Every model. Every agent.
One call away.
The open index of everything you can invoke programmatically — canonical IDs, live provider availability and pricing, and working request code for each one.
357
models
19
agents
18
providers
1164
code snippets
| Name | Type | Canonical ID | Released | Context | In $/M | Out $/M | Available via | |
|---|---|---|---|---|---|---|---|---|
| GLM-5.3Zhipu AI | model | glm-5-3 | 2026-08 | 1M | — | — | weights only | open → |
| Qwen3.8 27BAlibaba Qwen | model | qwen3-8-27b | 2026-08 | 262K | — | — | weights only | open → |
| Gemini 3.7 FlashGoogle | model | gemini-3.7-flash | 2026-08 | 1M | — | — | 1 provider | open → |
| DeepSeek V4 Pro 0813DeepSeek | model | deepseek-v4-pro-0813 | 2026-08 | 1M | — | — | 1 provider | open → |
| Grok 4.6xAI | model | grok-4.6 | 2026-08 | 500K | — | — | 1 provider | open → |
| Qwen3.8 2.4T A95BAlibaba Qwen | model | qwen3-8-2-4t-a95b | 2026-08 | 262K | — | — | weights only | open → |
| MAI-Code-1.1-FlashMicrosoft | model | mai-code-1-1-flash | 2026-08 | 256K | — | — | weights only | open → |
| Nemotron 3.5 Lightning 30B A3BNVIDIA | model | nemotron-3-5-lightning | 2026-08 | 262K | — | — | weights only | open → |
| Muse Glimmer 30BMeta | model | muse-glimmer-30b | 2026-08 | 131K | — | — | weights only | open → |
| LFM2.5 2.6BLiquid AI | model | lfm2.5-2.6b | 2026-08 | 131K | — | — | weights only | open → |
| Solar Pro 4Upstage | model | solar-pro4 | 2026-08 | 524K | — | — | weights only | open → |
| Muse Spark 1.2Meta | model | muse-spark-1-2 | 2026-08 | 1M | — | — | weights only | open → |
| Sakana NamazuSakana AI | model | sakana-namazu | 2026-08 | 262K | — | — | weights only | open → |
| DeepSeek V4 Flash 0731DeepSeek | model | deepseek-v4-flash-0731 | 2026-07 | 1M | — | — | 1 provider | open → |
| Inkling SmallThinking Machines | model | inkling-small | 2026-07 | 1M | — | — | weights only | open → |
| Claude Opus 5Anthropic | model | claude-opus-5 | 2026-07 | 1M | — | — | 1 provider | open → |
| Gemini 3.5 Flash LiteGoogle | model | gemini-3.5-flash-lite | 2026-07 | 1M | — | — | 1 provider | open → |
| Gemini 3.6 FlashGoogle | model | gemini-3.6-flash | 2026-07 | 1M | — | — | 1 provider | open → |
| Laguna S 2.1Poolside | model | laguna-s-2-1 | 2026-07 | 1M | — | — | weights only | open → |
| Qwen3.8 Max PreviewAlibaba Qwen | model | qwen3-8-max | 2026-07 | 1M | — | — | weights only | open → |
| Kimi K3Moonshot AI | model | kimi-k3 | 2026-07 | 1M | — | — | 1 provider | open → |
| InklingThinking Machines | model | inkling | 2026-07 | 1M | — | — | weights only | open → |
| Qwen3.7 FlashAlibaba Qwen | model | qwen3-7-flash | 2026-07 | 1M | — | — | weights only | open → |
| GPT-5.6 LunaOpenAI | model | gpt-5.6-luna | 2026-07 | 1.1M | — | — | 1 provider | open → |
| GPT-5.6 SolOpenAI | model | gpt-5.6-sol | 2026-07 | 1.1M | — | — | 1 provider | open → |
| GPT-5.6 TerraOpenAI | model | gpt-5.6-terra | 2026-07 | 1.1M | — | — | 1 provider | open → |
| Grok 4.5xAI | model | grok-4.5 | 2026-07 | 500K | — | — | 1 provider | open → |
| GPT-Realtime-2.1OpenAI | model | gpt-realtime-2.1 | 2026-07 | 128K | — | — | 1 provider | open → |
| Laguna XS 2.1Poolside | model | laguna-xs-2-1 | 2026-07 | 262K | — | — | weights only | open → |
| Claude Sonnet 5Anthropic | model | claude-sonnet-5 | 2026-06 | 1M | — | — | 1 provider | open → |
| LongCat-2.0Meituan | model | longcat-2-0 | 2026-06 | 1M | — | — | weights only | open → |
| Nano Banana 2 LiteGoogle | model | gemini-3.1-flash-lite-image | 2026-06 | 66K | — | — | 1 provider | open → |
| Ornith 1.0 31BDeepReinforce | model | ornith-1-0-31b | 2026-06 | 262K | — | — | weights only | open → |
| Ornith 1.0 35BDeepReinforce | model | ornith-1-0-35b | 2026-06 | 262K | — | — | weights only | open → |
| Ornith 1.0 397BDeepReinforce | model | ornith-1-0-397b | 2026-06 | 262K | — | — | weights only | open → |
| Ornith 1.0 9BDeepReinforce | model | ornith-1-0-9b | 2026-06 | 262K | — | — | weights only | open → |
| Seed 2.1 ProByteDance Seed | model | seed-2-1-pro | 2026-06 | 256K | — | — | weights only | open → |
| Seed 2.1 TurboByteDance Seed | model | seed-2-1-turbo | 2026-06 | 256K | — | — | weights only | open → |
| Seed CharacterByteDance Seed | model | seed-character | 2026-06 | 256K | — | — | weights only | open → |
| Seed EvolvingByteDance Seed | model | seed-evolving | 2026-06 | 256K | — | — | weights only | open → |
| FuguSakana AI | model | fugu | 2026-06 | 1M | — | — | weights only | open → |
| Fugu UltraSakana AI | model | fugu-ultra | 2026-06 | 1M | — | — | weights only | open → |
| GLM-5.2Zhipu AI | model | glm-5-2 | 2026-06 | 1M | — | — | weights only | open → |
| Kimi K2.7 CodeMoonshot AI | model | kimi-k2.7-code | 2026-06 | 262K | — | — | 1 provider | open → |
| Kimi K2.7 Code HighspeedMoonshot AI | model | kimi-k2.7-code-highspeed | 2026-06 | 262K | — | — | 1 provider | open → |
| Claude Fable 5Anthropic | model | claude-fable-5 | 2026-06 | 1M | — | — | 1 provider | open → |
