Curated Directory of Free AI Models

⚠️
Important Disclaimer: Free AI models come with trade-offs. You may experience limited daily usage, random availability, data sharing for model training, temporary promotional deals, and smaller models that may not handle complex tasks. Use responsibly.

Free AI Models Directory

Curated collection of 318 AI models with zero cost for both input and output tokens

318 Free Models
32 Providers
107 Capabilities
0
0

Filter by Provider

All Free Models

OpenRouter (77 models)

OpenRouter
✓ FREE

Molmo2 8B (free)

Family: allenai

📄 Context: 37K tokens 📤 Output: 37K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Nemotron Nano 12B 2 VL (free)

Family: nemotron

📄 Context: 128K tokens 📤 Output: 128K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Nemotron 3 Nano 30B A3B (free)

Family: nemotron

📄 Context: 256K tokens 📤 Output: 256K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Uncensored (free)

Family: mistral

📄 Context: 33K tokens 📤 Output: 33K tokens
🔓 Open Weights
OpenRouter
✓ FREE

R1T Chimera (free)

Family: tngtech

📄 Context: 164K tokens 📤 Output: 164K tokens
🔓 Open Weights
OpenRouter
✓ FREE

gpt-oss-20b (free)

Family: gpt-oss

📄 Context: 131K tokens 📤 Output: 33K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Seedream 4.5

Family: seed

📄 Context: 4K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

FLUX.2 Pro

Family: flux

📄 Context: 47K tokens 📤 Output: 47K tokens
👁️ Vision
OpenRouter
✓ FREE

FLUX.2 Flex

Family: flux

📄 Context: 67K tokens 📤 Output: 67K tokens
👁️ Vision
OpenRouter
✓ FREE

FLUX.2 Max

Family: flux

📄 Context: 47K tokens 📤 Output: 47K tokens
👁️ Vision
OpenRouter
✓ FREE

FLUX.2 Klein 4B

Family: flux

📄 Context: 41K tokens 📤 Output: 41K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Step 3.5 Flash (free)

Family: step

📄 Context: 256K tokens 📤 Output: 256K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Trinity Large Preview

Family: trinity

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Trinity Mini

Family: trinity-mini

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenRouter
✓ FREE

LFM2.5-1.2B-Thinking (free)

Family: liquid

📄 Context: 131K tokens 📤 Output: 33K tokens
🔓 Open Weights
OpenRouter
✓ FREE

LFM2.5-1.2B-Instruct (free)

Family: liquid

📄 Context: 131K tokens 📤 Output: 33K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Riverflow V2 Fast Preview

Family: sourceful

📄 Context: 8K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Riverflow V2 Max Preview

Family: sourceful

📄 Context: 8K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Riverflow V2 Standard Preview

Family: sourceful

📄 Context: 8K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Sherlock Think Alpha

Family: sherlock

📄 Context: 1.8M tokens
👁️ Vision
OpenRouter
✓ FREE

Sherlock Dash Alpha

Family: sherlock

📄 Context: 1.8M tokens
👁️ Vision
OpenRouter
✓ FREE

Kat Coder Pro (free)

Family: kat-coder

📄 Context: 256K tokens 📤 Output: 66K tokens
OpenRouter
✓ FREE

Devstral 2 2512 (free)

Family: devstral

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen3 Next 80B A3B Instruct (free)

Family: qwen

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Nemotron Nano 9B V2 (free)

Family: nemotron

📄 Context: 128K tokens 📤 Output: 128K tokens
🔓 Open Weights
OpenRouter
✓ FREE

gpt-oss-120b (free)

Family: gpt-oss

📄 Context: 131K tokens 📤 Output: 33K tokens
🔓 Open Weights
OpenRouter
✓ FREE

GLM 4.5 Air (free)

Family: glm-air

📄 Context: 128K tokens 📤 Output: 96K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen3 Coder 480B A35B Instruct (free)

Family: qwen

📄 Context: 262K tokens 📤 Output: 67K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen3 4B (free)

Family: qwen

📄 Context: 41K tokens 📤 Output: 41K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen3 235B A22B Instruct 2507 (free)

Family: qwen

📄 Context: 262K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Kimi K2 (free)

Family: kimi

📄 Context: 33K tokens 📤 Output: 33K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Gemma 3n 2B (free)

Family: gemma

📄 Context: 8K tokens 📤 Output: 2K tokens
🔓 Open Weights
OpenRouter
✓ FREE

DeepSeek R1T2 Chimera (free)

Family: deepseek-thinking

📄 Context: 164K tokens 📤 Output: 164K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Mistral Small 3.2 24B Instruct

Family: mistral-small

📄 Context: 96K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Mistral Small 3.2 24B (free)

Family: mistral-small

📄 Context: 96K tokens 📤 Output: 96K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Kimi Dev 72b (free)

Family: kimi

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Deepseek R1 0528 Qwen3 8B (free)

Family: qwen

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenRouter
✓ FREE

R1 0528 (free)

Family: deepseek

📄 Context: 164K tokens 📤 Output: 164K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Sarvam-M (free)

Family: sarvam

📄 Context: 33K tokens 📤 Output: 33K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Devstral Small 2505 (free)

Family: devstral

📄 Context: 33K tokens 📤 Output: 33K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Gemma 3n 4B (free)

Family: gemma

📄 Context: 8K tokens 📤 Output: 2K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen3 32B (free)

