightning-ai/nemotron-3-nano-omni-30b-a3b-reasoning Lightning AI Nemotron text — — — 14.9
gpt-oss-20b Microsoft for Startups GPT text — — — 14.9
openai/gpt-oss-20b Nebius AI Studio GPT text — — — 14.9
GPT OSS 20B Nscale Serverless Inference GPT text — — — 14.9
gpt-oss-20b NVIDIA NIM GPT (OpenAI open) text — — — 14.9
nemotron-3-nano-omni-30b-a3b-reasoning NVIDIA NIM Nemotron text — — — 14.9
gpt-oss-20b OpenAI for Startups GPT text — — — 14.9
gpt-oss-20b OVHcloud AI Endpoints GPT text — — — 14.9
GPT-OSS 20B (openai-fast) Pollinations AI GPT text — — — 14.9
gpt-oss-20B Together AI Startup Accelerator GPT text — — — 14.9
Llama 4 Maverick 17B AWS Bedrock Credits Llama text — — — 14.3
Llama-4-Maverick-17B-128E-Instruct-FP8 GitHub Models Llama text — — — 14.3
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 Hugging Face Inference Llama text — — — 14.3
Llama 4 Maverick 17B 128E FP8 Microsoft for Startups Llama text — — — 14.3
LLM-Research/Llama-4-Maverick-17B-128E-Instruct ModelScope API-Inference Llama text — — — 14.3
llama-4-maverick-17b-128e-instruct NVIDIA NIM Llama text — — — 14.3
meta/llama-4-maverick Vercel AI Gateway Llama text — — — 14.3
Gemini 2.5 Flash Google AI Studio / Gemini API Gemini text, image, audio, video 1M 10 250000 14.1
Gemini 2.5 Flash Live Preview Google AI Studio / Gemini API Gemini audio, video, text — — — 14.1
Gemini 2.5 Flash Native Audio (Live API) Google AI Studio / Gemini API Gemini audio, text — — — 14.1
Gemini 2.5 Flash Preview TTS Google AI Studio / Gemini API Gemini text, audio — — — 14.1
Gemini 2.5 Flash-Lite Google AI Studio / Gemini API Gemini text, image, audio, video 1M 15 250000 14.1
Gemini 2.5 Flash-Lite Preview (09-2025) Google AI Studio / Gemini API Gemini text, image, audio, video 1M 15 250000 14.1
Gemini 2.5 Flash Google for Startups Cloud Program Gemini text — — — 14.1
Gemini 2.5 Flash Live Google for Startups Cloud Program Gemini text — — — 14.1
Gemini 2.5 Flash TTS Google for Startups Cloud Program Gemini text — — — 14.1
Gemini 2.5 Flash-Lite Google for Startups Cloud Program Gemini text — — — 14.1
Nano Banana (Gemini 2.5 Flash Image) Google for Startups Cloud Program Gemini text — — — 14.1
google/gemini-2.5-flash Lightning AI Gemini text — — — 14.1
google/gemini-2.5-flash-lite-preview-06-17 Lightning AI Gemini text — — — 14.1
Mistral Medium 3.1 Mistral AI — text — — — 12.5
Mistral Medium 3.1 Mistral La Plateforme API Mistral text, code, vision 262.1K — — 12.5
Sarvam 105B Sarvam AI Mistral text — — — 11.9
gpt-4o GitHub Models GPT text — — — 11.2
openai/gpt-4o Lightning AI GPT text — — — 11.2
GPT-4o Microsoft for Startups GPT text — — — 11.2
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b Cloudflare Workers AI DeepSeek text — — — 11
DeepSeek V3 0324 Baseten DeepSeek text — — — 10.4
DeepSeek-V3 GitHub Models DeepSeek text — — — 10.4
DeepSeek V3 GMI Cloud DeepSeek text — — — 10.4
DeepSeek V3 Inference.net DeepSeek text — — — 10.4
DeepSeek V3 0324 Inference.net DeepSeek text — — — 10.4
Llama 4 Scout 17B AWS Bedrock Credits Llama text — — — 10
@cf/meta/llama-4-scout-17b-16e-instruct Cloudflare Workers AI Llama text — — — 10
Llama-4-Scout-17B-16E-Instruct GitHub Models Llama text — — — 10
meta-llama/llama-4-scout-17b-16e-instruct GroqCloud Llama text, image, code 131.1K 30 30000 10
meta-llama/Llama-4-Scout-17B-16E-Instruct Hugging Face Inference Llama text — — — 10
Llama 4 (Scout/Maverick) Inference.net API — text — — — 10
Llama 4 Scout 17B 16E Instruct Microsoft for Startups Llama text — — — 10
Llama 4 Scout 17B 16E Instruct Nscale Serverless Inference Llama text — — — 10
Llama 4 Scout Together AI Startup Accelerator Llama text — — — 10
meta/llama-4-scout Vercel AI Gateway Llama text — — — 10
Mistral Large 2.1 Mistral La Plateforme API Mistral text — — — 9.2
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 Nebius AI Studio Llama text — — — 9.1
Llama 3.1 405B Instruct AWS Bedrock Credits Llama text — — — 8.5
Meta-Llama-3.1-405B-Instruct GitHub Models Llama text — — — 8.5
Llama 3.1 405B Together AI Startup Accelerator Llama text — — — 8.5
openai/gpt-4-turbo Lightning AI GPT text — — — 7.9
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B Nebius AI Studio Nemotron text — — — 7.4
nemotron-3-nano-30b-a3b NVIDIA NIM Nemotron text — — — 7.4
NVIDIA: Nemotron 3 Nano 30B A3B (free) OpenRouter NVIDIA text — — — 7.4
gpt-4.1-nano GitHub Models GPT text — — — 7.3
@cf/qwen/qwen2.5-coder-32b-instruct Cloudflare Workers AI Qwen text — — — 7.1
Qwen/Qwen2.5-Coder-32B-Instruct Hugging Face Inference Qwen text — — — 7.1
gpt-4o-mini GitHub Models GPT text — — — 6.9
Sarvam 30B Sarvam AI Mistral text — — — 6.6
Gemma 3 27B Instruct Google for Startups Cloud Program Gemma text — — — 4.8
Gemma 3 27B Instruct Inference.net Gemma text — — — 4.8
Gemma 3 27B Together AI Startup Accelerator Gemma text — — — 4.8
Claude 3 Haiku AWS Bedrock Credits Claude text — — — 3.9
Jamba 3B (Jamba2 3B / Jamba Reasoning 3B) AI21 Studio Jamba text — — — —