| Claude Mythos 5Anthropic | model | claude-mythos-5 | 2026-06 | 1M | — | — | 1 provider | open → |
| Gemini 3.5 Live Translate PreviewGoogle | model | gemini-3.5-live-translate-preview | 2026-06 | 131K | — | — | 1 provider | open → |
| North Mini CodeCohere | model | north-mini-code-1-0 | 2026-06 | 256K | — | — | weights only | open → |
| MiMo-V2.5-Pro-UltraSpeedXiaomi | model | mimo-v2-5-pro-ultraspeed | 2026-06 | 1M | — | — | weights only | open → |
| Nemotron 3 Ultra 550B A55BNVIDIA | model | nemotron-3-ultra-550b-a55b | 2026-06 | 1M | — | — | weights only | open → |
| Nemotron 3.5 Content SafetyNVIDIA | model | nemotron-3-5-content-safety | 2026-06 | 128K | — | — | weights only | open → |
| MAI-Code-1-FlashMicrosoft | model | mai-code-1-flash | 2026-06 | 256K | — | — | weights only | open → |
| Qwen3.7 PlusAlibaba Qwen | model | qwen3-7-plus | 2026-06 | 1M | — | — | weights only | open → |
| MiniMax-M3MiniMax | model | minimax-m3 | 2026-06 | 512K | — | — | weights only | open → |
| Step 3.7 FlashStepfun | model | step-3-7-flash | 2026-05 | 256K | — | — | weights only | open → |
| Claude Opus 4.8Anthropic | model | claude-opus-4-8 | 2026-05 | 1M | — | — | 1 provider | open → |
| Qwen3.7 MaxAlibaba Qwen | model | qwen3-7-max | 2026-05 | 1M | — | — | weights only | open → |
| Command A PlusCohere | model | command-a-plus-05-2026 | 2026-05 | 128K | — | — | weights only | open → |
| Gemini 3.5 FlashGoogle | model | gemini-3.5-flash | 2026-05 | 1M | — | — | 1 provider | open → |
| Gemini Flash LatestGoogle | model | gemini-flash-latest | 2026-05 | 1M | 0.50 | 3.00 | 2 providers | open → |
| Gemini Flash-Lite LatestGoogle | model | gemini-flash-lite-latest | 2026-05 | 1M | — | — | 1 provider | open → |
| GPT Realtime WhisperOpenAI | model | gpt-realtime-whisper | 2026-05 | — | — | — | 1 provider | open → |
| GPT-5.5 InstantOpenAI | model | gpt-5.5-instant | 2026-05 | 400K | — | — | 1 provider | open → |
| Mistral Medium (latest)Mistral AI | model | mistral-medium-latest | 2026-04 | 262K | — | — | 1 provider | open → |
| Mistral Medium 3.5Mistral AI | model | mistral-medium-2604 | 2026-04 | 262K | — | — | 1 provider | open → |
| Laguna M.1Poolside | model | laguna-m-1 | 2026-04 | 262K | — | — | weights only | open → |
| Laguna XS.2Poolside | model | laguna-xs-2 | 2026-04 | 262K | — | — | weights only | open → |
| Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA | model | nemotron-3-nano-omni-30b-a3b-reasoning | 2026-04 | 256K | — | — | weights only | open → |
| Qwen3.6 FlashAlibaba Qwen | model | qwen3.6-flash | 2026-04 | 1M | 0.19 | 1.13 | 1 provider | open → |
| DeepSeek V4 FlashDeepSeek | model | deepseek-v4-flash | 2026-04 | 1M | 0.13 | 0.25 | 2 providers | open → |
| DeepSeek V4 ProDeepSeek | model | deepseek-v4-pro | 2026-04 | 1M | 0.43 | 0.87 | 2 providers | open → |
| GPT-5.5OpenAI | model | gpt-5.5 | 2026-04 | 1.1M | 5.00 | 30.00 | 2 providers | open → |
| GPT-5.5 ProOpenAI | model | gpt-5.5-pro | 2026-04 | 1.1M | 30.00 | 180.00 | 2 providers | open → |
| Gemini Embedding 2Google | model | gemini-embedding-2 | 2026-04 | 8K | — | — | 1 provider | open → |
| MiMo-V2.5Xiaomi | model | mimo-v2.5 | 2026-04 | 1M | 0.40 | 2.00 | 1 provider | open → |
| MiMo-V2.5-ProXiaomi | model | mimo-v2.5-pro | 2026-04 | 1M | 1.00 | 3.00 | 1 provider | open → |
| Qwen3.6 27BAlibaba Qwen | model | qwen3.6-27b | 2026-04 | 262K | 0.32 | 3.20 | 1 provider | open → |
| Deep Research Max PreviewGoogle | model | deep-research-max-preview-04-2026 | 2026-04 | 1M | — | — | 1 provider | open → |
| Gemini Deep Research PreviewGoogle | model | deep-research-preview-04-2026 | 2026-04 | 1M | — | — | 1 provider | open → |
| Kimi K2.6Moonshot AI | model | kimi-k2.6 | 2026-04 | 262K | 0.73 | 3.49 | 2 providers | open → |
| Hunyuan Hy3Tencent | model | hy3 | 2026-04 | 262K | 0.07 | 0.26 | 1 provider | open → |
| Qwen3.6 Max PreviewAlibaba Qwen | model | qwen3.6-max-preview | 2026-04 | 262K | 1.04 | 6.24 | 1 provider | open → |
| Grok 4.3xAI | model | grok-4.3 | 2026-04 | 1M | 1.25 | 2.50 | 2 providers | open → |
| Qwen3.6 35B-A3BAlibaba Qwen | model | qwen3.6-35b-a3b | 2026-04 | 262K | 0.15 | 1.00 | 1 provider | open → |
| Claude Opus 4.7Anthropic | model | claude-opus-4-7 | 2026-04 | 1M | 5.00 | 25.00 | 2 providers | open → |
| Grok Build 0.1xAI | model | grok-build-0.1 | 2026-04 | 256K | — | — | 1 provider | open → |
| Nemotron 3 Content SafetyNVIDIA | model | nemotron-3-content-safety | 2026-04 | 128K | — | — | weights only | open → |
| Gemini Robotics-ER 1.6 PreviewGoogle | model | gemini-robotics-er-1.6-preview | 2026-04 | 131K | — | — | 1 provider | open → |
| Muse Spark 1.1Meta | model | muse-spark-1-1 | 2026-04 | 1M | — | — | weights only | open → |
| GLM-5.1Zhipu AI | model | glm-5.1 | 2026-04 | 200K | 0.98 | 3.08 | 1 provider | open → |
| Gemma 4 26B A4B ITGoogle | model | gemma-4-26b-a4b-it | 2026-04 | 262K | 0.06 | 0.33 | 2 providers | open → |
