VercelEngineering PostOfficial Source

Claude Opus 5.5 now available on AI Gateway

Claude Opus 5.5 reaches Vercel AI Gateway with stronger long-run agent positioning, but adaptive thinking and retired forced tool use can break existing requests with HTTP 400s.

Vercel · Sep 22, 2026

Open Source Open Markdown Open JSON

Source Summary

Claude **Opus 5.5** is available on AI Gateway with a **1M-token context window** and up to **128K output tokens**. Anthropic says it matches Fable 5.1 while running about 30% faster and costing about 40% less per task than Opus 5.

Practical Implication

Audit harnesses before switching: fixed or disabled thinking is rejected, and forced tool selection is retired. Steer thinking with effort and prompts; use structured outputs for JSON, and add retry handling when the model skips a requested tool.

Agent-Ready Context

Claude **Opus 5.5** is available on AI Gateway with a **1M-token context window** and up to **128K output tokens**. Anthropic says it matches Fable 5.1 while running about 30% faster and costing about 40% less per task than Opus 5.

Audit harnesses before switching: fixed or disabled thinking is rejected, and forced tool selection is retired. Steer thinking with effort and prompts; use structured outputs for JSON, and add retry handling when the model skips a requested tool.

The speed and cost figures are provider claims, not results from the supplied material. Adaptive thinking and non-forced tools also reduce deterministic control, so production migrations need error-path and tool-selection tests.

Connected Context · Feed7 Judgment

This adds a high-capacity long-run agent option but makes migration behavior, not the provider’s speed and cost claims, the immediate engineering concern. Existing harnesses may fail because fixed thinking is rejected and forced tool selection is gone; production adoption therefore depends on request compatibility, structured-output validation, skipped-tool retries, and matched workload results.

Inkling Small from Thinking Machines is now available on AI GatewayBoth expose adjustable reasoning for tool-heavy work, but Opus 5.5 removes fixed thinking and forced tool selection, making control-path compatibility a sharper evaluation criterion than Inkling Small’s efficiency positioning alone.Qwen 3.8 Flash now available on AI GatewayQwen 3.8 Flash provides another 1M-context agent route, but with a 65K output ceiling versus Opus 5.5’s 128K; capacity still does not resolve comparative tool reliability, latency, or cost.GLM 5.3 Flash now available on AI GatewayGLM 5.3 Flash reinforces that million-token context, function calling, and structured output are available from adjacent routes, so Opus 5.5’s migration risks and workload performance should drive selection rather than feature presence.

Context Map

modelcoding#coding-agents#model-selection#tool-use

Uncertainty

The speed and cost figures are provider claims, not results from the supplied material. Adaptive thinking and non-forced tools also reduce deterministic control, so production migrations need error-path and tool-selection tests.