Family: qwen

📄 Context: 41K tokens 📤 Output: 41K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen3 30B A3B (free)

Family: qwen

📄 Context: 41K tokens 📤 Output: 41K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen3 14B (free)

Family: qwen

📄 Context: 41K tokens 📤 Output: 41K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen3 235B A22B (free)

Family: qwen

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen3 8B (free)

Family: qwen

📄 Context: 41K tokens 📤 Output: 41K tokens
🔓 Open Weights
OpenRouter
✓ FREE

MAI DS R1 (free)

Family: mai

📄 Context: 164K tokens 📤 Output: 164K tokens
🔓 Open Weights
OpenRouter
✓ FREE

GLM Z1 32B (free)

Family: glm-z

📄 Context: 33K tokens 📤 Output: 33K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Llama 4 Scout (free)

Family: llama

📄 Context: 64K tokens 📤 Output: 64K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Llama 3.1 405B Instruct (free)

Family: llama

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenRouter
✓ FREE

DeepSeek V3 Base (free)

Family: deepseek

📄 Context: 164K tokens 📤 Output: 164K tokens
🔓 Open Weights
OpenRouter
✓ FREE

DeepSeek V3 0324

Family: deepseek

📄 Context: 16K tokens 📤 Output: 8K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen2.5 VL 32B Instruct (free)

Family: qwen

📄 Context: 8K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Qwerky 72B

Family: qwerky

📄 Context: 33K tokens 📤 Output: 8K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Mistral Small 3.1 24B Instruct

Family: mistral-small

📄 Context: 128K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Gemma 3 12B (free)

Family: gemma

📄 Context: 33K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Gemma 3 4B (free)

Family: gemma

📄 Context: 33K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Reka Flash 3

Family: reka

📄 Context: 33K tokens 📤 Output: 8K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Gemma 3 27B (free)

Family: gemma

📄 Context: 131K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

QwQ 32B (free)

Family: qwen

📄 Context: 33K tokens 📤 Output: 33K tokens
🔓 Open Weights
OpenRouter
✓ FREE

DeepHermes 3 Llama 3 8B Preview

Family: llama

📄 Context: 131K tokens 📤 Output: 8K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Dolphin3.0 R1 Mistral 24B

Family: mistral

📄 Context: 33K tokens 📤 Output: 8K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Dolphin3.0 Mistral 24B

Family: mistral

📄 Context: 33K tokens 📤 Output: 8K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen2.5 VL 72B Instruct

Family: qwen

📄 Context: 33K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Qwen2.5 VL 72B Instruct (free)

Family: qwen

📄 Context: 33K tokens 📤 Output: 33K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

DeepSeek R1 Distill Qwen 14B

Family: qwen

📄 Context: 64K tokens 📤 Output: 8K tokens
🔓 Open Weights
OpenRouter
✓ FREE

DeepSeek R1 Distill Llama 70B

Family: deepseek-thinking

📄 Context: 8K tokens 📤 Output: 8K tokens
🔓 Open Weights
OpenRouter
✓ FREE

R1 (free)

Family: deepseek

📄 Context: 164K tokens 📤 Output: 164K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Gemini 2.0 Flash Experimental (free)

Family: gemini-flash

📄 Context: 1.0M tokens 📤 Output: 1.0M tokens
👁️ Vision
OpenRouter
✓ FREE

Llama 3.3 70B Instruct (free)

Family: llama

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Qwen2.5 Coder 32B Instruct

Family: qwen

📄 Context: 33K tokens 📤 Output: 8K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Llama 3.2 11B Vision Instruct

Family: llama

📄 Context: 131K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Llama 3.2 3B Instruct (free)

Family: llama

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Qwen2.5-VL 7B Instruct (free)

Family: qwen

📄 Context: 33K tokens 📤 Output: 33K tokens
🔓 Open Weights👁️ Vision
OpenRouter
✓ FREE

Hermes 3 405B Instruct (free)

Family: hermes

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Mistral Nemo (free)

Family: mistral-nemo

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenRouter
✓ FREE

Mistral 7B Instruct (free)

Family: mistral

📄 Context: 33K tokens 📤 Output: 33K tokens
🔓 Open Weights

Nvidia (60 models)

Nvidia
✓ FREE

Kimi K2.5

Family: kimi

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights👁️ Vision
Nvidia
✓ FREE

MiniMax-M2.1

Family: minimax

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights
Nvidia
✓ FREE

GLM-4.7

Family: glm

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights
Nvidia
✓ FREE

Devstral-2-123B-Instruct-2512

Family: devstral

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights
Nvidia
✓ FREE

Ministral 3 14B Instruct 2512

Family: ministral

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights👁️ Vision
Nvidia
✓ FREE

Mistral Large 3 675B Instruct 2512

Family: mistral-large

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights👁️ Vision
Nvidia
✓ FREE