| Gemma 4 31B ITGoogle | model | gemma-4-31b-it | 2026-04 | 262K | 0.12 | 0.37 | 2 providers | open → |
| Gemma 4 E2B ITGoogle | model | gemma-4-E2B-it | 2026-04 | 131K | — | — | 1 provider | open → |
| Gemma 4 E4B ITGoogle | model | gemma-4-E4B-it | 2026-04 | 131K | — | — | 1 provider | open → |
| Qwen3.6 PlusAlibaba Qwen | model | qwen3.6-plus | 2026-04 | 1M | 0.33 | 1.95 | 1 provider | open → |
| Step 3.5 Flash 2603Stepfun | model | step-3-5-flash-2603 | 2026-04 | 256K | — | — | weights only | open → |
| GLM-5V-TurboZhipu AI | model | glm-5v-turbo | 2026-04 | 200K | 1.20 | 4.00 | 1 provider | open → |
| Trinity Large ThinkingArcee Ai | model | trinity-large-thinking | 2026-04 | 524K | — | — | 1 provider | open → |
| Gemini 3.1 Flash Live PreviewGoogle | model | gemini-3.1-flash-live-preview | 2026-03 | 131K | — | — | 1 provider | open → |
| Lyria 3 Clip PreviewGoogle | model | lyria-3-clip-preview | 2026-03 | 131K | — | — | 2 providers | open → |
| Lyria 3 Pro PreviewGoogle | model | lyria-3-pro-preview | 2026-03 | 131K | — | — | 2 providers | open → |
| Nemotron Cascade 2 30B A3BNVIDIA | model | nemotron-cascade-2-30b-a3b | 2026-03 | 256K | — | — | weights only | open → |
| MiMo-V2-OmniXiaomi | model | mimo-v2-omni | 2026-03 | 262K | 0.40 | 2.00 | 1 provider | open → |
| MiMo-V2-ProXiaomi | model | mimo-v2-pro | 2026-03 | 1M | 1.00 | 3.00 | 1 provider | open → |
| MiniMax-M2.7MiniMax | model | MiniMax-M2.7 | 2026-03 | 205K | 0.28 | 1.20 | 1 provider | open → |
| MiniMax-M2.7-highspeedMiniMax | model | minimax-m2-7-highspeed | 2026-03 | 205K | — | — | weights only | open → |
| GPT-5.4 miniOpenAI | model | gpt-5.4-mini | 2026-03 | 400K | 0.75 | 4.50 | 2 providers | open → |
| GPT-5.4 nanoOpenAI | model | gpt-5.4-nano | 2026-03 | 400K | 0.20 | 1.25 | 2 providers | open → |
| GLM-5-TurboZhipu AI | model | glm-5-turbo | 2026-03 | 200K | 1.20 | 4.00 | 1 provider | open → |
| Mistral Small (latest)Mistral AI | model | mistral-small-latest | 2026-03 | 256K | — | — | 1 provider | open → |
| Mistral Small 4Mistral AI | model | mistral-small-2603 | 2026-03 | 256K | 0.15 | 0.60 | 2 providers | open → |
| Nemotron VoiceChatNVIDIA | model | nemotron-voicechat | 2026-03 | 128K | — | — | weights only | open → |
| Nemotron 3 Super 120B A12BNVIDIA | model | nemotron-3-super-120b-a12b | 2026-03 | 262K | 0.09 | 0.45 | 1 provider | open → |
| Grok 4.20 (Non-Reasoning)xAI | model | grok-4.20-0309-non-reasoning | 2026-03 | 1M | — | — | 1 provider | open → |
| Grok 4.20 (Reasoning)xAI | model | grok-4.20-0309-reasoning | 2026-03 | 1M | — | — | 1 provider | open → |
| GPT-5.4OpenAI | model | gpt-5.4 | 2026-03 | 1.1M | 2.50 | 15.00 | 2 providers | open → |
| GPT-5.4 ProOpenAI | model | gpt-5.4-pro | 2026-03 | 1.1M | 30.00 | 180.00 | 2 providers | open → |
| Mercury 2Inception | model | mercury-2 | 2026-03 | 128K | 0.25 | 0.75 | 2 providers | open → |
| Gemini 3.1 Flash LiteGoogle | model | gemini-3.1-flash-lite | 2026-03 | 1M | 0.25 | 1.50 | 2 providers | open → |
| GPT-5.3 Chat (latest)OpenAI | model | gpt-5.3-chat-latest | 2026-03 | 128K | — | — | 1 provider | open → |
| Nano Banana 2Google | model | gemini-3.1-flash-image | 2026-02 | 131K | 0.50 | 3.00 | 2 providers | open → |
| Qwen3.5 122B-A10BAlibaba Qwen | model | qwen3.5-122b-a10b | 2026-02 | 262K | 0.26 | 2.08 | 1 provider | open → |
| Qwen3.5 27BAlibaba Qwen | model | qwen3.5-27b | 2026-02 | 262K | 0.20 | 1.56 | 1 provider | open → |
| Qwen3.5 35B-A3BAlibaba Qwen | model | qwen3.5-35b-a3b | 2026-02 | 262K | 0.14 | 1.00 | 1 provider | open → |
| Qwen3.5 9BAlibaba Qwen | model | qwen3.5-9b | 2026-02 | 262K | 0.04 | 0.15 | 1 provider | open → |
| Qwen3.5 FlashAlibaba Qwen | model | qwen3-5-flash | 2026-02 | 1M | — | — | weights only | open → |
| Gemini 3.1 Pro PreviewGoogle | model | gemini-3.1-pro-preview | 2026-02 | 1M | 2.00 | 12.00 | 2 providers | open → |
| Gemini 3.1 Pro Preview Custom ToolsGoogle | model | gemini-3.1-pro-preview-customtools | 2026-02 | 1M | 2.00 | 12.00 | 2 providers | open → |
| Trendyol Asure 12BTrendyol | model | asure-12b | 2026-02 | 131K | — | — | weights only | open → |
| Sarvam 30BSarvam AI | model | sarvam-30b | 2026-02 | 128K | — | — | weights only | open → |
| Claude Sonnet 4.6Anthropic | model | claude-sonnet-4-6 | 2026-02 | 1M | 3.00 | 15.00 | 2 providers | open → |
| Qwen3.5 PlusAlibaba Qwen | model | qwen3-5-plus | 2026-02 | 1M | — | — | weights only | open → |
| Qwen3.5 397B-A17BAlibaba Qwen | model | qwen3.5-397b-a17b | 2026-02 | 262K | 0.39 | 2.34 | 1 provider | open → |
| Seed 2.0 CodeByteDance Seed | model | seed-2-0-code | 2026-02 | 262K | — | — | weights only | open → |
| Seed 2.0 LiteByteDance Seed | model | seed-2.0-lite | 2026-02 | 256K | 0.25 | 2.00 | 1 provider | open → |
| Seed 2.0 MiniByteDance Seed | model | seed-2.0-mini | 2026-02 | 256K | 0.10 | 0.40 | 1 provider | open → |
| Seed 2.0 ProByteDance Seed | model | seed-2-0-pro | 2026-02 | 256K | — | — | weights only | open → |
