🏷️ Models by Category
Find the best models across all providers for each use case — click a tab to filter
💬 Chat Models
General-purpose conversational AI — all providers offer chat models
| Model | Provider | Speed | Context | Price Tier | Notes |
|---|---|---|---|---|---|
| llama-3.3-70b-versatile | Groq | ⚡ 212 tok/s | 128K | Free | Best free fast chat |
| openai/gpt-oss-120b | Groq | ⚡ 215 tok/s | 128K | Free | GPT-OSS on LPU |
| groq/compound | Groq | ⚡ 289 tok/s | 128K | Free | Agentic compound model |
| llama-3.1-8b-instant | Groq | ⚡ 300+ tok/s | 128K | Free | Ultra-fast small model |
| qwen/qwen3-32b | Groq | ⚡ 295 tok/s | 128K | Free | Qwen3 on LPU |
| deepseek-r1-distill-llama-70b | Groq | ⚡ 180 tok/s | 128K | Free | Reasoning distill |
| mixtral-8x7b-32768 | Groq | ⚡ 190 tok/s | 32K | Free | MoE architecture |
| gemma2-9b-it | Groq | ⚡ 250 tok/s | 8K | Free | Google Gemma2 |
| step-3-chat | StepFun | ⚡ 93 tok/s | — | $9/mo | Strong Chinese/English |
| step-3-mini | StepFun | ⚡ Fast | — | $9/mo | Small/fast variant |
| glm-5 | OpenCode | ⚡ 52 tok/s | — | $10/mo | GLM-5 champion |
| glm-5.1 | OpenCode | ⚡ 52 tok/s | — | $10/mo | Improved GLM |
| deepseek-v4-flash | OpenCode | ⚡ 58 tok/s | — | $10/mo | Fast DeepSeek |
| minimax-m2.5 | OpenCode | — | — | $10/mo | MiniMax model |
| minimax-m2.7 | OpenCode | — | — | $10/mo | MiniMax v2.7 |
| kimi-k2.5 | OpenCode | — | — | $10/mo | Kimi latest |
| qwen3-235b | OpenCode | — | — | $10/mo | Qwen3 reasoning |
| gpt-oss:120b | Ollama | ⚡ 71 tok/s | — | Unlimited | Large open model |
| glm-5.1 | Ollama | ⚡ 63 tok/s | — | Unlimited | GLM-5.1 |
| deepseek-v4-pro | Ollama | ⚡ 50 tok/s | — | Unlimited | DeepSeek reasoner |
| kimi-k2.5 | Ollama | ⚡ 58 tok/s | — | Unlimited | Kimi latest |
| glm-4.7 | Ollama | ⚡ 51 tok/s | — | Unlimited | GLM-4.7 |
| deepseek-v4-flash | Ollama | ⚡ 44 tok/s | — | Unlimited | Flash variant |
| nemotron-3-super | Ollama | ⚡ 102 tok/s | — | Unlimited | 🆕 Exclusive |
| minimax-m2.1 | Ollama | ⚡ 83 tok/s | — | Unlimited | 🆕 Exclusive |
| qwen3-next:80b | Ollama | ⚡ 82 tok/s | — | Unlimited | 🆕 Exclusive |
| qwen3.5:397b | Ollama | ⚡ 72 tok/s | — | Unlimited | 🆕 Exclusive |
| kimi-k2.6 | Ollama | 🐢 18 tok/s | — | Unlimited | Kimi v2.6 |
| claude-opus-4-6 | Venice | — | 200K | Uncensored | Uncensored Claude Opus |
| claude-sonnet-4-5 | Venice | — | 200K | Uncensored | Uncensored Claude Sonnet |
| kimi-k2.5 | Venice | ⚡ 86 tok/s | — | Uncensored | Uncensored Kimi |
| kimi-k2.6 | Venice | ⚡ 93 tok/s | — | Uncensored | Uncensored Kimi v2.6 |
| grok-4 | Venice | ⚡ 102 tok/s | — | Uncensored | 🆕 Exclusive uncensored |