DeepSeek V3.2

Family: deepseek

📄 Context: 164K tokens 📤 Output: 66K tokens
Nvidia
✓ FREE

Kimi K2 Thinking

Family: kimi-thinking

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights
Nvidia
✓ FREE

MiniMax-M2

Family: minimax

📄 Context: 128K tokens 📤 Output: 16K tokens
🔓 Open Weights
Nvidia
✓ FREE

DeepSeek V3.1 Terminus

Family: deepseek

📄 Context: 128K tokens 📤 Output: 8K tokens
Nvidia
✓ FREE

Llama-3.1-Nemotron-Ultra-253B-v1

Family: llama

📄 Context: 131K tokens 📤 Output: 8K tokens
Nvidia
✓ FREE

Parakeet TDT 0.6B v2

Family: parakeet

📤 Output: 4K tokens
🎵 Audio
Nvidia
✓ FREE

Cosmos Nemotron 34B

Family: nemotron

📄 Context: 131K tokens 📤 Output: 8K tokens
👁️ Vision
Nvidia
✓ FREE

NeMo Retriever OCR v1

Family: nemoretriever

📤 Output: 4K tokens
👁️ Vision
Nvidia
✓ FREE

Kimi K2 Instruct

Family: kimi

📄 Context: 128K tokens 📤 Output: 8K tokens
Nvidia
✓ FREE

Kimi K2 0905

Family: kimi

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights
Nvidia
✓ FREE

Gemma-3-27B-IT

Family: gemma

📄 Context: 131K tokens 📤 Output: 8K tokens
👁️ Vision
Nvidia
✓ FREE

Qwen3-Next-80B-A3B-Thinking

Family: qwen

📄 Context: 262K tokens 📤 Output: 16K tokens
🔓 Open Weights
Nvidia
✓ FREE

Qwen3-235B-A22B

Family: qwen

📄 Context: 131K tokens 📤 Output: 8K tokens
Nvidia
✓ FREE

Qwen3-Next-80B-A3B-Instruct

Family: qwen

📄 Context: 262K tokens 📤 Output: 16K tokens
Nvidia
✓ FREE

Whisper Large v3

Family: whisper

📤 Output: 4K tokens
🔓 Open Weights🎵 Audio
Nvidia
✓ FREE

FLUX.1-dev

Family: flux

📄 Context: 4K tokens
Nvidia
✓ FREE

DeepSeek V3.1

Family: deepseek

📄 Context: 128K tokens 📤 Output: 8K tokens
Nvidia
✓ FREE

nvidia-nemotron-nano-9b-v2

Family: nemotron

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
Nvidia
✓ FREE

GPT-OSS-120B

Family: gpt-oss

📄 Context: 128K tokens 📤 Output: 8K tokens
Nvidia
✓ FREE

Qwen3 Coder 480B A35B Instruct

Family: qwen

📄 Context: 262K tokens 📤 Output: 67K tokens
Nvidia
✓ FREE

Gemma 3n E2b It

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision
Nvidia
✓ FREE

Gemma 3n E4b It

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision
Nvidia
✓ FREE

Deepseek R1 0528

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Llama 4 Maverick 17b 128e Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision
Nvidia
✓ FREE

Llama Embed Nemotron 8B

Family: llama

📄 Context: 33K tokens 📤 Output: 2K tokens
Nvidia
✓ FREE

Llama 3.3 Nemotron Super 49b V1.5

📄 Context: 128K tokens 📤 Output: 4K tokens
Nvidia
✓ FREE

Llama 3.3 Nemotron Super 49b V1

📄 Context: 128K tokens 📤 Output: 4K tokens
Nvidia
✓ FREE

Mistral Small 3.1 24b Instruct 2503

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Gemma 3 1b It

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision
Nvidia
✓ FREE

Qwq 32b

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Gemma 3 12b It

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Deepseek R1

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

nemotron-3-nano-30b-a3b

Family: nemotron

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
Nvidia
✓ FREE

Qwen2.5 Coder 32b Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Llama 3.1 Nemotron 70b Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
Nvidia
✓ FREE

Llama 3.1 Nemotron 51b Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
Nvidia
✓ FREE

Llama 3.2 1b Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Qwen2.5 Coder 7b Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Mistral Large 2 Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Gemma 2 2b It

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Llama 3.1 70b Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Llama 3.1 405b Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Mamba Codestral 7b V0.1

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Gemma 2 27b It

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Nemotron 4 340b Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
Nvidia
✓ FREE

Codestral 22b Instruct V0.1

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Phi 3 Vision 128k Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision
Nvidia
✓ FREE

Codegemma 1.1 7b

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Llama3 Chatqa 1.5 70b

📄 Context: 128K tokens 📤 Output: 4K tokens
Nvidia
✓ FREE

Llama3 8b Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Llama3 70b Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Codegemma 7b

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Codellama 70b

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Nvidia
✓ FREE

Deepseek Coder 6.7b Instruct

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights

GitHub Models (55 models)

GitHub Models
✓ FREE

DeepSeek-R1-0528

Family: deepseek-thinking

📄 Context: 66K tokens 📤 Output: 8K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Mistral Medium 3 (25.05)

Family: mistral-medium

📄 Context: 128K tokens 📤 Output: 33K tokens
👁️ Vision
GitHub Models
✓ FREE

GPT-4.1-nano

Family: gpt-nano

📄 Context: 128K tokens 📤 Output: 16K tokens
👁️ Vision
GitHub Models
✓ FREE

GPT-4.1

Family: gpt

📄 Context: 128K tokens 📤 Output: 16K tokens
👁️ Vision
GitHub Models
✓ FREE

GPT-4.1-mini

Family: gpt-mini

📄 Context: 128K tokens 📤 Output: 16K tokens
👁️ Vision
GitHub Models
✓ FREE

DeepSeek-V3-0324

Family: deepseek

📄 Context: 128K tokens 📤 Output: 8K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Mistral Small 3.1