| MiniMax-M2.5-highspeedMiniMax | model | minimax-m2-5-highspeed | 2026-02 | 205K | — | — | weights only | open → |
| GLM-5Zhipu AI | model | glm-5 | 2026-02 | 205K | 0.60 | 1.92 | 1 provider | open → |
| MiniMax-M2.5MiniMax | model | MiniMax-M2.5 | 2026-02 | 205K | 0.15 | 1.15 | 1 provider | open → |
| Claude Opus 4.6Anthropic | model | claude-opus-4-6 | 2026-02 | 1M | 5.00 | 25.00 | 2 providers | open → |
| GPT-5.3 CodexOpenAI | model | gpt-5.3-codex | 2026-02 | 400K | 1.75 | 14.00 | 2 providers | open → |
| GPT-5.3 Codex SparkOpenAI | model | gpt-5.3-codex-spark | 2026-02 | 128K | — | — | 1 provider | open → |
| Qwen3 Coder NextAlibaba Qwen | model | qwen3-coder-next | 2026-02 | 262K | 0.11 | 0.80 | 1 provider | open → |
| Step 3.5 FlashStepfun | model | step-3.5-flash | 2026-01 | 256K | 0.10 | 0.30 | 1 provider | open → |
| DeepSeek OCR 2DeepSeek | model | deepseek-ocr-2 | 2026-01 | 8K | — | — | 1 provider | open → |
| Trinity Large PreviewArcee Ai | model | trinity-large-preview | 2026-01 | 524K | 0.15 | 0.45 | 1 provider | open → |
| MiniMax-M2 HerMiniMax | model | MiniMax-M2-Her | 2026-01 | 200K | 0.30 | 1.20 | 1 provider | open → |
| Nemotron Content Safety Reasoning 4BNVIDIA | model | nemotron-content-safety-reasoning-4b | 2026-01 | 128K | — | — | weights only | open → |
| GLM-4.7-FlashZhipu AI | model | glm-4.7-flash | 2026-01 | 200K | 0.06 | 0.40 | 1 provider | open → |
| GLM-4.7-FlashXZhipu AI | model | glm-4-7-flashx | 2026-01 | 200K | — | — | weights only | open → |
| Falcon-H1R 7BTII | model | falcon-h1r-7b | 2026-01 | — | — | — | weights only | open → |
| Kimi K2.5Moonshot AI | model | kimi-k2.5 | 2026-01 | 262K | 0.40 | 1.90 | 2 providers | open → |
| Solar Pro 3Upstage | model | solar-pro3 | 2026-01 | 131K | — | — | weights only | open → |
| Seed 1.8ByteDance Seed | model | seed-1-8 | 2025-12 | 256K | — | — | weights only | open → |
| MiniMax-M2.1MiniMax | model | MiniMax-M2.1 | 2025-12 | 205K | 0.29 | 0.95 | 1 provider | open → |
| GLM-4.7Zhipu AI | model | glm-4.7 | 2025-12 | 205K | 0.40 | 1.75 | 1 provider | open → |
| Gemini 3 Flash PreviewGoogle | model | gemini-3-flash-preview | 2025-12 | 1M | 0.50 | 3.00 | 2 providers | open → |
| MiMo-V2-FlashXiaomi | model | mimo-v2-flash | 2025-12 | 262K | 0.10 | 0.30 | 1 provider | open → |
| OLMo 3.1 32B InstructAllen AI | model | olmo-3.1-32b-instruct | 2025-12 | — | — | — | 1 provider | open → |
| OLMo 3.1 32B ThinkAllen AI | model | olmo-3.1-32b-think | 2025-12 | — | — | — | 1 provider | open → |
| Nemotron 3 Nano 30B A3BNVIDIA | model | nemotron-3-nano-30b-a3b | 2025-12 | 262K | — | — | 1 provider | open → |
| GPT-5.2OpenAI | model | gpt-5.2 | 2025-12 | 400K | 1.75 | 14.00 | 2 providers | open → |
| GPT-5.2 ChatOpenAI | model | gpt-5.2-chat-latest | 2025-12 | 128K | — | — | 1 provider | open → |
| GPT-5.2 CodexOpenAI | model | gpt-5.2-codex | 2025-12 | 400K | 1.75 | 14.00 | 2 providers | open → |
| GPT-5.2 ProOpenAI | model | gpt-5.2-pro | 2025-12 | 400K | 21.00 | 168.00 | 2 providers | open → |
| Devstral 2Mistral AI | model | devstral-2512 | 2025-12 | 262K | 0.40 | 2.00 | 2 providers | open → |
| GLM-4.6VZhipu AI | model | glm-4.6v | 2025-12 | 128K | 0.30 | 0.90 | 1 provider | open → |
| GLM-4.6V-FlashZhipu AI | model | glm-4-6v-flash | 2025-12 | 128K | — | — | weights only | open → |
| Devstral 2 (latest)Mistral AI | model | devstral-medium-latest | 2025-12 | 262K | — | — | 1 provider | open → |
| DeepSeek ChatDeepSeek | model | deepseek-chat | 2025-12 | 1M | 0.32 | 0.89 | 2 providers | open → |
| DeepSeek ReasonerDeepSeek | model | deepseek-reasoner | 2025-12 | 1M | — | — | 1 provider | open → |
| Trinity MiniArcee Ai | model | trinity-mini | 2025-12 | 131K | 0.04 | 0.15 | 1 provider | open → |
| Trinity Nano PreviewArcee Ai | model | trinity-nano | 2025-12 | 131K | — | — | weights only | open → |
| GPT-Image-1.5OpenAI | model | gpt-image-1.5 | 2025-11 | — | — | — | 1 provider | open → |
| Claude Opus 4.5Anthropic | model | claude-opus-4-5 | 2025-11 | 200K | 5.00 | 25.00 | 4 providers | open → |
| Nano Banana ProGoogle | model | gemini-3-pro-image | 2025-11 | 66K | 2.00 | 12.00 | 2 providers | open → |
| Grok 4.1 FastxAI | model | grok-4.1-fast | 2025-11 | 2M | 0.20 | 0.50 | 2 providers | open → |
| Gemini 3 ProGoogle | model | gemini-3-pro | 2025-11 | 1M | 2.00 | 12.00 | 3 providers | open → |
| GPT-5.1OpenAI | model | gpt-5.1 | 2025-11 | 400K | 1.25 | 10.00 | 2 providers | open → |
| GPT-5.1 ChatOpenAI | model | gpt-5.1-chat-latest | 2025-11 | 128K | — | — | 1 provider | open → |
| GPT-5.1 CodexOpenAI | model | gpt-5.1-codex | 2025-11 | 400K | 1.25 | 10.00 | 2 providers | open → |
| GPT-5.1 Codex MaxOpenAI | model | gpt-5.1-codex-max | 2025-11 | 400K | 1.25 | 10.00 | 2 providers | open → |
| GPT-5.1 Codex miniOpenAI | model | gpt-5.1-codex-mini | 2025-11 | 400K | 0.25 | 2.00 | 2 providers | open → |
| Kimi K2 ThinkingMoonshot AI | model | kimi-k2-thinking | 2025-11 | 262K | 0.60 | 2.50 | 2 providers | open → |
