兔子API 兔子API
中

model

Anthropic Claude

Direct answerAs reviewed on 2026-08-08, Anthropic positions Fable 5, Opus 5, Sonnet 5, and Haiku 4.5 for highest capability, complex agents, balanced work, and low latency.

Updated · Reviewed

Current official line

Anthropic's current comparison positions Claude Fable 5 as its most capable widely released model, Opus 5 for complex agentic coding and enterprise work, Sonnet 5 for a speed-intelligence balance, and Haiku 4.5 for low latency. Limited previews are not general availability.

Shared capabilities

Anthropic states that current Claude models support text and image input, text output, multilingual capability, and vision and are available through the Claude API and multiple cloud channels. Tools, extended thinking, prompt caching, and output caps remain model-specific.

Choosing within the family

Evaluate Fable or Opus for high-value long-running agents and the hardest reasoning; Sonnet for interactive coding, documents, and routine agents; Haiku for classification, routing, and short high-throughput work. Compare quality, tool success, time to first token, and cost.

API use

The native route is /v1/messages with system instructions, messages, and content blocks; this site uses a Bearer token. Bedrock, Google Cloud, and Microsoft Foundry use different IDs, authentication, and feature exposure.

Migration and limits

New generations can change verbosity, prompt sensitivity, and thinking behavior. Before upgrade, retain a fixed evaluation set and verify exact ID, context, maximum output, region, tools, stop reasons, data terms, and deprecation plan.

Use cases

  • Long-running agents
  • Complex coding
  • Enterprise knowledge work

API protocols

  • /v1/chat/completions

FAQ

Is the model name permanent?

No. Official aliases can move and enabled API IDs can change; pin a tested ID in production and verify availability separately in the model marketplace.

How should I choose among capability-first, balanced, and low-latency Claude tiers?

Evaluate capability-first tiers for high-value long-running agents and the hardest reasoning, start with balanced tiers for interactive coding and documents, and test low-latency tiers for classification and routing. Compare quality, tool success, first-token latency, and cost on real tasks.

Do the Claude API, Bedrock, and other cloud hosts use the same model IDs and protocol?

Not exactly. Native Claude uses Messages content blocks, while cloud hosts can change IDs, authentication, and exposed features. Validate tools, thinking, caching, stop reasons, and region during migration rather than changing only the base URL.

  • Anthropic ClaudeDirect Anthropic Messages calls require x-api-key and anthropic-version. This site recommends Bearer and also accepts native x-api-key on /v1/messages; an HTTP 200 stream can still carry an error event.
  • Anthropic Messages API guideMessages uses system instructions, role messages, and content blocks; direct Anthropic calls require x-api-key and a version header, while this site recommends Bearer and also accepts native x-api-key.
  • Choosing and calling coding modelsSelect coding models by patch correctness, test pass rate, tool success, latency, and cost on real repositories, not marketplace copy or a single benchmark.
  • Tool use and AI agent model guideAn agent is a controlled loop, not merely tool calling: structured schemas, least privilege, state, idempotency, timeouts, approval, audit, and replayable evaluation.

Official sources

  1. Claude Models Official