Skip to content
Compare

Side by side, on the numbers you are billed from

These are the same prices the gateway meters against — not a marketing table maintained separately from the code.

Models compared side by side, one column per model.
ModelLing-2.6-flashinclusionaiQwen3.6 FlashqwenKimi K2.7 Codemoonshoto1-proopenai
Cost of a typical call2,000 in / 500 out$0.00004$0.00094$0.00321$0.60000
Input / 1M$0.010$0.188$0.730$150.00
Output / 1M$0.030$1.13$3.50$600.00
Cached input / 1M$0.0020$0.150
Context window262K1M262K200K
Max output33K66K262K100K
Tool calling
Structured output
Image input
Extended reasoning
Streaming
ProvidersMore than one means automatic failoverOpenRouterOpenRouterOpenRouterOpenRouter

Compare something else

Pick up to 4. The selection lives in the URL, so a comparison is a link you can send to whoever is asking why the bill changed.

Jamba Large 1.7Aion-2.0Aion-3.0Aion-3.0-MiniAion-RP 1.0 (8B)Olmo 3 32B ThinkNova 2 LiteNova Lite 1.0Nova Micro 1.0Nova Premier 1.0Nova Pro 1.0Magnum v4 72BClaude 3 HaikuClaude Fable 5Claude Haiku 4.5Claude Haiku 4.5Claude Opus 4Claude Opus 4.8Claude Opus 4.1Claude Opus 4.5Claude Opus 4.6Claude Opus 4.7Claude Opus 4.7 (Fast)Claude Opus 4.8Claude Opus 4.8 (Fast)Claude Opus 5Claude Opus 5 (Fast)Claude Sonnet 4Claude Sonnet 4.6Claude Sonnet 4.5Claude Sonnet 4.6Claude Sonnet 5Trinity Large ThinkingVirtuoso LargeERNIE 4.5 VL 424B A47B Seed 1.6Seed 1.6 FlashSeed-2.0-LiteSeed-2.0-MiniUI-TARS 7B UncensoredCommand ACommand R (08-2024)Command R+ (08-2024)Command R7B (12-2024)Cogito v2.1 671BDeepSeek V3DeepSeek V3 0324DeepSeek V3.1DeepSeek R1 (0528)R1 0528R1 Distill Llama 70BDeepSeek V3.1DeepSeek V3.1 TerminusDeepSeek V3.2DeepSeek V3.2 ExpDeepSeek V4 FlashDeepSeek V4 Flash 0731DeepSeek V4 ProGemini 2.5 FlashGemini 2.5 Flash LiteGemini 2.5 ProGemini 2.5 Pro Preview 06-05Gemini 2.5 Pro Preview 05-06Gemini 3 Flash PreviewGemini 3.1 Flash LiteGemini 3.1 Flash Lite PreviewGemini 3.1 Pro PreviewGemini 3.1 Pro Preview Custom ToolsGemini 3.5 FlashGemini 3.5 Flash LiteGemini 3.6 FlashGemma 2 27BGemma 3 12BGemma 3 27BGemma 3 4BGemma 3n E4B InstructGemma 3n 4BGemma 4 26B A4B Gemma 4 31BMythoMax 13BGranite 4.0 MicroGranite 4.1 8BMercury 2Ling-2.6-1TLing-2.6-flashRing-2.6-1TKAT-Coder-Air V2.5KAT-Coder-Pro V2KAT-Coder-Pro V2.5Weaver (alpha)LongCat 2.0Llama 3.1 70B InstructLlama 3.1 8B InstructLlama 3.2 1B InstructLlama 3.2 3B InstructLlama 3.3 70B InstructLlama 4 MaverickLlama 4 ScoutLlama Guard 4 12BMuse Spark 1.1Phi 4WizardLM-2 8x22BMiniMax-01MiniMax M1MiniMax M2MiniMax M2-herMiniMax M2.1MiniMax M2.5MiniMax M2.7MiniMax M3Codestral 2508Ministral 3 14B 2512Ministral 3 3B 2512Ministral 3 8B 2512Mistral LargeMistral Large 2407Mistral Large 3 2512Mistral Medium 3Mistral Medium 3.5Mistral Medium 3.1Mistral NemoSabaMistral Small 3Mistral Small 4Mistral Small 