| deepseek-v4-pro | Venice | ⚡ 50 tok/s | — | Uncensored | Uncensored DeepSeek |
| anthropic/claude-3.5-sonnet | OpenRouter | — | 200K | Free (:free) | Free Claude tier |
| meta-llama/llama-3.1-8b | OpenRouter | — | 128K | Free (:free) | Free Llama tier |
| google/gemini-2.5-pro | OpenRouter | ⚡ 67 tok/s | 1M | Paid | Best Gemini model |
| google/gemini-2.5-flash | OpenRouter | ⚡ 74 tok/s | 1M | Free/Paid | Fast Gemini |
| +320 more models | OpenRouter | — | — | Mixed | 356 total models |
| gemini-2.5-pro | ZenMux | ⚡ 41 tok/s | 1M | Free 700/d | Best Gemini coverage |
| gemini-2.5-flash | ZenMux | ⚡ 90 tok/s | 1M | Free 700/d | Fast Gemini |
| Qwen/Qwen3-32B-TEE | Chutes | ⚡ 192 tok/s | — | $20/mo | 🔒 TEE privacy |
| zai-org/GLM-5.1-TEE | Chutes | — | — | $20/mo | 🔒 TEE privacy |
| moonshotai/Kimi-K2.5-TEE | Chutes | — | — | $20/mo | 🔒 TEE privacy |
| MiniMaxAI/MiniMax-M2.5-TEE | Chutes | — | — | $20/mo | 🔒 TEE privacy |
| zai-org/GLM-5-TEE | Chutes | — | — | $20/mo | 🔒 TEE privacy |
| unsloth/Mistral-Nemo-2407-TEE | Chutes | — | — | $20/mo | 🔒 TEE privacy |
| zai-org/GLM-5-Turbo | Chutes | — | — | $20/mo | Fast GLM variant |
| claude-opus-4-6 | ORBIT | ⚡ 29 tok/s | 200K | Free (2B/mo) | Claude-only, free |
| claude-sonnet-4-5 | ORBIT | ⚡ 25 tok/s | 200K | Free (2B/mo) | Latest Sonnet |
| claude-3.5-sonnet | ORBIT | ⚡ 28 tok/s | 200K | Free (2B/mo) | Stable Claude |
| claude-3-opus | ORBIT | 🐢 22 tok/s | 200K | Free (2B/mo) | Legacy Opus |
| glm-4.7 | BytePlus | ⚡ 71 tok/s | — | $9/mo Pro | ✅ Verified & Working |
| glm-5.1 | BytePlus | ⚡ 30 tok/s | — | $9/mo Pro | ✅ Verified & Working |
| kimi-k2.5 | BytePlus | ⚡ 26 tok/s | — | $9/mo Pro | ✅ Verified & Working |
| gpt-oss-120b | BytePlus | 🐢 15 tok/s | — | $9/mo Pro | Large open model |
| ark-code-latest | BytePlus | 🐢 15 tok/s | — | $9/mo Pro | Auto-code agent |
| Doubao-Pro-32K | BytePlus | — | 32K | $9/mo Pro | General API |
| Doubao-Pro-128K | BytePlus | — | 128K | $9/mo Pro | General API |
| Doubao-Lite-32K | BytePlus | — | 32K | $9/mo Pro | General API |
| Doubao-Lite-128K | BytePlus | — | 128K | $9/mo Pro | General API |
| DeepSeek-V3.2 | BytePlus | — | — | $9/mo Pro | General API |
💻 Coding Models
Models optimized for code generation, completion, and debugging
| Model | Provider | Speed | Context | Price Tier | Notes |
|---|---|---|---|---|---|
| dola-seed-2.0-code | BytePlus | ⚡ 80 tok/s | — | $9/mo Pro | 🥇 Best coding model ✅ |
| dola-seed-2.0-lite | BytePlus | ⚡ 84 tok/s | — | $9/mo Pro | Fastest coder ✅ |
| bytedance-seed-code | BytePlus | ⚡ 63 tok/s | — | $9/mo Pro | Strong code completion ✅ |