Family: mistral-small

📄 Context: 128K tokens 📤 Output: 33K tokens
👁️ Vision
GitHub Models
✓ FREE

Llama 4 Scout 17B 16E Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
GitHub Models
✓ FREE

Llama 4 Maverick 17B 128E Instruct FP8

Family: llama

📄 Context: 128K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
GitHub Models
✓ FREE

OpenAI o3

Family: o

📄 Context: 200K tokens 📤 Output: 100K tokens
👁️ Vision
GitHub Models
✓ FREE

OpenAI o4-mini

Family: o-mini

📄 Context: 200K tokens 📤 Output: 100K tokens
👁️ Vision
GitHub Models
✓ FREE

OpenAI o3-mini

Family: o-mini

📄 Context: 200K tokens 📤 Output: 100K tokens
GitHub Models
✓ FREE

MAI-DS-R1

Family: mai

📄 Context: 66K tokens 📤 Output: 8K tokens
GitHub Models
✓ FREE

DeepSeek-R1

Family: deepseek-thinking

📄 Context: 66K tokens 📤 Output: 8K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Codestral 25.01

Family: codestral

📄 Context: 32K tokens 📤 Output: 8K tokens
GitHub Models
✓ FREE

OpenAI o1

Family: o

📄 Context: 200K tokens 📤 Output: 100K tokens
👁️ Vision
GitHub Models
✓ FREE

OpenAI o1-mini

Family: o-mini

📄 Context: 128K tokens 📤 Output: 66K tokens
GitHub Models
✓ FREE

Phi-4-mini-instruct

Family: phi

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Phi-4-multimodal-instruct

Family: phi

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision🎵 Audio
GitHub Models
✓ FREE

Phi-4

Family: phi

📄 Context: 16K tokens 📤 Output: 4K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Phi-4-mini-reasoning

Family: phi

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Phi-4-Reasoning

Family: phi

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Grok 3

Family: grok

📄 Context: 128K tokens 📤 Output: 8K tokens
GitHub Models
✓ FREE

Grok 3 Mini

Family: grok

📄 Context: 128K tokens 📤 Output: 8K tokens
GitHub Models
✓ FREE

Llama-3.3-70B-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 33K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Mistral Large 24.11

Family: mistral-large

📄 Context: 128K tokens 📤 Output: 33K tokens
GitHub Models
✓ FREE

Cohere Command A

Family: command-a

📄 Context: 128K tokens 📤 Output: 4K tokens
GitHub Models
✓ FREE

Ministral 3B

Family: ministral

📄 Context: 128K tokens 📤 Output: 8K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Llama-3.2-11B-Vision-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision🎵 Audio
GitHub Models
✓ FREE

Llama-3.2-90B-Vision-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision🎵 Audio
GitHub Models
✓ FREE

OpenAI o1-preview

Family: o

📄 Context: 128K tokens 📤 Output: 33K tokens
GitHub Models
✓ FREE

AI21 Jamba 1.5 Mini

Family: jamba

📄 Context: 256K tokens 📤 Output: 4K tokens
GitHub Models
✓ FREE

AI21 Jamba 1.5 Large

Family: jamba

📄 Context: 256K tokens 📤 Output: 4K tokens
GitHub Models
✓ FREE

Phi-3.5-mini instruct (128k)

Family: phi

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Phi-3.5-MoE instruct (128k)

Family: phi

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Phi-3.5-vision instruct (128k)

Family: phi

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision
GitHub Models
✓ FREE

Cohere Command R+ 08-2024

Family: command-r

📄 Context: 128K tokens 📤 Output: 4K tokens
GitHub Models
✓ FREE

Cohere Command R

Family: command-r

📄 Context: 128K tokens 📤 Output: 4K tokens
GitHub Models
✓ FREE

Cohere Command R 08-2024

Family: command-r

📄 Context: 128K tokens 📤 Output: 4K tokens
GitHub Models
✓ FREE

Cohere Command R+

Family: command-r

📄 Context: 128K tokens 📤 Output: 4K tokens
GitHub Models
✓ FREE

Meta-Llama-3.1-405B-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 33K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Meta-Llama-3.1-70B-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 33K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Meta-Llama-3.1-8B-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 33K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Mistral Nemo

Family: mistral-nemo

📄 Context: 128K tokens 📤 Output: 8K tokens
🔓 Open Weights
GitHub Models
✓ FREE

GPT-4o mini

Family: gpt-mini

📄 Context: 128K tokens 📤 Output: 16K tokens
👁️ Vision🎵 Audio
GitHub Models
✓ FREE

GPT-4o

Family: gpt

📄 Context: 128K tokens 📤 Output: 16K tokens
👁️ Vision🎵 Audio
GitHub Models
✓ FREE

Phi-3-small instruct (128k)

Family: phi

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Phi-3-medium instruct (128k)

Family: phi

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Phi-3-medium instruct (4k)

Family: phi

📄 Context: 4K tokens 📤 Output: 1K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Phi-3-small instruct (8k)

Family: phi

📄 Context: 8K tokens 📤 Output: 2K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Phi-3-mini instruct (4k)

Family: phi

📄 Context: 4K tokens 📤 Output: 1K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Phi-3-mini instruct (128k)