Jamba Large 1.7 AI21 Studio Jamba text — — — —
Jamba Mini 2 (Jamba2 Mini) AI21 Studio Jamba text — — — —
aion-labs/aion-1.0 Aion Labs Aion text — — — —
aion-labs/aion-1.0-mini Aion Labs Aion text — — — —
aion-labs/aion-2.0 Aion Labs Aion text — — — —
aion-labs/aion-2.5 Aion Labs Aion text — — — —
aion-labs/aion-rp-llama-3.1-8b Aion Labs Aion text — — — —
CosyVoice (v2 / v3-flash/plus / v3.5) Alibaba Cloud Model Studio Qwen text — — — —
Fun-ASR / Paraformer Alibaba Cloud Model Studio Qwen text — — — —
multimodal-embedding-v1 Alibaba Cloud Model Studio Qwen text — — — —
QVQ (visual reasoning) Alibaba Cloud Model Studio Qwen text — — — —
Qwen-Flash (qwen-flash-2025-07-28) Alibaba Cloud Model Studio Qwen text — — — —
Qwen-Image / Qwen-Image-2.0(-Pro) / Qwen-Image-Max Alibaba Cloud Model Studio Qwen text — — — —
Qwen-Image-Edit (Plus/Max) Alibaba Cloud Model Studio Qwen text — — — —
Qwen-Math-Plus / Qwen-Math-Turbo Alibaba Cloud Model Studio Qwen text — — — —
Qwen-Max (qwen-max-2025-01-25, aka Qwen2.5-Max) Alibaba Cloud Model Studio Qwen text — — — —
Qwen-Omni-Turbo (+ Realtime) Alibaba Cloud Model Studio Qwen text — — — —
Qwen-Plus (qwen-plus-2025-12-01) Alibaba Cloud Model Studio Qwen text — — — —
Qwen-Turbo Alibaba Cloud Model Studio Qwen text — — — —
Qwen-VL-Max (qwen-vl-max-2025-08-13) Alibaba Cloud Model Studio Qwen text — — — —
Qwen-VL-OCR Alibaba Cloud Model Studio Qwen text — — — —
Qwen-VL-Plus Alibaba Cloud Model Studio Qwen text — — — —
Qwen3 dense (32B / 14B / 8B / 4B / 1.7B / 0.6B) Alibaba Cloud Model Studio Qwen text — — — —
Qwen3-235B-A22B-Instruct-2507 Alibaba Cloud Model Studio Qwen text — — — —
Qwen3-235B-A22B-Thinking-2507 Alibaba Cloud Model Studio Qwen text — — — —
Qwen3-30B-A3B (Thinking-2507 / Instruct-2507 / base) Alibaba Cloud Model Studio Qwen text — — — —
Qwen3-ASR-Flash (+ Realtime / Filetrans) Alibaba Cloud Model Studio Qwen text — — — —
Qwen3-Coder-480B-A35B-Instruct Alibaba Cloud Model Studio Qwen text — — — —
Qwen3-Coder-Flash / Qwen3-Coder-30B-A3B-Instruct Alibaba Cloud Model Studio Qwen text — — — —
Qwen3-Coder-Plus (qwen3-coder-plus-2025-09-23) Alibaba Cloud Model Studio Qwen text — — — —
Qwen3-Next-80B-A3B-Thinking / Instruct Alibaba Cloud Model Studio Qwen text — — — —
Qwen3-Omni-Flash (+ Realtime) Alibaba Cloud Model Studio Qwen text — — — —
Qwen3-TTS-Flash (+ Realtime / Instruct / VD) Alibaba Cloud Model Studio Qwen text — — — —
Qwen3-VL (235B-A22B / 30B-A3B / 32B / 8B; Instruct & Thinking) Alibaba Cloud Model Studio Qwen text — — — —
Qwen3.5-Flash (qwen3.5-flash-2026-02-23) Alibaba Cloud Model Studio Qwen text — — — —
Qwen3.5-Plus (qwen3.5-plus-2026-02-15) Alibaba Cloud Model Studio Qwen text — — — —
QwQ-Plus / QwQ-32B Alibaba Cloud Model Studio Qwen text — — — —
text-embedding-v4 / v3 Alibaba Cloud Model Studio Qwen text — — — —
Wan2.6 / Wan2.5 / Wan2.1 (text-to-image, image-edit, text/image-to-video) Alibaba Cloud Model Studio Wan text — — — —
Z-Image Alibaba Cloud Model Studio Qwen text — — — —
Amazon Nova 2 Lite AWS Bedrock Credits Nova text — — — —
Amazon Nova 2 Multimodal Embeddings AWS Bedrock Credits Nova text — — — —
Amazon Nova 2 Sonic AWS Bedrock Credits Nova text — — — —
Amazon Nova Canvas AWS Bedrock Credits Nova text — — — —
Amazon Nova Lite AWS Bedrock Credits Nova text — — — —
Amazon Nova Micro AWS Bedrock Credits Nova text — — — —
Amazon Nova Premier AWS Bedrock Credits Nova text — — — —
Amazon Nova Pro AWS Bedrock Credits Nova text — — — —
Amazon Nova Reel AWS Bedrock Credits Nova text — — — —
Amazon Nova Sonic AWS Bedrock Credits Nova text — — — —
Amazon Rerank AWS Bedrock Credits Amazon text — — — —
Amazon Titan Embeddings G1 - Text v1 AWS Bedrock Credits Titan text — — — —
Amazon Titan Image Generator G1 v2 AWS Bedrock Credits Titan text — — — —
Amazon Titan Multimodal Embeddings G1 AWS Bedrock Credits Titan text — — — —
Amazon Titan Text Embeddings V2 AWS Bedrock Credits Titan text — — — —
Claude 3.5 Haiku AWS Bedrock Credits Claude text — — — —
Claude Haiku 4.5 AWS Bedrock Credits Claude text — — — —
Claude Opus 4 AWS Bedrock Credits Claude text — — — —
Claude Opus 4.1 AWS Bedrock Credits Claude text — — — —
Claude Sonnet 4 AWS Bedrock Credits Claude text — — — —
Claude Sonnet 4.5 AWS Bedrock Credits Claude text — — — —
Llama 3 70B Instruct AWS Bedrock Credits Llama text — — — —
Llama 3 8B Instruct AWS Bedrock Credits Llama text — — — —
Llama 3.1 70B Instruct AWS Bedrock Credits Llama text — — — —
Llama 3.1 8B Instruct AWS Bedrock Credits Llama text — — — —
Llama 3.2 11B Vision AWS Bedrock Credits Llama text — — — —
Llama 3.2 90B Vision AWS Bedrock Credits Llama text — — — —
Llama 3.3 70B Instruct AWS Bedrock Credits Llama text — — — —
Mistral Large 24.07 AWS Bedrock Credits Mistral text — — — —
Mixtral 8x7B Instruct AWS Bedrock Credits Mistral text — — — —
Pixtral Large 25.02 AWS Bedrock Credits Mistral text — — — —
NVIDIA Nemotron 3 Super Baseten Nemotron text — — — —
Qwen3 Coder 480B Baseten Qwen text — — — —
btl-2 BTL Runtime Gemma text — — — —