| Kimi K2 Thinking TurboMoonshot AI | model | kimi-k2-thinking-turbo | 2025-11 | 262K | — | — | 1 provider | open → |
| GPT OSS Safeguard 120BOpenAI | model | gpt-oss-safeguard-120b | 2025-10 | 131K | — | — | 1 provider | open → |
| Nemotron Nano 12B v2 VLNVIDIA | model | nemotron-nano-12b-v2-vl | 2025-10 | 128K | — | — | 1 provider | open → |
| MiniMax-M2MiniMax | model | MiniMax-M2 | 2025-10 | 197K | 0.26 | 1.00 | 1 provider | open → |
| Claude Haiku 4.5Anthropic | model | claude-haiku-4-5 | 2025-10 | 200K | 1.00 | 5.00 | 4 providers | open → |
| Seed 1.6ByteDance Seed | model | seed-1-6 | 2025-10 | 256K | 0.25 | 2.00 | 1 provider | open → |
| Gemini 2.5 Computer Use PreviewGoogle | model | gemini-2.5-computer-use-preview-10-2025 | 2025-10 | 128K | — | — | 1 provider | open → |
| GPT-5 ProOpenAI | model | gpt-5-pro | 2025-10 | 400K | 15.00 | 120.00 | 2 providers | open → |
| Granite-4.0-H-MicroIBM | model | granite-4-h-micro | 2025-10 | 131K | — | — | weights only | open → |
| Granite-4.0-H-SmallIBM | model | granite-4-h-small | 2025-10 | 131K | — | — | weights only | open → |
| GLM-4.6Zhipu AI | model | glm-4.6 | 2025-09 | 200K | 0.60 | 2.20 | 1 provider | open → |
| Claude Sonnet 4.5Anthropic | model | claude-sonnet-4-5 | 2025-09 | 200K | 3.00 | 15.00 | 4 providers | open → |
| DeepSeek V3.2DeepSeek | model | deepseek-v3.2 | 2025-09 | 128K | 0.28 | 0.42 | 3 providers | open → |
| Gemma-SEA-LION-v4-27B-ITAI Singapore | model | gemma-sea-lion-v4-27b-it | 2025-09 | 128K | — | — | weights only | open → |
| Qwen3 MaxAlibaba Qwen | model | qwen3-max | 2025-09 | 262K | 0.78 | 3.90 | 1 provider | open → |
| Qwen3 VL 235B A22B InstructAlibaba Qwen | model | qwen3-vl-235b-a22b-instruct | 2025-09 | 131K | 0.20 | 0.88 | 1 provider | open → |
| Qwen3 VL 235B A22B ThinkingAlibaba Qwen | model | qwen3-vl-235b-a22b-thinking | 2025-09 | 131K | 0.26 | 2.60 | 1 provider | open → |
| Qwen3-VL PlusAlibaba Qwen | model | qwen3-vl-plus | 2025-09 | 262K | — | — | weights only | open → |
| Grok 4 FastxAI | model | grok-4-fast | 2025-09 | 2M | 0.20 | 0.50 | 2 providers | open → |
| GPT-5-CodexOpenAI | model | gpt-5-codex | 2025-09 | 400K | 1.25 | 10.00 | 2 providers | open → |
| Kimi K2 (0905)Moonshot AI | model | kimi-k2-0905 | 2025-09 | 262K | 0.60 | 2.50 | 4 providers | open → |
| Apertus 70BSwiss AI | model | apertus-70b | 2025-09 | 66K | — | — | weights only | open → |
| Apertus 8BSwiss AI | model | apertus-8b | 2025-09 | 66K | — | — | weights only | open → |
| Sarvam 105BSarvam AI | model | sarvam-105b | 2025-09 | 131K | — | — | weights only | open → |
| Qwen3-Next 80B-A3B (Thinking)Alibaba Qwen | model | qwen3-next-80b-a3b-thinking | 2025-09 | 131K | 0.10 | 0.78 | 1 provider | open → |
| Qwen3-Next 80B-A3B InstructAlibaba Qwen | model | qwen3-next-80b-a3b-instruct | 2025-09 | 131K | 0.09 | 1.10 | 1 provider | open → |
| Command A TranslateCohere | model | command-a-translate-08-2025 | 2025-08 | 8K | — | — | weights only | open → |
| Seed 1.6 FlashByteDance Seed | model | seed-1-6-flash | 2025-08 | 256K | 0.07 | 0.30 | 1 provider | open → |
| Grok Code Fast 1xAI | model | grok-code-fast-1 | 2025-08 | 256K | 0.20 | 1.50 | 2 providers | open → |
| Nano BananaGoogle | model | gemini-2.5-flash-image | 2025-08 | 33K | 0.30 | 2.50 | 2 providers | open → |
| Command A ReasoningCohere | model | command-a-reasoning-08-2025 | 2025-08 | 256K | — | — | weights only | open → |
| DeepSeek-V3.1DeepSeek | model | deepseek-v3.1 | 2025-08 | 131K | — | — | 1 provider | open → |
| Nemotron Nano 9B v2NVIDIA | model | nemotron-nano-9b-v2 | 2025-08 | 131K | — | — | 1 provider | open → |
| Seed 1.6 VisionByteDance Seed | model | seed-1-6-vision | 2025-08 | 256K | — | — | weights only | open → |
| GLM-4.5VZhipu AI | model | glm-4.5v | 2025-08 | 64K | 0.60 | 1.80 | 1 provider | open → |
| GPT-5OpenAI | model | gpt-5 | 2025-08 | 400K | 1.25 | 10.00 | 2 providers | open → |
| GPT-5 Chat (latest)OpenAI | model | gpt-5-chat-latest | 2025-08 | 400K | — | — | 1 provider | open → |
| GPT-5 miniOpenAI | model | gpt-5-mini | 2025-08 | 400K | 0.25 | 2.00 | 2 providers | open → |
| GPT-5 nanoOpenAI | model | gpt-5-nano | 2025-08 | 400K | 0.05 | 0.40 | 2 providers | open → |
| Claude Opus 4.1Anthropic | model | claude-opus-4-1 | 2025-08 | 200K | 15.00 | 75.00 | 4 providers | open → |
| GPT OSS 20BOpenAI | model | gpt-oss-20b | 2025-08 | 131K | — | — | 2 providers | open → |
| gpt-oss-120bOpenAI | model | gpt-oss-120b | 2025-08 | 131K | — | — | 6 providers | open → |
| Command A VisionCohere | model | command-a-vision-07-2025 | 2025-07 | 128K | — | — | weights only | open → |
| GLM-4.5Zhipu AI | model | glm-4.5 | 2025-07 | 131K | 0.60 | 2.20 | 1 provider | open → |
| GLM-4.5-AirZhipu AI | model | glm-4.5-air | 2025-07 | 131K | — | — | 1 provider | open → |
| GLM-4.5-FlashZhipu AI | model | glm-4-5-flash | 2025-07 | 131K | — | — | weights only | open → |
| Qwen FlashAlibaba Qwen | model | qwen-flash | 2025-07 | 1M | — | — | weights only | open → |