Family: phi

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Meta-Llama-3-8B-Instruct

Family: llama

📄 Context: 8K tokens 📤 Output: 2K tokens
🔓 Open Weights
GitHub Models
✓ FREE

Meta-Llama-3-70B-Instruct

Family: llama

📄 Context: 8K tokens 📤 Output: 2K tokens
🔓 Open Weights
GitHub Models
✓ FREE

JAIS 30b Chat

Family: jais

📄 Context: 8K tokens 📤 Output: 2K tokens
🔓 Open Weights

GitHub Copilot (20 models)

GitHub Copilot
✓ FREE

Claude Opus 4.6

Family: claude-opus

📄 Context: 128K tokens 📤 Output: 64K tokens
👁️ Vision
GitHub Copilot
✓ FREE

Gemini 3 Flash

Family: gemini-flash

📄 Context: 128K tokens 📤 Output: 64K tokens
👁️ Vision🎵 Audio
GitHub Copilot
✓ FREE

GPT-5.2-Codex

Family: gpt-codex

📄 Context: 272K tokens 📤 Output: 128K tokens
👁️ Vision
GitHub Copilot
✓ FREE

GPT-5.2

Family: gpt

📄 Context: 128K tokens 📤 Output: 64K tokens
👁️ Vision
GitHub Copilot
✓ FREE

GPT-5.1-Codex-max

Family: gpt-codex

📄 Context: 128K tokens 📤 Output: 128K tokens
👁️ Vision
GitHub Copilot
✓ FREE

Gemini 3 Pro Preview

Family: gemini-pro

📄 Context: 128K tokens 📤 Output: 64K tokens
👁️ Vision🎵 Audio
GitHub Copilot
✓ FREE

GPT-5.1

Family: gpt

📄 Context: 128K tokens 📤 Output: 64K tokens
👁️ Vision
GitHub Copilot
✓ FREE

GPT-5.1-Codex-mini

Family: gpt-codex

📄 Context: 128K tokens 📤 Output: 128K tokens
👁️ Vision
GitHub Copilot
✓ FREE

GPT-5.1-Codex

Family: gpt-codex

📄 Context: 128K tokens 📤 Output: 128K tokens
👁️ Vision
GitHub Copilot
✓ FREE

Claude Haiku 4.5

Family: claude-haiku

📄 Context: 128K tokens 📤 Output: 32K tokens
👁️ Vision
GitHub Copilot
✓ FREE

Claude Sonnet 4.5

Family: claude-sonnet

📄 Context: 128K tokens 📤 Output: 32K tokens
👁️ Vision
GitHub Copilot
✓ FREE

Grok Code Fast 1

Family: grok

📄 Context: 128K tokens 📤 Output: 64K tokens
GitHub Copilot
✓ FREE

GPT-5-mini

Family: gpt-mini

📄 Context: 128K tokens 📤 Output: 64K tokens
👁️ Vision
GitHub Copilot
✓ FREE

GPT-5

Family: gpt

📄 Context: 128K tokens 📤 Output: 128K tokens
👁️ Vision
GitHub Copilot
✓ FREE

Claude Opus 4.1

Family: claude-opus

📄 Context: 80K tokens 📤 Output: 16K tokens
👁️ Vision
GitHub Copilot
✓ FREE

Claude Opus 4.5

Family: claude-opus

📄 Context: 128K tokens 📤 Output: 32K tokens
👁️ Vision
GitHub Copilot
✓ FREE

Gemini 2.5 Pro

Family: gemini-pro

📄 Context: 128K tokens 📤 Output: 64K tokens
👁️ Vision🎵 Audio
GitHub Copilot
✓ FREE

Claude Sonnet 4

Family: claude-sonnet

📄 Context: 128K tokens 📤 Output: 16K tokens
👁️ Vision
GitHub Copilot
✓ FREE

GPT-4.1

Family: gpt

📄 Context: 64K tokens 📤 Output: 16K tokens
👁️ Vision
GitHub Copilot
✓ FREE

GPT-4o

Family: gpt

📄 Context: 64K tokens 📤 Output: 16K tokens
👁️ Vision

iFlow (13 models)

iFlow
✓ FREE

Kimi-K2-0905

Family: kimi

📄 Context: 256K tokens 📤 Output: 64K tokens
iFlow
✓ FREE

Qwen3-235B-A22B-Instruct

Family: qwen

📄 Context: 256K tokens 📤 Output: 64K tokens
🔓 Open Weights
iFlow
✓ FREE

Qwen3-235B-A22B-Thinking

Family: qwen

📄 Context: 256K tokens 📤 Output: 64K tokens
🔓 Open Weights
iFlow
✓ FREE

Qwen3-Coder-Plus

Family: qwen

📄 Context: 256K tokens 📤 Output: 64K tokens
🔓 Open Weights
iFlow
✓ FREE

DeepSeek-R1

Family: deepseek-thinking

📄 Context: 128K tokens 📤 Output: 32K tokens
🔓 Open Weights
iFlow
✓ FREE

Qwen3-Max-Preview

Family: qwen

📄 Context: 256K tokens 📤 Output: 32K tokens
iFlow
✓ FREE

DeepSeek-V3.2-Exp

Family: deepseek

📄 Context: 128K tokens 📤 Output: 64K tokens
🔓 Open Weights
iFlow
✓ FREE

Qwen3-VL-Plus

Family: qwen

📄 Context: 256K tokens 📤 Output: 32K tokens
👁️ Vision
iFlow
✓ FREE

Qwen3-Max

Family: qwen

📄 Context: 256K tokens 📤 Output: 32K tokens
iFlow
✓ FREE

DeepSeek-V3

Family: deepseek

📄 Context: 128K tokens 📤 Output: 32K tokens
🔓 Open Weights
iFlow
✓ FREE

Kimi-K2

Family: kimi

📄 Context: 128K tokens 📤 Output: 64K tokens
iFlow
✓ FREE

Qwen3-32B

Family: qwen

📄 Context: 128K tokens 📤 Output: 32K tokens
🔓 Open Weights
iFlow
✓ FREE

Qwen3-235B-A22B

Family: qwen

📄 Context: 128K tokens 📤 Output: 32K tokens
🔓 Open Weights

Z.AI Coding Plan (9 models)