Llama 3.3 70B Instruct BTL Runtime Llama text — — — —
@cf/aisingapore/gemma-sea-lion-v4-27b-it Cloudflare Workers AI Gemma text — — — —
@cf/google/gemma-2b-it-lora Cloudflare Workers AI Gemma text — — — —
@cf/google/gemma-3-12b-it Cloudflare Workers AI Gemma text — — — —
@cf/google/gemma-7b-it-lora Cloudflare Workers AI Gemma text — — — —
@cf/ibm-granite/granite-4.0-h-micro Cloudflare Workers AI Granite text — — — —
@cf/llava-hf/llava-1.5-7b-hf Cloudflare Workers AI LLaVA text — — — —
@cf/meta-llama/llama-2-7b-chat-hf-lora Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-2-7b-chat-fp16 Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-2-7b-chat-int8 Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-3-8b-instruct Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-3-8b-instruct-awq Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-3.1-70b-instruct-fp8-fast Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-3.1-8b-instruct Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-3.1-8b-instruct-awq Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-3.1-8b-instruct-fp8 Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-3.1-8b-instruct-fp8-fast Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-3.2-11b-vision-instruct Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-3.2-1b-instruct Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-3.2-3b-instruct Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-3.3-70b-instruct-fp8-fast Cloudflare Workers AI Llama text — — — —
@cf/meta/llama-guard-3-8b Cloudflare Workers AI Llama text — — — —
@cf/mistral/mistral-7b-instruct-v0.1 Cloudflare Workers AI Mistral text — — — —
@cf/mistral/mistral-7b-instruct-v0.2-lora Cloudflare Workers AI Mistral text — — — —
@cf/mistralai/mistral-small-3.1-24b-instruct Cloudflare Workers AI Mistral text — — — —
@cf/nousresearch/hermes-2-pro-mistral-7b Cloudflare Workers AI Mistral text — — — —
@cf/nvidia/nemotron-3-120b-a12b Cloudflare Workers AI Nemotron text — — — —
@cf/qwen/qwen3-30b-a3b-fp8 Cloudflare Workers AI Qwen text — — — —
@cf/qwen/qwq-32b Cloudflare Workers AI Qwen text — — — —
@hf/google/gemma-7b-it Cloudflare Workers AI Gemma text — — — —
@hf/mistral/mistral-7b-instruct-v0.2 Cloudflare Workers AI Mistral text — — — —
@hf/thebloke/llamaguard-7b-awq Cloudflare Workers AI Llama text — — — —
Aya Expanse 32B (c4ai-aya-expanse-32b) Cohere Trial API Key Aya text — — — —
Aya Vision 32B (c4ai-aya-vision-32b) Cohere Trial API Key Aya text — — — —
Cohere Transcribe (cohere-transcribe-03-2026) Cohere Trial API Key Cohere Transcribe text — — — —
Command (command) Cohere Trial API Key Command text — — — —
Command A (command-a-03-2025) Cohere Trial API Key Command text — — — —
Command A Reasoning (command-a-reasoning-08-2025) Cohere Trial API Key Command text — — — —
Command A Translate (command-a-translate-08-2025) Cohere Trial API Key Command text — — — —
Command A Vision (command-a-vision-07-2025) Cohere Trial API Key Command text — — — —
Command A+ (command-a-plus-05-2026) Cohere Trial API Key Command text — — — —
Command Light (command-light) Cohere Trial API Key Command text — — — —
Command R (command-r-03-2024 / alias command-r) Cohere Trial API Key Command text — — — —
Command R (command-r-08-2024) Cohere Trial API Key Command text — — — —
Command R+ (command-r-plus-04-2024 / alias command-r-plus) Cohere Trial API Key Command text — — — —
Command R+ (command-r-plus-08-2024) Cohere Trial API Key Command text — — — —
Command R7B (command-r7b-12-2024) Cohere Trial API Key Command text — — — —
Embed English/Multilingual v3.0 (embed-english-v3.0, embed-multilingual-v3.0 + light variants) Cohere Trial API Key Cohere Embed text — — — —
Embed v4.0 (embed-v4.0) Cohere Trial API Key Cohere Embed text — — — —
Rerank v4.0 (rerank-v4.0-pro / rerank-v4.0-fast) Cohere Trial API Key Cohere Rerank text — — — —
Tiny Aya Earth (tiny-aya-earth) Cohere Trial API Key Aya text — — — —
Tiny Aya Fire (tiny-aya-fire) Cohere Trial API Key Aya text — — — —
Tiny Aya Global (tiny-aya-global) Cohere Trial API Key Aya text — — — —
Tiny Aya Water (tiny-aya-water) Cohere Trial API Key Aya text — — — —
deepseek-chat (legacy alias) deprecated DeepSeek Platform DeepSeek text, code 1M — — —
deepseek-reasoner (legacy alias) deprecated DeepSeek Platform DeepSeek text, code 1M — — —
Codestral-2501 GitHub Models Mistral text — — — —
DeepSeek-R1-0528 GitHub Models DeepSeek text — — — —
DeepSeek-V3-0324 GitHub Models DeepSeek text — — — —
grok-3 GitHub Models Grok text — — — —
grok-3-mini GitHub Models Grok text — — — —
Llama-3.2-11B-Vision-Instruct GitHub Models Llama text — — — —
Llama-3.2-90B-Vision-Instruct GitHub Models Llama text — — — —
Llama-3.3-70B-Instruct GitHub Models Llama text — — — —
MAI-DS-R1 GitHub Models DeepSeek text — — — —
Meta-Llama-3-70B-Instruct GitHub Models Llama text — — — —
Meta-Llama-3-8B-Instruct GitHub Models Llama text — — — —
Meta-Llama-3.1-70B-Instruct GitHub Models Llama text — — — —
