Claude Sonnet 5.5 API

Price check: official, OpenRouter and Wokey

USD per million tokens. Official and OpenRouter rates were checked by hand on 2026-09-29, excluding tax; the Wokey rate is read from the live price list.

Checked 2026-09-29 · Official pricing page · OpenRouter endpoint list

Use it in Claude Code

This model supports /v1/messages on Wokey. Set these variables, then start claude.

export ANTHROPIC_BASE_URL="https://api.wokey.ai"
export ANTHROPIC_AUTH_TOKEN="$WOKEY_API_KEY"
export ANTHROPIC_MODEL="claude-sonnet-5-5"

Claude Sonnet 5.5 at a glance

Release date

2026-09-28, the second Claude 5.5 model (Opus 5.5 shipped 09-22; Anthropic says Haiku 5.5 follows in the coming weeks)

Positioning

A direct upgrade over Sonnet 5: 30%+ faster and up to 30% cheaper for most work because it uses fewer tokens. Anthropic calls it the fastest Sonnet to date

Context and output

1M context; 128K max output, or 300K on the Batch API with the output-300k-2026-03-24 beta header

Input and cutoff

Text and image input; knowledge cutoff June 2026

Default effort

high on the API, medium in Claude Code and the Claude apps; five recalibrated levels: low / medium / high / xhigh / max

Official price

$2 input / $10 output per million tokens, same as Sonnet 5; cache read $0.20, 5-minute cache write $2.50, 1-hour $4; Batch $1 / $5

Model ID

claude-sonnet-5-5 (anthropic.claude-sonnet-5-5 on Bedrock)

Checked 2026-09-29 · Sources: Anthropic · What’s new

Official benchmarks: Sonnet 5.5 vs Sonnet 5 vs Opus 5.5 vs GPT-6 Sol

From Anthropic’s launch page; these are vendor-reported results. “—” means no score was published. Anthropic did not publish SWE-bench.

In Artificial Analysis’ independent run, Terminal-Bench came out at 64% for Sonnet 5.5 and 60% for Opus 5.5, lower than the official figures but in the same order. Anthropic also states that Opus 5.5 remains clearly stronger at complex, open-ended work that needs sustained judgment.

Which to use: Sonnet 5.5, Sonnet 5 or Opus 5.5

vs Sonnet 5

Same price, faster, and ahead on every published benchmark, so it is a drop-in upgrade. Check the migration list below first: disabling thinking, forced tool use and non-default sampling parameters all return 400 on Sonnet 5.5.

vs Opus 5.5

Use Sonnet 5.5 for well-scoped everyday coding, bug fixes, and documents, spreadsheets and slides; use Opus 5.5 for complex, open-ended work that needs sustained judgment. Opus 5.5 lists at twice the price ($4 / $20), but both models read cache at $0.20. A common pattern is Opus 5.5 as the orchestrator with Sonnet 5.5 sub-agents.

Choosing effort

Anthropic recommends starting agentic coding at medium and moving hard tasks to high; use medium or low for chat. Artificial Analysis found high to be its most competitive setting; at max it averaged about 193K output tokens per task, the highest they have measured. A common community view: if you need xhigh or max, try Opus 5.5 at low or medium instead.

Effort documentation

Third-party and community reviews

• Artificial Analysis: Intelligence Index 56, second only to Opus 5.5 (max) and 18 points above Sonnet 5; hallucination rate 47% versus 59% for Opus 5.5. An index task averaged $7.60 at official prices, about 50% more than Sonnet 5, which leaves it off the cost/intelligence Pareto frontier. Every Wokey meter is 15% of the official rate, so the same task comes to about $1.14.
• Hacker News (545-point thread): Positive: noticeably fast, with agentic coding close to Opus. Critical: at high or xhigh effort you may as well run Opus 5.5 at low or medium, so the two overlap; cache reads cost the same as Opus; some false refusals on security questions. Simon Willison saw max effort burn 128K thinking tokens in 15 minutes.

Migrating from Sonnet 5: requests that return 400

These changes come from Anthropic’s What’s new page. Check your requests for them before switching the model to claude-sonnet-5-5.

• thinking: {"type": "disabled"} returns 400. To skip up-front thinking, use {"type": "between_tools"}; it only works at low, medium or high effort and returns 400 at xhigh or max.
• tool_choice of any or tool returns 400. Use auto and add strict: true to the tool definition to enforce the argument shape.
• Non-default temperature, top_p or top_k returns 400; remove those fields.
• Thinking blocks are bound to the model, conversation prefix and account: replaying them after editing history returns 400, and blocks sent from another account are silently dropped.
• The computer_20251124 tool version is no longer supported.
• Text between tool calls now comes back inside thinking blocks; if your client hides thinking, progress updates between tool calls disappear.
• The minimum cacheable prompt drops from 1,024 to 512 tokens; refusals return stop_reason: "refusal".

Request body that skips up-front thinking (/v1/messages)

{
  "model": "claude-sonnet-5-5",
  "max_tokens": 4096,
  "thinking": { "type": "between_tools" },
  "output_config": { "effort": "medium" },
  "messages": [{ "role": "user", "content": "Fix the failing test in src/app.ts" }]
}

Catalog pricing snapshot

Prices are per 1M tokens; request-time pricing controls settlement.

Official price source: https://www.anthropic.com/claude-sonnet-5-5

Model capabilities

Context

1,000,000 tokens

Max output

128,000 tokens

Streaming

Supported

Tools

Supported

Vision

Supported

Supported API forms

/v1/messages

Send a request

/v1/messages

curl https://api.wokey.ai/v1/messages \
  -H "x-api-key: $WOKEY_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-sonnet-5-5","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

Use Claude Sonnet 5.5 in your tools

The gateway is https://api.wokey.ai (OpenAI-compatible clients usually take https://api.wokey.ai/v1), and the model ID is claude-sonnet-5-5. Open the guide for the client you use.

• Use Claude Sonnet 5.5 in Claude Code: Anthropic Messages · base URL and API key setup
• Use Claude Sonnet 5.5 in Claude Desktop: Anthropic Messages · base URL and API key setup
• Claude API cost calculator: what Claude Sonnet 5.5 costs per month: Compare monthly cost on the Anthropic API, OpenRouter and Wokey for your usage and cache hit rate.
• OpenRouter alternative: Wokey vs OpenRouter: Compare token prices, payment fees, API forms, and upstream sources.
• Verifiable AI API: check a Claude Sonnet 5.5 response came from the official upstream: Which responses carry a tee.proof, and what a proof does and does not show.
• Verify a Claude Sonnet 5.5 response online: AI API relay verifier: Paste a response with its tee.proof and check it locally in your browser; nothing is uploaded.

Frequently asked questions

Related models and documentation

• Claude Sonnet 5
• Claude Sonnet 4.6
• Claude Sonnet 4.5
• Claude Fable 5.1
• API documentation
• All models and pricing
• Provider Node