Z.AI Coding Plan
✓ FREE

GLM-5

Family: glm

📄 Context: 205K tokens 📤 Output: 131K tokens
Z.AI Coding Plan
✓ FREE

GLM-4.7-Flash

Family: glm-flash

📄 Context: 200K tokens 📤 Output: 131K tokens
🔓 Open Weights
Z.AI Coding Plan
✓ FREE

GLM-4.7

Family: glm

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights
Z.AI Coding Plan
✓ FREE

GLM-4.6V

Family: glm

📄 Context: 128K tokens 📤 Output: 33K tokens
🔓 Open Weights👁️ Vision
Z.AI Coding Plan
✓ FREE

GLM-4.6

Family: glm

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights
Z.AI Coding Plan
✓ FREE

GLM-4.5V

Family: glm

📄 Context: 64K tokens 📤 Output: 16K tokens
🔓 Open Weights👁️ Vision
Z.AI Coding Plan
✓ FREE

GLM-4.5-Flash

Family: glm-flash

📄 Context: 131K tokens 📤 Output: 98K tokens
🔓 Open Weights
Z.AI Coding Plan
✓ FREE

GLM-4.5

Family: glm

📄 Context: 131K tokens 📤 Output: 98K tokens
🔓 Open Weights
Z.AI Coding Plan
✓ FREE

GLM-4.5-Air

Family: glm-air

📄 Context: 131K tokens 📤 Output: 98K tokens
🔓 Open Weights

GitLab Duo (9 models)

GitLab Duo
✓ FREE

Agentic Chat (Claude Opus 4.6)

Family: claude-opus

📄 Context: 200K tokens 📤 Output: 64K tokens
👁️ Vision
GitLab Duo
✓ FREE

Agentic Chat (GPT-5.2)

Family: gpt

📄 Context: 400K tokens 📤 Output: 128K tokens
👁️ Vision
GitLab Duo
✓ FREE

Agentic Chat (GPT-5.2 Codex)

Family: gpt-codex

📄 Context: 400K tokens 📤 Output: 128K tokens
👁️ Vision
GitLab Duo
✓ FREE

Agentic Chat (GPT-5 Mini)

Family: gpt-mini

📄 Context: 400K tokens 📤 Output: 128K tokens
👁️ Vision
GitLab Duo
✓ FREE

Agentic Chat (GPT-5 Codex)

Family: gpt-codex

📄 Context: 400K tokens 📤 Output: 128K tokens
👁️ Vision
GitLab Duo
✓ FREE

Agentic Chat (GPT-5.1)

Family: gpt

📄 Context: 400K tokens 📤 Output: 128K tokens
👁️ Vision
GitLab Duo
✓ FREE

Agentic Chat (Claude Sonnet 4.5)

Family: claude-sonnet

📄 Context: 200K tokens 📤 Output: 64K tokens
👁️ Vision
GitLab Duo
✓ FREE

Agentic Chat (Claude Haiku 4.5)

Family: claude-haiku

📄 Context: 200K tokens 📤 Output: 64K tokens
👁️ Vision
GitLab Duo
✓ FREE

Agentic Chat (Claude Opus 4.5)

Family: claude-opus

📄 Context: 200K tokens 📤 Output: 64K tokens
👁️ Vision

OpenCode Zen (8 models)

OpenCode Zen
✓ FREE

MiniMax M2.5 Free

Family: minimax-free

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenCode Zen
✓ FREE

Trinity Large Preview

Family: trinity

📄 Context: 131K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenCode Zen
✓ FREE

Kimi K2.5 Free

Family: kimi-free

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights👁️ Vision
OpenCode Zen
✓ FREE

MiniMax M2.1 Free

Family: minimax-free

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenCode Zen
✓ FREE

GLM-4.7 Free

Family: glm-free

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights
OpenCode Zen
✓ FREE

Big Pickle

Family: big-pickle

📄 Context: 200K tokens 📤 Output: 128K tokens
OpenCode Zen
✓ FREE

Grok Code Fast 1

Family: grok

📄 Context: 256K tokens 📤 Output: 256K tokens
OpenCode Zen
✓ FREE

GPT-5 Nano

Family: gpt-nano

📄 Context: 400K tokens 📤 Output: 128K tokens
👁️ Vision

ModelScope (7 models)