Meta-Llama-3.1-8B-Instruct GitHub Models Llama text — — — —
Ministral-3B GitHub Models Mistral text — — — —
Mistral-large-2407 GitHub Models Mistral text — — — —
Mistral-Large-2411 GitHub Models Mistral text — — — —
mistral-medium-2505 GitHub Models Mistral text — — — —
Mistral-Nemo GitHub Models Mistral text — — — —
Mistral-small GitHub Models Mistral text — — — —
mistral-small-2503 GitHub Models Mistral text — — — —
DeepSeek R1 Distill Qwen 1.5B GMI Cloud DeepSeek text — — — —
Llama-3.1-8B-Instruct GMI Cloud Llama text — — — —
Gemini 2.0 Flash deprecated Google AI Studio / Gemini API Gemini text, image, audio, video 1M 15 1000000 —
Gemini 2.0 Flash-Lite deprecated Google AI Studio / Gemini API Gemini text, image 1M 30 1000000 —
Gemini 3.1 Flash Live Preview Google AI Studio / Gemini API Gemini audio, video, text — — — —
Gemini 3.1 Flash TTS Preview Google AI Studio / Gemini API Gemini text, audio — — — —
Gemini Embedding (embedding-001) Google AI Studio / Gemini API Gemini embedding — — — —
Gemini Embedding 2 Google AI Studio / Gemini API Gemini embedding, multimodal — — — —
Gemini Robotics-ER 1.6 Preview Google AI Studio / Gemini API Gemini text, vision — — — —
Gemma 4 Google AI Studio / Gemini API Gemma text, image — — — —
Lyria RealTime Experimental Google AI Studio / Gemini API Lyria audio — — — —
Computer Use Google for Startups Cloud Program Gemini text — — — —
Gemini 2.0 Flash Google for Startups Cloud Program Gemini text — — — —
Gemini 2.0 Flash-Lite Google for Startups Cloud Program Gemini text — — — —
Gemini 3.1 Flash Live Google for Startups Cloud Program Gemini text — — — —
Gemini 3.1 Flash TTS Google for Startups Cloud Program Gemini text — — — —
Gemini Deep Research Google for Startups Cloud Program Gemini text — — — —
Gemini Embedding Google for Startups Cloud Program Gemini text — — — —
Gemini Embedding 2 Google for Startups Cloud Program Gemini text — — — —
Gemma 3n Google for Startups Cloud Program Gemma text — — — —
Gemma 4 Google for Startups Cloud Program Gemma text — — — —
Imagen 4 Google for Startups Cloud Program Gemini text — — — —
allam-2-7b GroqCloud ALLaM text — — — —
canopylabs/orpheus-arabic-saudi GroqCloud Orpheus (Canopy Labs) text, audio 4.1K — — —
canopylabs/orpheus-v1-english GroqCloud Orpheus (Canopy Labs) text, audio 4.1K — — —
groq/compound GroqCloud Groq (system) text, code 131.1K — — —
groq/compound-mini GroqCloud Groq (system) text, code 131.1K — — —
llama-3.1-8b-instant GroqCloud Llama text, code 131.1K 30 6000 —
llama-3.3-70b-versatile GroqCloud Llama text, code 131.1K 30 12000 —
meta-llama/llama-prompt-guard-2-22m GroqCloud Llama text 512 — — —
meta-llama/llama-prompt-guard-2-86m GroqCloud Llama text 512 — — —
openai/gpt-oss-safeguard-20b GroqCloud GPT text 131.1K 30 8000 —
qwen/qwen3-32b GroqCloud Qwen text, code 131.1K 60 6000 —
whisper-large-v3 GroqCloud Whisper audio — — — —
whisper-large-v3-turbo GroqCloud Whisper audio — — — —
CohereLabs/c4ai-command-a-03-2025 Hugging Face Inference Cohere text — — — —
CohereLabs/command-a-reasoning-08-2025 Hugging Face Inference Cohere text — — — —
deepseek-ai/DeepSeek-Prover-V2-671B Hugging Face Inference DeepSeek text — — — —
deepseek-ai/DeepSeek-R1-0528 Hugging Face Inference DeepSeek text — — — —
deepseek-ai/DeepSeek-V3-0324 Hugging Face Inference DeepSeek text — — — —
google/gemma-3-27b-it Hugging Face Inference Gemma text — — — —
meta-llama/Llama-3.3-70B-Instruct Hugging Face Inference Llama text — — — —
MiniMaxAI/MiniMax-M2 Hugging Face Inference MiniMax text — — — —
MiniMaxAI/MiniMax-M2.5 Hugging Face Inference MiniMax text — — — —
mistralai-not-listed/placeholder Hugging Face Inference Mistral text — — — —
moonshotai/Kimi-K2-Instruct-0905 Hugging Face Inference Kimi text — — — —
openai/gpt-oss-safeguard-20b Hugging Face Inference GPT text — — — —
Qwen/Qwen2.5-72B-Instruct Hugging Face Inference Qwen text — — — —
Qwen/Qwen3-235B-A22B-Instruct-2507 Hugging Face Inference Qwen text — — — —
Qwen/Qwen3-235B-A22B-Thinking-2507 Hugging Face Inference Qwen text — — — —
Qwen/Qwen3-Coder-480B-A35B-Instruct Hugging Face Inference Qwen text — — — —
Qwen/Qwen3-Next-80B-A3B-Thinking Hugging Face Inference Qwen text — — — —
Qwen/Qwen3-VL-235B-A22B-Instruct Hugging Face Inference Qwen text — — — —
Qwen/QwQ-32B Hugging Face Inference Qwen text — — — —
zai-org/GLM-4.5 Hugging Face Inference GLM text — — — —
zai-org/GLM-4.6V Hugging Face Inference GLM text — — — —
ClipTagger 12B Inference.net Gemma text — — — —
DeepSeek R1 Distill Llama 70B Inference.net DeepSeek text — — — —
Llama 3.1 70B Instruct Inference.net Llama text — — — —
Llama 3.1 8B Instruct Inference.net Llama text — — — —
Llama 3.2 11B Instruct Inference.net Llama text — — — —
Llama 3.2 1B Instruct Inference.net Llama text — — — —
Llama 3.2 3B Instruct Inference.net Llama text — — — —
Llama 3.3 70B Instruct Inference.net Llama text — — — —
Mistral Nemo 12B Instruct Inference.net Mistral text — — — —
Nemotron 3 Super Inference.net Nemotron text — — — —