| Qwen3 Coder FlashAlibaba Qwen | model | qwen3-coder-flash | 2025-07 | 1M | 0.20 | 0.97 | 1 provider | open → |
| Llama 3.3 Nemotron Super 49B v1.5NVIDIA | model | llama-3.3-nemotron-super-49b-v1.5 | 2025-07 | 131K | 0.10 | 0.40 | 1 provider | open → |
| Qwen3 Coder PlusAlibaba Qwen | model | qwen3-coder-plus | 2025-07 | 1M | 0.65 | 3.25 | 1 provider | open → |
| Qwen3 Coder 480BAlibaba Qwen | model | qwen3-coder-480b | 2025-07 | 262K | — | — | 3 providers | open → |
| Qwen3 235B-A22B Instruct 2507Alibaba Qwen | model | qwen3-235b-a22b-instruct-2507 | 2025-07 | 262K | — | — | weights only | open → |
| Voxtral Small (latest)Mistral AI | model | voxtral-small-latest | 2025-07 | 32K | — | — | 1 provider | open → |
| Devstral MediumMistral AI | model | devstral-medium-2507 | 2025-07 | 128K | 0.40 | 2.00 | 2 providers | open → |
| Devstral SmallMistral AI | model | devstral-small-2507 | 2025-07 | 128K | 0.10 | 0.30 | 2 providers | open → |
| Grok 4xAI | model | grok-4 | 2025-07 | 256K | 3.00 | 15.00 | 2 providers | open → |
| Mistral Small 3.2Mistral AI | model | mistral-small-2506 | 2025-06 | 128K | — | — | 1 provider | open → |
| Gemini 2.5 Flash-LiteGoogle | model | gemini-2.5-flash-lite | 2025-06 | 1M | 0.10 | 0.40 | 3 providers | open → |
| Mistral NemotronNVIDIA | model | mistral-nemotron | 2025-06 | 128K | — | — | weights only | open → |
| Magistral SmallMistral AI | model | magistral-small-2506 | 2025-06 | 131K | — | — | 1 provider | open → |
| o3-proOpenAI | model | o3-pro | 2025-06 | 200K | 20.00 | 80.00 | 2 providers | open → |
| Claude Opus 4Anthropic | model | claude-opus-4-20250514 | 2025-05 | 200K | — | — | 1 provider | open → |
| Claude Opus 4 (latest)Anthropic | model | claude-opus-4-0 | 2025-05 | 200K | — | — | 1 provider | open → |
| Claude Sonnet 4Anthropic | model | claude-sonnet-4 | 2025-05 | 200K | 3.00 | 15.00 | 4 providers | open → |
| Claude Sonnet 4 (latest)Anthropic | model | claude-sonnet-4-0 | 2025-05 | 200K | — | — | 1 provider | open → |
| Gemini Embedding 001Google | model | gemini-embedding-001 | 2025-05 | 2K | — | — | 1 provider | open → |
| Solar Pro 2Upstage | model | solar-pro2 | 2025-05 | 66K | — | — | weights only | open → |
| Mistral Medium 3Mistral AI | model | mistral-medium-2505 | 2025-05 | 131K | — | — | 1 provider | open → |
| Mistral Medium 3Mistral AI | model | mistral-medium-3 | 2025-05 | 131K | 0.40 | 2.00 | 2 providers | open → |
| Amazon Nova PremierAmazon | model | nova-premier | 2025-04 | 1M | 2.00 | 8.00 | 1 provider | open → |
| Qwen3 235B-A22BAlibaba Qwen | model | qwen3-235b-a22b | 2025-04 | 262K | — | — | 3 providers | open → |
| Palmyra X5Writer | model | palmyra-x5 | 2025-04 | 1M | 0.60 | 6.00 | 2 providers | open → |
| Qwen3 30B A3BAlibaba Qwen | model | qwen3-30b-a3b | 2025-04 | 131K | 0.09 | 0.45 | 1 provider | open → |
| Gemini 2.5 FlashGoogle | model | gemini-2.5-flash | 2025-04 | 1M | 0.30 | 2.50 | 3 providers | open → |
| OpenAI o3OpenAI | model | o3 | 2025-04 | 200K | 2.00 | 8.00 | 2 providers | open → |
| OpenAI o4-miniOpenAI | model | o4-mini | 2025-04 | 200K | 1.10 | 4.40 | 2 providers | open → |
| Llama 3.1 Nemotron 70B InstructNVIDIA | model | llama-3-1-nemotron-70b-instruct | 2025-04 | 128K | — | — | weights only | open → |
| GPT-4.1OpenAI | model | gpt-4.1 | 2025-04 | 1M | 2.00 | 8.00 | 2 providers | open → |
| GPT-4.1 miniOpenAI | model | gpt-4.1-mini | 2025-04 | 1M | 0.40 | 1.60 | 2 providers | open → |
| GPT-4.1 nanoOpenAI | model | gpt-4.1-nano | 2025-04 | 1M | 0.10 | 0.40 | 2 providers | open → |
| Llama 3.1 Nemotron Ultra 253BNVIDIA | model | llama-3-1-nemotron-ultra-253b | 2025-04 | 128K | — | — | weights only | open → |
| Llama 3.3 Nemotron Super 49B v1NVIDIA | model | llama-3-3-nemotron-super-49b-v1 | 2025-04 | 131K | — | — | weights only | open → |
| Llama 4 MaverickMeta | model | llama-4-maverick | 2025-04 | 1M | — | — | 3 providers | open → |
| Llama 4 Maverick 17B InstructMeta | model | llama-4-maverick-17b-instruct | 2025-04 | 1M | — | — | weights only | open → |
| Llama 4 ScoutMeta | model | llama-4-scout | 2025-04 | 10M | — | — | 3 providers | open → |
| Llama 4 Scout 17B InstructMeta | model | llama-4-scout-17b-instruct | 2025-04 | 3.5M | — | — | weights only | open → |
| Qwen3 32BAlibaba Qwen | model | qwen3-32b | 2025-04 | 131K | 0.08 | 0.28 | 1 provider | open → |
| Qwen3-Coder 30B-A3B InstructAlibaba Qwen | model | qwen3-coder-30b-a3b-instruct | 2025-04 | 262K | 0.07 | 0.27 | 1 provider | open → |
| Qwen3-Coder 480B-A35B InstructAlibaba Qwen | model | qwen3-coder-480b-a35b-instruct | 2025-04 | 262K | — | — | weights only | open → |
| Gemini 2.5 ProGoogle | model | gemini-2.5-pro | 2025-03 | 1M | 1.25 | 10.00 | 3 providers | open → |
| DeepSeek V3 0324DeepSeek | model | deepseek-v3-0324 | 2025-03 | 164K | — | — | 1 provider | open → |
| o1-proOpenAI | model | o1-pro | 2025-03 | 200K | 150.00 | 600.00 | 2 providers | open → |
| Magistral MediumMistral AI | model | magistral-medium | 2025-03 | 128K | 2.00 | 5.00 | 2 providers | open → |
