Gemini 4 Argon is available on RouterHub. Explore Google’s model for complex coding, reasoning, and multi-step agent tasks.
作者:辰, 吴
Nano Banana 2.1: Image Generation and Editing for Product Workflows
Nano Banana 2.1 is available on RouterHub. Explore Google’s image generation and editing model for developer-led visual workflows.
Muse Wonder: Coding and Reasoning for Long-Running Agents

Muse Wonder is available on RouterHub in preview. Explore Meta’s model for coding, tool use, multimodal understanding, and long-running agents, with a one-million-token context window.
GPT-6.1 Sol: A Stronger Sol for Complex Work

GPT-6.1 Sol is available on RouterHub. Explore OpenAI’s upgrade for coding, document-heavy work, and multi-step workflows, plus a practical way to evaluate it against your current model.
Claude Sonnet 5.5: Faster Output for Everyday Workflows

Claude Sonnet 5.5 is available on RouterHub. Explore Anthropic’s reported speed and task-cost results, model specifications, and practical uses for well-scoped work.
Typed Decisions, Not Generated Text: Jev 1.13 on RouterHub

TypeSafe Jev 1.13 is available through RouterHub’s System One API. Use typed questions to turn text and structured state into choices, scores, and likelihoods your application can act on.
Claude Opus 5.5: Testing Long-Running Coding and Agent Work

Claude Opus 5.5 is available on RouterHub. Explore its coding and agent capabilities, Anthropic-published evaluation results, and practical workloads to test first.
GPT-6 Sol and Luna: Match the Model to the Work

GPT-6 Sol and GPT-6 Luna are available on RouterHub. See where each model fits and how to evaluate them against your own workloads.
Grok 4.7: Stronger Coding, More Careful Verification

Grok 4.7 is available on RouterHub. Explore its capabilities, provider-published benchmarks, and uses in coding and document-heavy workflows.
DeepSeek V4.1 Flash: A Causal Encoder–Decoder for Long-Context AI

DeepSeek V4.1 Flash brings a 1M-token context window, native image understanding, and stage-specific active parameters to RouterHub for long-context and multimodal evaluation.