Qwen2.5 7B Instruct Inference.net Qwen text — — — —
Qwen3 30B A3B Inference.net Qwen text — — — —
QwQ-32B Inference.net Qwen text — — — —
Schematron V2 Small Inference.net Llama text — — — —
Schematron V2 Turbo Inference.net Granite text — — — —
DeepSeek R1 family Inference.net API — text — — — —
Qwen3 family Inference.net API — text — — — —
Schematron-8B Inference.net API — text — — — —
jina-clip-v1 Jina AI Search Foundation Jina CLIP embedding, multimodal 8.2K — — —
jina-clip-v2 Jina AI Search Foundation Jina CLIP embedding, multimodal 8.2K — — —
jina-code-embeddings-0.5b Jina AI Search Foundation Jina (Qwen2.5-Coder-based) embedding, code 32.8K — — —
jina-code-embeddings-1.5b Jina AI Search Foundation Jina (Qwen2.5-Coder-based) embedding, code 32.8K — — —
jina-colbert-v2 Jina AI Search Foundation Jina ColBERT embedding 8.2K — — —
jina-embeddings-v2-base-code deprecated Jina AI Search Foundation Jina v2 embedding, code 8.2K — — —
jina-embeddings-v2-base-de deprecated Jina AI Search Foundation Jina v2 embedding 8.2K — — —
jina-embeddings-v2-base-en deprecated Jina AI Search Foundation Jina v2 embedding 8.2K — — —
jina-embeddings-v2-base-es deprecated Jina AI Search Foundation Jina v2 embedding 8.2K — — —
jina-embeddings-v2-base-zh deprecated Jina AI Search Foundation Jina v2 embedding 8.2K — — —
jina-embeddings-v3 Jina AI Search Foundation Jina (XLM-RoBERTa-based) embedding 8.2K — — —
jina-embeddings-v4 Jina AI Search Foundation Jina (Qwen2-VL-based) embedding, multimodal 32.8K — — —
jina-embeddings-v5-omni-nano Jina AI Search Foundation Jina embedding, multimodal 8.2K — — —
jina-embeddings-v5-omni-small Jina AI Search Foundation Jina (Qwen3-based) embedding, multimodal 32.8K — — —
jina-embeddings-v5-text-nano Jina AI Search Foundation Jina embedding 8.2K — — —
jina-embeddings-v5-text-small Jina AI Search Foundation Jina (Qwen3-based) embedding 32.8K — — —
jina-reranker-m0 Jina AI Search Foundation Jina Reranker embedding, multimodal 10.2K — — —
jina-reranker-v1-base-en / turbo-en / tiny-en deprecated Jina AI Search Foundation Jina Reranker embedding 8.2K — — —
jina-reranker-v2-base-multilingual Jina AI Search Foundation Jina Reranker embedding 1K — — —
jina-reranker-v3 Jina AI Search Foundation Jina Reranker embedding 131.1K — — —
jina-vlm Jina AI Search Foundation Jina VLM (Qwen-based) text, vision 32.8K — — —
ReaderLM-v2 Jina AI Search Foundation Jina ReaderLM (Qwen-based SLM) text, code 524.3K — — —
kilo-auto/free Kilo Code Gateway Router text — — — —
nvidia/nemotron-3-super-120b-a12b Kilo Code Gateway Nemotron text — — — —
openrouter/free Kilo Code Gateway Router text — — — —
minimax-m2.5 Kimchi MiniMax text — — — —
nemotron-3-super-fp4 Kimchi Nemotron text — — — —
anthropic/claude-haiku-4-5-20251001 Lightning AI Claude text — — — —
anthropic/claude-opus-4-1-20250805 Lightning AI Claude text — — — —
anthropic/claude-opus-4-20250514 Lightning AI Claude text — — — —
anthropic/claude-opus-4-5-20251101 Lightning AI Claude text — — — —
anthropic/claude-opus-4-6 Lightning AI Claude text — — — —
anthropic/claude-opus-4-7 Lightning AI Claude text — — — —
anthropic/claude-opus-4-8 Lightning AI Claude text — — — —
anthropic/claude-sonnet-4-5-20250929 Lightning AI Claude text — — — —
anthropic/claude-sonnet-4-6 Lightning AI Claude text — — — —
lightning-ai/gemma-4-31B-it Lightning AI Gemma text — — — —
lightning-ai/minimax-m2.5 Lightning AI MiniMax text — — — —
lightning-ai/nemotron-3-super-120b-a12b Lightning AI Nemotron text — — — —
openai/gpt-3.5-turbo Lightning AI GPT text — — — —
openai/gpt-4 Lightning AI GPT text — — — —
openai/gpt-4-turbo-preview Lightning AI GPT text — — — —
openai/gpt-5 Lightning AI GPT text — — — —
openai/gpt-5-mini Lightning AI GPT text — — — —
openai/gpt-5-nano Lightning AI GPT text — — — —
openai/gpt-5.2-2025-12-11 Lightning AI GPT text — — — —
openai/gpt-5.4-2026-03-05 Lightning AI GPT text — — — —
openai/gpt-5.5-2026-04-23 Lightning AI GPT text — — — —
codestral-latest LLM7.io Mistral text — — — —
default LLM7.io router alias text — — — —
devstral-small-2:24b LLM7.io Mistral (Devstral) text — — — —
fast LLM7.io router alias text — — — —
mistral-small-3.2 LLM7.io Mistral text — — — —
Claude Haiku 4.5 Microsoft for Startups Claude text — — — —
Codestral-2501 Microsoft for Startups Mistral text — — — —
GPT-5 Microsoft for Startups GPT text — — — —
GPT-5 mini Microsoft for Startups GPT text — — — —
GPT-5 nano Microsoft for Startups GPT text — — — —
GPT-5-codex Microsoft for Startups GPT text — — — —
GPT-5-pro Microsoft for Startups GPT text — — — —
GPT-5.4 pro Microsoft for Startups GPT text — — — —
gpt-image-2 Microsoft for Startups GPT text — — — —
grok-4-1-fast-reasoning Microsoft for Startups Grok text — — — —
Llama 3.3 70B Instruct Microsoft for Startups Llama text — — — —
mistral-medium-2505 Microsoft for Startups Mistral text — — — —
o3-deep-research Microsoft for Startups GPT text — — — —
o4-mini Microsoft for Startups GPT text — — — —