ModelScope
✓ FREE

GLM-4.6

Family: glm

📄 Context: 203K tokens 📤 Output: 98K tokens
🔓 Open Weights
ModelScope
✓ FREE

Qwen3 Coder 30B A3B Instruct

Family: qwen

📄 Context: 262K tokens 📤 Output: 66K tokens
🔓 Open Weights
ModelScope
✓ FREE

Qwen3 30B A3B Instruct 2507

Family: qwen

📄 Context: 262K tokens 📤 Output: 16K tokens
🔓 Open Weights
ModelScope
✓ FREE

Qwen3 30B A3B Thinking 2507

Family: qwen

📄 Context: 262K tokens 📤 Output: 33K tokens
🔓 Open Weights
ModelScope
✓ FREE

GLM-4.5

Family: glm

📄 Context: 131K tokens 📤 Output: 98K tokens
🔓 Open Weights
ModelScope
✓ FREE

Qwen3-235B-A22B-Thinking-2507

Family: qwen

📄 Context: 262K tokens 📤 Output: 131K tokens
🔓 Open Weights
ModelScope
✓ FREE

Qwen3 235B A22B Instruct 2507

Family: qwen

📄 Context: 262K tokens 📤 Output: 131K tokens
🔓 Open Weights

Llama (7 models)

Llama
✓ FREE

Cerebras-Llama-4-Maverick-17B-128E-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Llama
✓ FREE

Llama-4-Scout-17B-16E-Instruct-FP8

Family: llama

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision
Llama
✓ FREE

Groq-Llama-4-Maverick-17B-128E-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Llama
✓ FREE

Cerebras-Llama-4-Scout-17B-16E-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Llama
✓ FREE

Llama-4-Maverick-17B-128E-Instruct-FP8

Family: llama

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision
Llama
✓ FREE

Llama-3.3-8B-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights
Llama
✓ FREE

Llama-3.3-70B-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights

Cloudflare AI Gateway (6 models)

Cloudflare AI Gateway
✓ FREE

MyShell MeloTTS

Family: melotts

📄 Context: 128K tokens 📤 Output: 16K tokens
Cloudflare AI Gateway
✓ FREE

Pipecat Smart Turn v2

Family: smart-turn

📄 Context: 128K tokens 📤 Output: 16K tokens
Cloudflare AI Gateway
✓ FREE

Deepgram Aura 2 (ES)

Family: aura

📄 Context: 128K tokens 📤 Output: 16K tokens
Cloudflare AI Gateway
✓ FREE

Deepgram Nova 3

Family: nova

📄 Context: 128K tokens 📤 Output: 16K tokens
Cloudflare AI Gateway
✓ FREE

Deepgram Aura 2 (EN)

Family: aura

📄 Context: 128K tokens 📤 Output: 16K tokens
Cloudflare AI Gateway
✓ FREE

BART Large CNN

Family: bart

📄 Context: 128K tokens 📤 Output: 16K tokens

Cloudflare Workers AI (6 models)

Cloudflare Workers AI
✓ FREE

MyShell MeloTTS

Family: melotts

📄 Context: 128K tokens 📤 Output: 16K tokens
Cloudflare Workers AI
✓ FREE

Pipecat Smart Turn v2

Family: smart-turn

📄 Context: 128K tokens 📤 Output: 16K tokens
Cloudflare Workers AI
✓ FREE

Deepgram Aura 2 (ES)

Family: aura

📄 Context: 128K tokens 📤 Output: 16K tokens
Cloudflare Workers AI
✓ FREE

Deepgram Nova 3

Family: nova

📄 Context: 128K tokens 📤 Output: 16K tokens
Cloudflare Workers AI
✓ FREE

Deepgram Aura 2 (EN)

Family: aura

📄 Context: 128K tokens 📤 Output: 16K tokens
Cloudflare Workers AI
✓ FREE

BART Large CNN

Family: bart

📄 Context: 128K tokens 📤 Output: 16K tokens

ZenMux (5 models)

ZenMux
✓ FREE

Step 3.5 Flash (Free)

📄 Context: 256K tokens 📤 Output: 64K tokens
ZenMux
✓ FREE

GLM 4.7 Flash (Free)

📄 Context: 200K tokens 📤 Output: 64K tokens
ZenMux
✓ FREE

MiMo-V2-Flash Free

📄 Context: 262K tokens 📤 Output: 64K tokens
ZenMux
✓ FREE

GLM 4.6V Flash (Free)

📄 Context: 200K tokens 📤 Output: 64K tokens
👁️ Vision
ZenMux
✓ FREE

KAT-Coder-Pro-V1 Free

📄 Context: 256K tokens 📤 Output: 64K tokens

Cortecs (4 models)

Cortecs
✓ FREE

Devstral Small 2 2512

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights👁️ Vision
Cortecs
✓ FREE

Devstral 2 2512

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights
Cortecs
✓ FREE

GPT Oss 120b

Family: gpt-oss

📄 Context: 128K tokens 📤 Output: 128K tokens
🔓 Open Weights
Cortecs
✓ FREE

Llama 3.1 405B Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 128K tokens
🔓 Open Weights

Privatemode AI (4 models)

Privatemode AI
✓ FREE

Qwen3-Embedding 4B

Family: qwen

📄 Context: 32K tokens 📤 Output: 3K tokens
🔓 Open Weights
Privatemode AI
✓ FREE

Qwen3-Coder 30B-A3B

Family: qwen

📄 Context: 128K tokens 📤 Output: 33K tokens
🔓 Open Weights
Privatemode AI
✓ FREE

Gemma 3 27B

Family: gemma

📄 Context: 128K tokens 📤 Output: 8K tokens
🔓 Open Weights👁️ Vision
Privatemode AI
✓ FREE