| ark-code-latest | BytePlus | 🐢 15 tok/s | — | $9/mo Pro | Auto-code agent |
| qwen2.5-coder-32b | Groq | ⚡ 212 tok/s | 128K | Free | 🥇 Best free coding |
| Qwen/Qwen2.5-Coder-32B-TEE | Chutes | — | — | $20/mo | 🔒 TEE privacy |
| qwen3-coder-next | Ollama | ⚡ 52 tok/s | — | Unlimited | 🆕 Exclusive |
| devstral-2:123b | Ollama | 🐢 36 tok/s | — | Unlimited | 🆕 Exclusive code model |
| deepseek-v4-pro | OpenCode | ⚡ 52 tok/s | — | $10/mo | Strong at code tasks |
| codestral-latest | OpenRouter | — | — | Paid | Mistral code model |
🧠 Reasoning Models
Thinking/reasoning models that show chain-of-thought
| Model | Provider | Speed | Context | Price Tier | Notes |
|---|---|---|---|---|---|
| dola-seed-2.0-pro | BytePlus | ⚡ 50 tok/s | — | $9/mo Pro | 🥇 Best reasoning ✅ |
| deepseek-v4-pro | OpenCode | ⚡ 52 tok/s | — | $10/mo | DeepSeek reasoning |
| deepseek-r1-distill-llama-70b | Groq | ⚡ 180 tok/s | 128K | Free | Fast free reasoning |
| step-3-reasoning | StepFun | ⚡ 93 tok/s | — | $9/mo | StepFun reasoning |
| Qwen/Qwen3-235B-Thinking | Chutes | ⚡ 40 tok/s | — | $20/mo | TEE thinking mode |
| deepseek-ai/DeepSeek-V3.2-TEE | Chutes | — | — | $20/mo | 🔒 TEE DeepSeek reason |
| Qwen/Qwen3-32B-TEE | Chutes | ⚡ 192 tok/s | — | $20/mo | 🔒 TEE privacy |
| deepseek-v3.2 | Ollama | 🐢 23 tok/s | — | Unlimited | DeepSeek V3.2 reasoning |
| claude-opus-4-6 | ORBIT | ⚡ 29 tok/s | 200K | Free (2B/mo) | Claude reasoning |
| qwen3-235b | OpenCode | — | — | $10/mo | Qwen3 reasoning |
| DeepSeek-V3.2 | BytePlus | — | — | $9/mo Pro | DeepSeek reasoning |
| o3 | Venice | — | — | Uncensored | Uncensored reasoning |
👁️ Vision / OCR Models
Multimodal models that can process images and text
| Model | Provider | Speed | Context | Price Tier | Notes |
|---|---|---|---|---|---|
| step-3-vl | StepFun | ⚡ 93 tok/s | — | $9/mo | Chinese/English OCR |
| glm-5-vision | OpenCode | ⚡ 52 tok/s | — | $10/mo | GLM vision |
| minimax-vl-01 | OpenCode | — | — | $10/mo | MiniMax vision |
| gemini-3-flash-preview | Ollama | ⚡ 47 tok/s | — | Unlimited | 🆕 Exclusive |
| llama-3.2-90b-vision | Groq | ⚡ Fast | — | Free | Llama vision at speed |
| gemini-2.5-pro | ZenMux | ⚡ 41 tok/s | 1M | Free 700/d | Best Gemini for vision |
| gemini-2.5-flash | ZenMux | ⚡ 90 tok/s | 1M | Free 700/d | Fast Gemini vision |
| google/gemini-2.5-pro | OpenRouter | ⚡ 67 tok/s | 1M | Paid | Gemini Pro vision |
| google/gemini-2.5-flash | OpenRouter | ⚡ 74 tok/s | 1M | Free/Paid | Gemini Flash vision |
| moonshotai/Kimi-K2.5-TEE | Chutes | — | — | $20/mo | 🔒 TEE, Vision+Chat |
| Qwen/Qwen3.5-397B-TEE | Chutes | — | — | $20/mo | 🔒 TEE, Vision+Chat |
| Qwen/Qwen3.6-27B-TEE | Chutes | — | — | $20/mo | 🔒 TEE, Vision |