Codestral Mistral AI — text — — — —
Devstral 2 Mistral AI — text — — — —
Magistral Medium 1.2 Mistral AI — text — — — —
Magistral Small 1.2 Mistral AI — text — — — —
Ministral 3 14B Mistral AI — text — — — —
Ministral 3 8B Mistral AI — text — — — —
Classifier API model 3B Mistral La Plateforme API Mistral text — — — —
Classifier API model 8B Mistral La Plateforme API Mistral text — — — —
Codestral Mistral La Plateforme API Mistral text, code 262.1K — — —
Codestral Embed Mistral La Plateforme API Mistral text — — — —
Devstral 2 (Medium) Mistral La Plateforme API Mistral text, code 262.1K — — —
Devstral Small 2 Mistral La Plateforme API Mistral text, code 131.1K — — —
Leanstral Mistral La Plateforme API Mistral text — — — —
Magistral Medium 1.2 Mistral La Plateforme API Mistral text, code, vision 131.1K — — —
Magistral Small 1.2 Mistral La Plateforme API Mistral text, code, vision 131.1K — — —
Ministral 3 14B Mistral La Plateforme API Mistral text, vision 131.1K — — —
Ministral 3 3B Mistral La Plateforme API Mistral text 131.1K — — —
Ministral 3 8B Mistral La Plateforme API Mistral text, vision 131.1K — — —
Mistral 7B Mistral La Plateforme API Mistral text — — — —
Mistral Embed Mistral La Plateforme API Mistral embedding — — — —
Mistral Moderation 2 Mistral La Plateforme API Mistral text — — — —
Mistral NeMo Mistral La Plateforme API Mistral text — — — —
Mistral Small 3.2 Mistral La Plateforme API Mistral text — — — —
Mistral Small Creative Mistral La Plateforme API Mistral text — — — —
Mixtral 8x22B Mistral La Plateforme API Mistral text — — — —
Mixtral 8x7B Mistral La Plateforme API Mistral text — — — —
OCR 3 Mistral La Plateforme API Mistral text — — — —
Pixtral Large Mistral La Plateforme API Mistral text — — — —
Voxtral Mini Mistral La Plateforme API Voxtral text — — — —
Voxtral Mini Transcribe Mistral La Plateforme API Voxtral text — — — —
Voxtral Mini Transcribe 2 Mistral La Plateforme API Voxtral text — — — —
Voxtral Mini Transcribe Realtime Mistral La Plateforme API Voxtral text — — — —
Voxtral Small Mistral La Plateforme API Voxtral text, audio — — — —
Voxtral TTS Mistral La Plateforme API Voxtral text — — — —
LLM-Research/c4ai-command-r-plus-08-2024 ModelScope API-Inference Command-R text — — — —
MiniMax/MiniMax-M1-80k ModelScope API-Inference MiniMax text — — — —
MiniMax/MiniMax-M2.5 ModelScope API-Inference MiniMax text — — — —
mistralai/Ministral-8B-Instruct-2410 ModelScope API-Inference Mistral text — — — —
mistralai/Mistral-Large-Instruct-2407 ModelScope API-Inference Mistral text — — — —
mistralai/Mistral-Small-Instruct-2409 ModelScope API-Inference Mistral text — — — —
MusePublic/Qwen-Image-Edit ModelScope API-Inference Qwen text — — — —
PaddlePaddle/ERNIE-4.5-300B-A47B-PT ModelScope API-Inference ERNIE text — — — —
PaddlePaddle/ERNIE-4.5-VL-28B-A3B-PT ModelScope API-Inference ERNIE text — — — —
Qwen/Qwen-Image-Edit ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-14B ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-235B-A22B ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-235B-A22B-Instruct-2507 ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-235B-A22B-Thinking-2507 ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-30B-A3B ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-30B-A3B-Thinking-2507 ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-32B ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-4B ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-8B ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-Coder-30B-A3B-Instruct ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-Next-80B-A3B-Instruct ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-Next-80B-A3B-Thinking ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-VL-235B-A22B-Instruct ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-VL-8B-Instruct ModelScope API-Inference Qwen text — — — —
Qwen/Qwen3-VL-8B-Thinking ModelScope API-Inference Qwen text — — — —
BAAI/bge-en-icl Nebius AI Studio BGE text — — — —
BAAI/bge-multilingual-gemma2 Nebius AI Studio Gemma text — — — —
deepseek-ai/DeepSeek-V3-0324 Nebius AI Studio DeepSeek text — — — —
google/gemma-3-27b-it Nebius AI Studio Gemma text — — — —
intfloat/e5-mistral-7b-instruct Nebius AI Studio Mistral text — — — —
meta-llama/Llama-3.1-70B-Instruct Nebius AI Studio Llama text — — — —
meta-llama/Llama-3.2-1B-Instruct Nebius AI Studio Llama text — — — —
meta-llama/Llama-3.2-3B-Instruct Nebius AI Studio Llama text — — — —
meta-llama/Llama-3.3-70B-Instruct Nebius AI Studio Llama text — — — —
meta-llama/Llama-Guard-3-8B Nebius AI Studio Llama text — — — —
meta-llama/Meta-Llama-3.1-8B-Instruct Nebius AI Studio Llama text — — — —
MiniMaxAI/MiniMax-M2.5 Nebius AI Studio MiniMax text — — — —
NousResearch/Hermes-4-405B Nebius AI Studio Llama text — — — —
NousResearch/Hermes-4-70B Nebius AI Studio Llama text — — — —
nvidia/Cosmos3-Super-Reasoner Nebius AI Studio Nemotron text — — — —
nvidia/Nemotron-3-Nano-Omni Nebius AI Studio Nemotron text — — — —
