Skip to Content
WikiModels ReferenceModel Comparison

Model Comparison

This page puts the currently active models side by side so you can pick one at a glance. Scan the table for context window, input modalities, what each model is best for, and its native API protocol, then read the “How to choose” notes below for quick guidance. Prices are not shown here because they change; live pricing and availability are on the model marketplace  in the dashboard, listed per model.

Comparison table

Anthropic (native protocol: Anthropic)

ModelContext windowModalitiesBest forNative protocol
Claude Fable 51,000,000 tokensText, imageFrontier autonomous coding and deep knowledge work; always-on adaptive thinkingAnthropic
Claude Sonnet 51,000,000 tokensText, imageBalanced default for production coding, high-concurrency services, long-context agentsAnthropic
Claude Opus 4.81,000,000 tokensText, imagePrevious-gen frontier for autonomous agents and long-horizon work; still servedAnthropic
Claude Haiku 4.5200,000 tokensText, imageFast, low-cost, high-volume real-time tasks and summarizationAnthropic

OpenAI (native protocol: OpenAI)

ModelContext windowModalitiesBest forNative protocol
GPT-5.6 Sol1,050,000 tokensText, image, PDFFlagship deep reasoning for complex coding, analysis, and planningOpenAI
GPT-5.6 Terra1,050,000 tokensText, image, PDFBalanced, mid-range price for general coding and business appsOpenAI
GPT-5.6 Luna1,050,000 tokensText, imageCost-effective, cost-first for high-frequency light tasks and real-timeOpenAI
GPT-5.51,050,000 tokensText, imagePrevious-gen flagship for multi-step autonomous tasks and researchOpenAI

Google (native protocol: OpenAI)

ModelContext windowModalitiesBest forNative protocol
Gemini 3.1 Pro1,050,000 tokensText, image, PDFFlagship Pro tier for advanced reasoning, coding, and multimodal analysisOpenAI
Gemini 3.5 Flash1,100,000 tokensText, image, videoWorkhorse for high-throughput coding and agentic execution at Flash-tier speedOpenAI
Gemini 3 Flash1,050,000 tokensText, imageLightweight, low-latency, cost-sensitive tasksOpenAI

Open / China (native protocol: OpenAI)

ModelContext windowModalitiesBest forNative protocol
GLM-5.21,000,000 tokensText, image, videoTop-tier open-weights model for long-horizon engineering and Chinese scenariosOpenAI
GLM-5.31,000,000 tokensTextNew-gen flagship, reasoning always on, for complex software engineering and long-horizon agentsOpenAI
GLM-5.1128,000 tokensTextPrevious-gen open-source flagship for agentic engineering; still servedOpenAI

How to choose

Full reference

See the full Models Reference for every model, including more models still coming online (such as video and additional open-weights models). Live pricing and current availability are listed there and on the model marketplace in the dashboard.

Last updated on