| Mistral Small 3.1 24BMistral AI | model | mistral-small-3-1-24b-instruct-2503 | 2025-03 | 128K | 0.35 | 0.56 | 2 providers | open → |
| Command ACohere | model | command-a-03-2025 | 2025-03 | 256K | 2.50 | 10.00 | 1 provider | open → |
| Command ACohere | model | command-a | 2025-03 | 256K | 2.50 | 10.00 | 1 provider | open → |
| QwQ 32BAlibaba Qwen | model | qwq-32b | 2025-03 | 131K | — | — | weights only | open → |
| QwQ PlusAlibaba Qwen | model | qwq-plus | 2025-03 | 131K | — | — | weights only | open → |
| Aya Vision 32BCohere | model | c4ai-aya-vision-32b | 2025-03 | 16K | — | — | weights only | open → |
| Aya Vision 8BCohere | model | c4ai-aya-vision-8b | 2025-03 | 16K | — | — | weights only | open → |
| Command R7B ArabicCohere | model | command-r7b-arabic-02-2025 | 2025-02 | 128K | — | — | weights only | open → |
| Claude 3.7 SonnetAnthropic | model | claude-3-7-sonnet | 2025-02 | 200K | 3.00 | 15.00 | 4 providers | open → |
| Sonar Deep ResearchPerplexity | model | sonar-deep-research | 2025-02 | 128K | 2.00 | 8.00 | 1 provider | open → |
| ALLaM-2-7bSDAIA | model | allam-2-7b | 2025-01 | 4K | — | — | weights only | open → |
| DeepSeek-R1DeepSeek | model | deepseek-r1 | 2025-01 | 128K | 0.70 | 2.50 | 2 providers | open → |
| DeepSeek-R1-Distill-Qwen-32BDeepSeek | model | deepseek-r1-distill-qwen-32b | 2025-01 | 131K | 0.29 | 0.29 | 2 providers | open → |
| Qwen-Omni TurboAlibaba Qwen | model | qwen-omni-turbo | 2025-01 | 33K | — | — | weights only | open → |
| DeepSeek-V3DeepSeek | model | deepseek-v3 | 2024-12 | 131K | — | — | 1 provider | open → |
| o3-miniOpenAI | model | o3-mini | 2024-12 | 200K | 1.10 | 4.40 | 2 providers | open → |
| Gemini 2.0 FlashGoogle | model | gemini-2.0-flash | 2024-12 | 1M | — | — | 1 provider | open → |
| Gemini 2.0 Flash-LiteGoogle | model | gemini-2.0-flash-lite | 2024-12 | 1M | — | — | 1 provider | open → |
| Phi-4-miniMicrosoft | model | phi-4-mini | 2024-12 | 128K | — | — | weights only | open → |
| Llama 3.3 70BMeta | model | llama-3.3-70b | 2024-12 | 131K | — | — | 4 providers | open → |
| Llama-3.3-70B-InstructMeta | model | llama-3.3-70b-instruct | 2024-12 | 128K | — | — | 1 provider | open → |
| o1OpenAI | model | o1 | 2024-12 | 200K | 15.00 | 60.00 | 2 providers | open → |
| Amazon Nova LiteAmazon | model | nova-lite | 2024-12 | 300K | 0.06 | 0.24 | 1 provider | open → |
| Amazon Nova MicroAmazon | model | nova-micro | 2024-12 | 128K | 0.04 | 0.14 | 1 provider | open → |
| Amazon Nova ProAmazon | model | nova-pro | 2024-12 | 300K | 0.80 | 3.20 | 1 provider | open → |
| Command R7BCohere | model | command-r7b-12-2024 | 2024-12 | 128K | 0.04 | 0.15 | 1 provider | open → |
| Mistral Large 2.1Mistral AI | model | mistral-large-2411 | 2024-11 | 131K | 2.00 | 6.00 | 2 providers | open → |
| Qwen2.5-Coder-0.5BAlibaba Qwen | model | qwen2-5-coder-0-5b | 2024-11 | 33K | — | — | weights only | open → |
| Qwen2.5-Coder-32B-InstructAlibaba Qwen | model | qwen2-5-coder-32b-instruct | 2024-11 | 131K | — | — | weights only | open → |
| Mistral Large (latest)Mistral AI | model | mistral-large-latest | 2024-11 | 262K | — | — | 1 provider | open → |
| Mistral Large 3Mistral AI | model | mistral-large-2512 | 2024-11 | 262K | 0.50 | 1.50 | 2 providers | open → |
| Pixtral Large (latest)Mistral AI | model | pixtral-large-latest | 2024-11 | 128K | — | — | 1 provider | open → |
| Qwen TurboAlibaba Qwen | model | qwen-turbo | 2024-11 | 1M | — | — | weights only | open → |
| Aya Expanse 32BCohere | model | c4ai-aya-expanse-32b | 2024-10 | 128K | — | — | weights only | open → |
| Aya Expanse 8BCohere | model | c4ai-aya-expanse-8b | 2024-10 | 8K | — | — | weights only | open → |
| Claude 3.5 HaikuAnthropic | model | claude-3-5-haiku | 2024-10 | 200K | 0.80 | 4.00 | 4 providers | open → |
| Claude Sonnet 3.5 v2Anthropic | model | claude-3-5-sonnet-20241022 | 2024-10 | 200K | — | — | 1 provider | open → |
| Ministral 8B InstructMistral AI | model | ministral-8b-instruct-2410 | 2024-10 | 131K | — | — | 1 provider | open → |
| Whisper 3 LargeOpenAI | model | whisper-large-v3 | 2024-10 | 448 | — | — | 1 provider | open → |
| Whisper Large v3 TurboOpenAI | model | whisper-large-v3-turbo | 2024-10 | 448 | — | — | 1 provider | open → |
| Llama-3.2-11B-Vision-InstructMeta | model | llama-3.2-11b-vision-instruct | 2024-09 | 128K | 0.24 | 0.24 | 1 provider | open → |
| Llama-3.2-1BMeta | model | llama-3-2-1b | 2024-09 | 131K | — | — | weights only | open → |
| Llama-3.2-3BMeta | model | llama-3-2-3b | 2024-09 | 131K | — | — | weights only | open → |
| Pixtral 12BMistral AI | model | pixtral-12b | 2024-09 | 128K | — | — | 1 provider | open → |
| Qwen2.5-VL 72B InstructAlibaba Qwen | model | qwen2-5-vl-72b-instruct | 2024-09 | 131K | 0.25 | 0.75 | 1 provider | open → |
| Command RCohere | model | command-r-08-2024 | 2024-08 | 128K | 0.15 | 0.60 | 1 provider | open → |
| Command R+Cohere | model | command-r-plus-08-2024 | 2024-08 | 128K | 2.50 | 10.00 | 1 provider | open → |