nvidia/nemotron-3-super-120b-a12b Nebius AI Studio Nemotron text — — — —
openbmb/MiniCPM-V-4_5 Nebius AI Studio MiniCPM text — — — —
PrimeIntellect/INTELLECT-3 Nebius AI Studio INTELLECT text — — — —
Qwen/Qwen2.5-VL-72B-Instruct Nebius AI Studio Qwen text — — — —
Qwen/Qwen3-235B-A22B-Instruct-2507 Nebius AI Studio Qwen text — — — —
Qwen/Qwen3-30B-A3B-Instruct-2507 Nebius AI Studio Qwen text — — — —
Qwen/Qwen3-32B Nebius AI Studio Qwen text — — — —
Qwen/Qwen3-Coder-480B-A35B-Instruct Nebius AI Studio Qwen text — — — —
Qwen/Qwen3-Embedding-8B Nebius AI Studio Qwen text — — — —
Qwen/Qwen3-Next-80B-A3B-Thinking Nebius AI Studio Qwen text — — — —
Nex-N2-Pro Novita AI Other text — — — —
DeepSeek R1 Distill Llama 8B Nscale Serverless Inference DeepSeek text — — — —
DeepSeek R1 Distill Qwen 14B Nscale Serverless Inference DeepSeek text — — — —
DeepSeek R1 Distill Qwen 7B (Math) Nscale Serverless Inference DeepSeek text — — — —
Devstral Small 2505 Nscale Serverless Inference Mistral text — — — —
Flux.1 [schnell] Nscale Serverless Inference FLUX text — — — —
Llama 3.1 8B Instruct Nscale Serverless Inference Llama text — — — —
Llama 3.2 11B Vision Instruct Nscale Serverless Inference Llama text — — — —
Mixtral 8x22B Instruct v0.1 Nscale Serverless Inference Mistral text — — — —
Qwen 2.5 Coder 32B Instruct Nscale Serverless Inference Qwen text — — — —
Qwen 2.5 Coder 3B Instruct Nscale Serverless Inference Qwen text — — — —
Qwen 2.5 Coder 7B Instruct Nscale Serverless Inference Qwen text — — — —
Qwen 3 235B A22B Nscale Serverless Inference Qwen text — — — —
Qwen 3 235B A22B Instruct 2507 Nscale Serverless Inference Qwen text — — — —
Qwen3 4B Instruct 2507 Nscale Serverless Inference Qwen text — — — —
Qwen3 4B Thinking 2507 Nscale Serverless Inference Qwen text — — — —
Qwen3 Embedding 8B Nscale Serverless Inference Qwen text — — — —
diffusiongemma-26b-a4b-it NVIDIA NIM Gemma text — — — —
gemma-2-2b-it NVIDIA NIM Gemma text — — — —
gemma-3n-e2b-it NVIDIA NIM Gemma text — — — —
gemma-3n-e4b-it NVIDIA NIM Gemma text — — — —
gemma-4-31b-it NVIDIA NIM Gemma text — — — —
llama-3.1-70b-instruct NVIDIA NIM Llama text — — — —
llama-3.1-8b-instruct NVIDIA NIM Llama text — — — —
llama-3.1-nemotron-nano-8b-v1 NVIDIA NIM Nemotron (Llama) text — — — —
llama-3.2-90b-vision-instruct NVIDIA NIM Llama text — — — —
llama-3.3-70b-instruct NVIDIA NIM Llama text — — — —
llama-3.3-nemotron-super-49b-v1.5 NVIDIA NIM Nemotron (Llama) text — — — —
ministral-14b-instruct-2512 NVIDIA NIM Mistral text — — — —
mistral-nemotron NVIDIA NIM Mistral/Nemotron text — — — —
mixtral-8x7b-instruct-v0.1 NVIDIA NIM Mistral text — — — —
nemotron-3-super-120b-a12b NVIDIA NIM Nemotron text — — — —
nvidia-nemotron-nano-9b-v2 NVIDIA NIM Nemotron text — — — —
paligemma NVIDIA NIM Gemma text — — — —
qwen3-next-80b-a3b-instruct NVIDIA NIM Qwen text — — — —
seed-oss-36b-instruct NVIDIA NIM Seed (ByteDance) text — — — —
step-3.5-flash NVIDIA NIM Step (StepFun) text — — — —
gemma4 Ollama Cloud Gemma text — — — —
gpt-oss Ollama Cloud GPT text — — — —
minimax-m2.1 Ollama Cloud MiniMax text — — — —
minimax-m2.5 Ollama Cloud MiniMax text — — — —
nemotron-3-super Ollama Cloud Nemotron text — — — —
qwen3-coder Ollama Cloud Qwen text — — — —
omni-moderation OpenAI for Startups GPT text — — — —
Cohere: North Mini Code (free) OpenRouter Cohere text — — — —
Free Models Router OpenRouter openrouter text — — — —
Google: Gemma 4 31B (free) OpenRouter Google text — — — —
Google: Lyria 3 Clip Preview OpenRouter Google text — — — —
Google: Lyria 3 Pro Preview OpenRouter Google text — — — —
LiquidAI: LFM2.5-1.2B-Instruct (free) OpenRouter LiquidAI text — — — —
LiquidAI: LFM2.5-1.2B-Thinking (free) OpenRouter LiquidAI text — — — —
Meta: Llama 3.2 3B Instruct (free) OpenRouter Meta text — — — —
Meta: Llama 3.3 70B Instruct (free) OpenRouter Meta text — — — —
Nex AGI: Nex-N2-Pro (free) OpenRouter Nex AGI text — — — —
Nous: Hermes 3 405B Instruct (free) OpenRouter Nous text — — — —
NVIDIA: Nemotron 3 Nano Omni (free) OpenRouter NVIDIA text — — — —
NVIDIA: Nemotron 3 Super (free) OpenRouter NVIDIA text — — — —
NVIDIA: Nemotron 3.5 Content Safety (free) OpenRouter NVIDIA text — — — —
NVIDIA: Nemotron Nano 12B 2 VL (free) OpenRouter NVIDIA text — — — —
NVIDIA: Nemotron Nano 9B V2 (free) OpenRouter NVIDIA text — — — —
OpenAI: gpt-oss-20b (free) OpenRouter OpenAI text — — — —
Owl Alpha OpenRouter openrouter text — — — —
Poolside: Laguna M.1 (free) OpenRouter Poolside text — — — —
Poolside: Laguna XS.2 (free) OpenRouter Poolside text — — — —
Qwen: Qwen3 Coder 480B A35B (free) OpenRouter Qwen text — — — —
Qwen: Qwen3 Next 80B A3B Instruct (free) OpenRouter Qwen text — — — —
Venice: Uncensored (free) OpenRouter Venice text — — — —
bge-m3 OVHcloud AI Endpoints bge text — — — —
bge-multilingual-gemma2 OVHcloud AI Endpoints Gemma text — — — —
Meta-Llama-3_3-70B-Instruct OVHcloud AI Endpoints Llama text — — — —
Mistral-7B-Instruct-v0.3 OVHcloud AI Endpoints Mistral text — — — —