3.1 24BMistral Small 3.2 24BMixtral 8x22B InstructVoxtral Small 24B 2507Kimi K2 0711Kimi K2 0905Kimi K2 ThinkingKimi K2.5Kimi K2.6Kimi K2.7 CodeKimi K3Morph V3 FastMorph V3 LargeNex-N2-MiniNex-N2-ProHermes 3 405B InstructHermes 3 70B InstructHermes 4 405BHermes 4 70BNemotron 3 Nano 30B A3BNemotron 3 SuperNemotron 3 UltraGPT-3.5 TurboGPT-3.5 Turbo (older v0613)GPT-3.5 Turbo 16kGPT-3.5 Turbo InstructGPT-4GPT-4 TurboGPT-4 Turbo PreviewGPT-4.1GPT-4.1 miniGPT-4.1 NanoGPT-4oGPT-4o (2024-05-13)GPT-4o (2024-08-06)GPT-4o (2024-11-20)GPT-4o miniGPT-4o-mini (2024-07-18)GPT-5GPT-5 miniGPT-5 nanoGPT-5 ProGPT-5.1GPT-5.1-CodexGPT-5.1-Codex-MaxGPT-5.1-Codex-MiniGPT-5.2GPT-5.2 ChatGPT-5.2-CodexGPT-5.2 ProGPT-5.3 ChatGPT-5.3-CodexGPT-5.4GPT-5.4 MiniGPT-5.4 NanoGPT-5.4 ProGPT-5.5GPT-5.5 ProGPT-5.6 LunaGPT-5.6 Luna ProGPT-5.6 SolGPT-5.6 Sol ProGPT-5.6 TerraGPT-5.6 Terra ProGPT Chat LatestGPT-OSS 120BGPT-OSS 20Bgpt-oss-safeguard-20bo1o1-proo3o3 Minio3 Mini Higho3 Proo4-minio4 Mini HighPerceptron Mk1SonarSonar Deep ResearchSonar ProSonar Pro SearchSonar Reasoning ProLaguna S 2.1Laguna XS 2.1Qwen2.5 72B InstructQwen2.5 7B InstructQwen2.5 Coder 32B InstructQwen-PlusQwen Plus 0728Qwen Plus 0728 (thinking)Qwen2.5 VL 72B InstructQwen3 14BQwen3 235B A22BQwen3 235B A22B Instruct 2507Qwen3 235B A22B InstructQwen3 235B A22B Thinking 2507Qwen3 30B A3BQwen3 30B A3B Instruct 2507Qwen3 30B A3B Thinking 2507Qwen3 32BQwen3 8BQwen3 Coder 480B A35BQwen3 Coder 30B A3B InstructQwen3 Coder FlashQwen3 Coder NextQwen3 Coder PlusQwen3 MaxQwen3 Max ThinkingQwen3 Next 80B A3B InstructQwen3 Next 80B A3B ThinkingQwen3 VL 235B A22B InstructQwen3 VL 235B A22B ThinkingQwen3 VL 30B A3B InstructQwen3 VL 30B A3B ThinkingQwen3 VL 32B InstructQwen3 VL 8B InstructQwen3 VL 8B ThinkingQwen3.5-122B-A10BQwen3.5-27BQwen3.5-35B-A3BQwen3.5 397B A17BQwen3.5 9BQwen3.5-FlashQwen3.5 Plus 2026-02-15Qwen3.5 Plus 2026-04-20Qwen3.6 27BQwen3.6 35B A3BQwen3.6 FlashQwen3.6 Max PreviewQwen3.6 PlusQwen3.7 FlashQwen3.7 MaxQwen3.7 PlusReka EdgeReka Flash 3Relace Apply 3Relace SearchFugu UltraLlama 3 8B LunarisLlama 3.1 Euryale 70B v2.2Llama 3.3 Euryale 70BStep 3.5 FlashStep 3.7 FlashHunyuan A13B InstructHy3Hy3 previewCydonia 24B V4.1Rocinante 12BSkyfall 36B V2UnslopNemo 12BInklingInkling SmallReMM SLERP 13BSolar Pro 3Palmyra X5Grok 4.20Grok 4.20 Multi-AgentGrok 4.3Grok 4.5Grok Build 0.1MiMo-V2.5MiMo-V2.5-ProGLM 4.5GLM 4.5 AirGLM 4.5VGLM 4.6GLM 4.6VGLM 4.7GLM 4.7 FlashGLM 5GLM 5 TurboGLM 5.1GLM-5.2GLM 5V Turbo

Stop guessing which one is worth it

A table settles price and context. It cannot settle whether the dearer model is better at your prompt — only running both does that. Signing up takes no card and commits you to nothing, and the playground answers the same question on two models side by side, pricing each reply as it arrives.

Compare models · Multigrid