| moonshotai/Kimi-K2.6-TEE | Chutes | — | — | $20/mo | 🔒 TEE, Vision+Video |
| google/gemma-4-31B-turbo-TEE | Chutes | — | — | $20/mo | 🔒 TEE, Gemma vision |
🎤 Speech-to-Text (STT) Models
Transcribe audio to text
| Model | Provider | Speed | Context | Price Tier | Notes |
|---|---|---|---|---|---|
| whisper-large-v3 | Groq | ⚡ Ultra-fast | — | Free | 🥇 Best free STT, on LPU |
| whisper-large-v3-turbo | Groq | ⚡ Ultra-fast | — | Free | Faster Whisper variant |
| step-asr | StepFun | — | — | $9/mo | StepFun ASR engine |
| step-asr | Infermatic | — | — | $20/mo | Via Infermatic API |
🔊 Text-to-Speech (TTS) Models
Generate speech from text
| Model | Provider | Speed | Context | Price Tier | Notes |
|---|---|---|---|---|---|
| step-tts | StepFun | — | — | $9/mo | StepFun TTS engine |
| kokoro-82m | Infermatic | — | — | $20/mo | Kokoro TTS engine |
| Kokoro-82M | Chutes | — | — | $20/mo | Kokoro TTS on Chutes |
| Seed Speech | BytePlus | — | — | $9/mo Pro | BytePlus TTS ✅ |
🖼️ Image Generation Models
Diffusion and generative image models
| Model | Provider | Type | Context | Price Tier | Notes |
|---|---|---|---|---|---|
| FLUX.1-schnell | Chutes | Diffusion | — | $20/mo | Fast FLUX generation |
| JuggernautXL-Ragnarok | Chutes | Diffusion | — | $20/mo | Cinematic style |
| DreamShaper-XL | Chutes | Diffusion | — | $20/mo | Artistic style |
| hunyuan-image-3 | Chutes | Diffusion | — | $20/mo | Photorealistic |
| flux-1 | Venice | Diffusion | — | Uncensored | Uncensored image gen |
| Various image models | ArliAI | Diffusion | — | From $10/mo | Image gen API |
| SDXL / Stable models | Featherless | Diffusion | — | Scale ×3 | Massive catalog, slow |
| Seedream-5.0-lite | BytePlus | Diffusion | 4K | $9/mo Pro | 4K image gen ✅ |
🎬 Video Generation
Models capable of generating or understanding video content
| Model | Provider | Speed | Context | Price Tier | Notes |
|---|---|---|---|---|---|
| Seedance-2.0 | BytePlus | — | — | $9/mo Pro | Video generation ✅ |
| Seedance-2.0-fast | BytePlus | — | — | $9/mo Pro | Fast video gen variant ✅ |
| OmniHuman | BytePlus | — | — | $9/mo Pro | Digital human ✅ |
| Video gen models | OpenRouter | — | — | Paid | Various video models |
| Gemini video understanding | ZenMux | — | — | Free/Paid | Gemini video capability |
📐 Embedding Models
Text embedding models for semantic search and similarity
| Model | Provider | Dimensions | Context | Price Tier | Notes |
|---|---|---|---|---|---|
| Qwen3-Embedding-8B-TEE | Chutes | — | — | $20/mo | 🔒 TEE embeddings |
| multilingual-e5-base | Infermatic | 768 | — | $20/mo | Multilingual embeddings |