Mistral-Nemo-Instruct-2407 OVHcloud AI Endpoints Mistral text — — — —
Mistral-Small-3.2-24B-Instruct-2506 OVHcloud AI Endpoints Mistral text — — — —
nvr-tts-de-de OVHcloud AI Endpoints NVIDIA Riva text — — — —
nvr-tts-en-us OVHcloud AI Endpoints NVIDIA Riva text — — — —
nvr-tts-es-es OVHcloud AI Endpoints NVIDIA Riva text — — — —
nvr-tts-it-it OVHcloud AI Endpoints NVIDIA Riva text — — — —
Qwen2.5-VL-72B-Instruct OVHcloud AI Endpoints Qwen text — — — —
Qwen3-32B OVHcloud AI Endpoints Qwen text — — — —
Qwen3-Coder-30B-A3B-Instruct OVHcloud AI Endpoints Qwen text — — — —
Qwen3-Embedding-8B OVHcloud AI Endpoints Qwen text — — — —
Qwen3.5-9B OVHcloud AI Endpoints Qwen text — — — —
Qwen3Guard-Gen-0.6B OVHcloud AI Endpoints Qwen text — — — —
Qwen3Guard-Gen-8B OVHcloud AI Endpoints Qwen text — — — —
stable-diffusion-xl-base-v10 OVHcloud AI Endpoints Stable Diffusion text — — — —
whisper-large-v3 OVHcloud AI Endpoints Whisper text — — — —
whisper-large-v3-turbo OVHcloud AI Endpoints Whisper text — — — —
Meta-Llama-3.3-70B-Instruct SambaNova Cloud Llama text — — — —
Bulbul v3 Sarvam AI Sarvam text — — — —
Mayura Sarvam AI Sarvam text — — — —
Saaras v3 Sarvam AI Sarvam text — — — —
Saarika v2.5 Sarvam AI Sarvam text — — — —
Sarvam Translate Sarvam AI Sarvam text — — — —
Sarvam Vision Sarvam AI Sarvam text — — — —
Sarvam-M (sarvam-m) Sarvam AI Mistral text — — — —
bge-multilingual-gemma2 Scaleway Gemma text — — — —
devstral-2-123b-instruct-2512 Scaleway Mistral text — — — —
gemma-3-27b-it Scaleway Gemma text — — — —
holo2-30b-a3b Scaleway Other (H Company) text — — — —
llama-3.3-70b-instruct Scaleway Llama text — — — —
mistral-small-3.2-24b-instruct-2506 Scaleway Mistral text — — — —
pixtral-12b-2409 Scaleway Mistral text — — — —
qwen3-235b-a22b-instruct-2507 Scaleway Qwen text — — — —
qwen3-coder-30b-a3b-instruct Scaleway Qwen text — — — —
qwen3-embedding-8b Scaleway Qwen text — — — —
voxtral-small-24b-2507 Scaleway Mistral text — — — —
whisper-large-v3 Scaleway Other (OpenAI Whisper) text — — — —
Qwen2.5-7B-Instruct SiliconFlow Qwen text — — — —
Cogito v1 Preview Qwen 32B Together AI Startup Accelerator Qwen text — — — —
Devstral Small 2505 Together AI Startup Accelerator Mistral text — — — —
GLM 4.5V Together AI Startup Accelerator GLM text — — — —
Llama 3.1 70B Instruct Together AI Startup Accelerator Llama text — — — —
Llama 3.2 90B Vision Instruct Together AI Startup Accelerator Llama text — — — —
MiniMax M1 Together AI Startup Accelerator MiniMax text — — — —
MiniMax M2 Together AI Startup Accelerator MiniMax text — — — —
Mistral Small 3.2 24B Together AI Startup Accelerator Mistral text — — — —
Mixtral 8x22B Instruct Together AI Startup Accelerator Mistral text — — — —
Nemotron 3 Super 120B A12B Together AI Startup Accelerator Llama text — — — —
Qwen3 30B A3B Instruct 2507 Together AI Startup Accelerator Qwen text — — — —
Qwen3 32B Together AI Startup Accelerator Qwen text — — — —
Qwen3 Coder 30B A3B Instruct Together AI Startup Accelerator Qwen text — — — —
Qwen3 Next 80B A3B Instruct Together AI Startup Accelerator Qwen text — — — —
Qwen3 VL 235B A22B Instruct Together AI Startup Accelerator Qwen text — — — —
R1 Distill Qwen 7B Together AI Startup Accelerator DeepSeek text — — — —
bfl/flux Vercel AI Gateway FLUX text — — — —
google/gemini-3.1-flash-image Vercel AI Gateway Gemini text — — — —
google/gemma-4-31b-it Vercel AI Gateway Gemma text — — — —
klingai/kling-video Vercel AI Gateway Kling text — — — —
mistral/devstral-2 Vercel AI Gateway Mistral text — — — —
openai/gpt-5.5-pro Vercel AI Gateway GPT text — — — —
openai/gpt-image-2 Vercel AI Gateway GPT text — — — —
perplexity/sonar Vercel AI Gateway Perplexity text — — — —
voyage/voyage-3 Vercel AI Gateway Voyage text — — — —
xai/grok-4.20-reasoning Vercel AI Gateway Grok text — — — —
rerank-2.5 Voyage AI Voyage embedding — — — —
rerank-2.5-lite Voyage AI Voyage embedding — — — —
voyage-4 Voyage AI Voyage embedding — — — —
voyage-4-large Voyage AI Voyage embedding — — — —
voyage-4-lite Voyage AI Voyage embedding — — — —
voyage-4-nano Voyage AI Voyage embedding — — — —
voyage-code-2 Voyage AI Voyage embedding — — — —
voyage-code-3 Voyage AI Voyage embedding — — — —
voyage-context-3 Voyage AI Voyage embedding — — — —
voyage-finance-2 Voyage AI Voyage embedding — — — —
voyage-law-2 Voyage AI Voyage embedding — — — —
voyage-multimodal-3 Voyage AI Voyage embedding — — — —
voyage-multimodal-3.5 Voyage AI Voyage embedding — — — —
CogVideoX-Flash Zhipu BigModel GLM Flash GLM text — — — —
CogView-3-Flash Zhipu BigModel GLM Flash GLM text — — — —
GLM-4-Flash-250414 Zhipu BigModel GLM Flash GLM text — — — —
GLM-4.1V-Thinking-Flash Zhipu BigModel GLM Flash GLM text — — — —
GLM-4.5-Flash Zhipu BigModel GLM Flash GLM text — — — —
GLM-4.6V-Flash Zhipu BigModel GLM Flash GLM text — — — —
GLM-4V-Flash Zhipu BigModel GLM Flash GLM text — — — —
GLM-4.5-Flash Zhipu ZCode GLM text — — — —
GLM-4.6V-Flash Zhipu ZCode GLM text — — — —