Whisper large-v3

Family: whisper

📤 Output: 4K tokens
🔓 Open Weights🎵 Audio

MiniMax Coding Plan (minimax.io) (3 models)

MiniMax Coding Plan (minimax.io)
✓ FREE

MiniMax-M2.5

Family: minimax

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights
MiniMax Coding Plan (minimax.io)
✓ FREE

MiniMax-M2.1

Family: minimax

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights
MiniMax Coding Plan (minimax.io)
✓ FREE

MiniMax-M2

Family: minimax

📄 Context: 197K tokens 📤 Output: 128K tokens
🔓 Open Weights

LMStudio (3 models)

LMStudio
✓ FREE

GPT OSS 20B

Family: gpt-oss

📄 Context: 131K tokens 📤 Output: 33K tokens
🔓 Open Weights
LMStudio
✓ FREE

Qwen3 30B A3B 2507

Family: qwen

📄 Context: 262K tokens 📤 Output: 16K tokens
🔓 Open Weights
LMStudio
✓ FREE

Qwen3 Coder 30B

Family: qwen

📄 Context: 262K tokens 📤 Output: 66K tokens
🔓 Open Weights

Vercel AI Gateway (3 models)

Vercel AI Gateway
✓ FREE

Llama-4-Maverick-17B-128E-Instruct-FP8

Family: llama

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision
Vercel AI Gateway
✓ FREE

Llama-4-Scout-17B-16E-Instruct-FP8

Family: llama

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights👁️ Vision
Vercel AI Gateway
✓ FREE

Llama-3.3-70B-Instruct

Family: llama

📄 Context: 128K tokens 📤 Output: 4K tokens
🔓 Open Weights

Nebius Token Factory (2 models)

Nebius Token Factory
✓ FREE

FLUX.1-dev

📄 Context: 77 tokens
🔓 Open Weights
Nebius Token Factory
✓ FREE

FLUX.1-schnell

📄 Context: 77 tokens
🔓 Open Weights

Nova (2 models)

Nova
✓ FREE

Nova 2 Pro

Family: nova-pro

📄 Context: 1.0M tokens 📤 Output: 64K tokens
👁️ Vision
Nova
✓ FREE

Nova 2 Lite

Family: nova-lite

📄 Context: 1.0M tokens 📤 Output: 64K tokens
👁️ Vision

Kimi For Coding (2 models)

Kimi For Coding
✓ FREE

Kimi K2.5

Family: kimi-thinking

📄 Context: 262K tokens 📤 Output: 33K tokens
🔓 Open Weights👁️ Vision
Kimi For Coding
✓ FREE

Kimi K2 Thinking

Family: kimi-thinking

📄 Context: 262K tokens 📤 Output: 33K tokens
🔓 Open Weights

AIHubMix (2 models)

AIHubMix
✓ FREE

Coding MiniMax M2.1 Free

Family: minimax

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights
AIHubMix
✓ FREE

Coding GLM 4.7 Free

Family: glm

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights

Alibaba (China) (2 models)

Alibaba (China)
✓ FREE

DeepSeek R1 Distill Llama 8B

Family: deepseek-thinking

📄 Context: 33K tokens 📤 Output: 16K tokens
Alibaba (China)
✓ FREE

DeepSeek R1 Distill Qwen 1.5B

Family: qwen

📄 Context: 33K tokens 📤 Output: 16K tokens

Cerebras (1 models)

Cerebras
✓ FREE

Z.AI GLM-4.7

📄 Context: 131K tokens 📤 Output: 40K tokens
🔓 Open Weights

Friendli (1 models)

Friendli
✓ FREE

K EXAONE 236B A23B

Family: exaone

📄 Context: 262K tokens 📤 Output: 262K tokens
🔓 Open Weights

Jiekou.AI (1 models)

Jiekou.AI
✓ FREE

XiaomiMiMo/MiMo-V2-Flash

Family: mimo

📄 Context: 262K tokens 📤 Output: 131K tokens
🔓 Open Weights

KUAE Cloud Coding Plan (1 models)

KUAE Cloud Coding Plan
✓ FREE

GLM-4.7

Family: glm

📄 Context: 205K tokens 📤 Output: 131K tokens
🔓 Open Weights

Mistral (1 models)

Mistral
✓ FREE

Devstral Small 2

Family: devstral

📄 Context: 256K tokens 📤 Output: 256K tokens
🔓 Open Weights👁️ Vision

Zhipu AI Coding Plan (1 models)

Zhipu AI Coding Plan
✓ FREE

GLM-4.6V-Flash

Family: glm

📄 Context: 128K tokens 📤 Output: 33K tokens
🔓 Open Weights👁️ Vision

SiliconFlow (China) (1 models)

SiliconFlow (China)
✓ FREE

tencent/Hunyuan-MT-7B

Family: hunyuan

📄 Context: 33K tokens 📤 Output: 33K tokens

NovitaAI (1 models)

NovitaAI
✓ FREE

KAT-Coder-Pro V1(Free)

📄 Context: 256K tokens 📤 Output: 32K tokens
🔓 Open Weights

Hugging Face (1 models)

Hugging Face
✓ FREE

GLM-4.7-Flash

Family: glm

📄 Context: 200K tokens 📤 Output: 128K tokens
🔓 Open Weights