| Nemotron Mini 4B InstructNVIDIA | model | nemotron-mini-4b-instruct | 2024-08 | 128K | — | — | weights only | open → |
| Llama-3.1-8B-InstructMeta | model | llama-3.1-8b-instruct | 2024-07 | 128K | 0.02 | 0.05 | 1 provider | open → |
| Llama-Guard-3-8BMeta | model | llama-guard-3-8b | 2024-07 | 128K | 0.48 | 0.03 | 1 provider | open → |
| GPT-4o miniOpenAI | model | gpt-4o-mini | 2024-07 | 128K | 0.15 | 0.60 | 2 providers | open → |
| Mistral NemoMistral AI | model | mistral-nemo | 2024-07 | 128K | 0.02 | 0.03 | 2 providers | open → |
| o3-deep-researchOpenAI | model | o3-deep-research | 2024-06 | 200K | 10.00 | 40.00 | 2 providers | open → |
| o4-mini-deep-researchOpenAI | model | o4-mini-deep-research | 2024-06 | 200K | 2.00 | 8.00 | 2 providers | open → |
| CodestralMistral AI | model | codestral | 2024-05 | 256K | 0.30 | 0.90 | 2 providers | open → |
| Codestral-22B-v0.1Mistral AI | model | codestral-22b-v0.1 | 2024-05 | 33K | — | — | 1 provider | open → |
| GPT-4oOpenAI | model | gpt-4o | 2024-05 | 128K | 2.50 | 10.00 | 2 providers | open → |
| Qwen-VL MaxAlibaba Qwen | model | qwen-vl-max | 2024-04 | 131K | — | — | weights only | open → |
| Qwen MaxAlibaba Qwen | model | qwen-max | 2024-04 | 33K | — | — | weights only | open → |
| Claude Haiku 3Anthropic | model | claude-3-haiku-20240307 | 2024-03 | 200K | — | — | 1 provider | open → |
| Qwen PlusAlibaba Qwen | model | qwen-plus | 2024-01 | 1M | 0.26 | 0.78 | 1 provider | open → |
| Qwen-VL PlusAlibaba Qwen | model | qwen-vl-plus | 2024-01 | 131K | — | — | weights only | open → |
| SonarPerplexity | model | sonar | 2024-01 | 128K | 1.00 | 1.00 | 1 provider | open → |
| Sonar ProPerplexity | model | sonar-pro | 2024-01 | 200K | 3.00 | 15.00 | 1 provider | open → |
| Sonar Reasoning ProPerplexity | model | sonar-reasoning-pro | 2024-01 | 128K | 2.00 | 8.00 | 1 provider | open → |
| GPT-4OpenAI | model | gpt-4 | 2023-11 | 8K | 30.00 | 60.00 | 2 providers | open → |
| GPT-4 TurboOpenAI | model | gpt-4-turbo | 2023-11 | 128K | 10.00 | 30.00 | 2 providers | open → |
| GPT-3.5-turboOpenAI | model | gpt-3.5-turbo | 2023-03 | 16K | 0.50 | 1.50 | 2 providers | open → |
| Falcon-H1 34BTII | model | falcon-h1-34b | — | 262K | — | — | weights only | open → |
| Falcon3 10BTII | model | falcon3-10b | — | — | — | — | weights only | open → |
| Hunyuan-A13BTencent | model | hunyuan-a13b | — | — | — | — | weights only | open → |
| Hunyuan-LargeTencent | model | hunyuan-large | — | — | — | — | weights only | open → |
| Hunyuan-T1Tencent | model | hunyuan-t1 | — | — | — | — | weights only | open → |
| Jamba Large 1.7AI21 Labs | model | jamba-large-1.7 | — | 262K | 2.00 | 8.00 | 2 providers | open → |
| Jamba Mini 2AI21 Labs | model | jamba-mini-2 | — | 262K | 0.20 | 0.40 | 2 providers | open → |
| Reka CoreReka | model | reka-core | — | 128K | 3.00 | — | 1 provider | open → |
| Reka EdgeReka | model | reka-edge | — | — | 0.10 | — | 1 provider | open → |
| Reka FlashReka | model | reka-flash | — | — | 0.20 | — | 1 provider | open → |
| AiderAider (open source) | agent | Aider-AI/aider | — | — | free (BYO key) | cli | open → | |
| AmpSourcegraph | agent | sourcegraph/amp-cli | — | — | freemium | cli · ide | open → | |
| Claude CodeAnthropic | agent | anthropics/claude-code | — | — | mixed | cli · sdk-typescript · sdk-python · web · ide · ci | open → | |
| ClineCline (open source) | agent | cline/cline | — | — | free (BYO key) | ide · cli | open → | |
| CodexOpenAI | agent | openai/codex | — | — | mixed | cli · cloud · ci · ide | open → | |
| ContinueContinue (open source) | agent | continuedev/continue | — | — | free (BYO key) | ide · cli | open → | |
| GitHub Copilot CLIGitHub | agent | copilot-cli | — | — | subscription | cli · web · ci | open → | |
| Cursor Agent (CLI)Anysphere | agent | cursor-agent | — | — | subscription | cli · ide · ci · web | open → | |
| DevinCognition | agent | devin | — | — | usage | api · web · slack | open → | |
| Gemini CLIGoogle | agent | google-gemini/gemini-cli | — | — | free | cli · ci | open → | |
| GooseBlock | agent | block/goose | — | — | free (BYO key) | cli · ide | open → | |
| JulesGoogle | agent | jules | — | — | subscription | web · cli · api | open → | |
| OpenCodeOpenCode (open source) | agent | sst/opencode | — | — | free (BYO key) | cli | open → | |
| OpenHandsAll Hands AI | agent | All-Hands-AI/OpenHands | — | — | free (BYO key) | cli · web · api · cloud | open → | |
| Qwen CodeAlibaba Qwen | agent | QwenLM/qwen-code | — | — | freemium | cli | open → | |
| Replit AgentReplit | agent | replit-agent | — | — | subscription+usage | web · cloud | open → | |
| Roo CodeRoo Code (open source) | agent | RooCodeInc/Roo-Code | — | — | free (BYO key) | ide | open → | |
| SWE-agentPrinceton NLP | agent | SWE-agent/SWE-agent | — | — | free (BYO key) | cli | open → | |
| Windsurf (Cascade)Windsurf | agent | windsurf | — | — | freemium | ide | open → | |