Claude Opus 5.5 is live on SeedRouter
AnthropicText generation

Claude Sonnet 5.5 for everyday coding and documents

Use Claude Sonnet 5.5 for code reviews and document questions. $0.70 / 1M input, $3.50 / 1M output.

Available$0.70 / 1M input · $3.50 / 1M output$2.00 / 1M input · $10.00 / 1M output-65%
  • Adaptive thinking
  • 1M-token context
  • Images and PDFs
  • Prompt caching
  • Streaming
Context window
1M tokens
Max output
128K tokens
Thinking
Adaptive
Default effort
high

Try Claude Sonnet 5.5

Test Claude Sonnet 5.5 with text or files. Inspect answers and usage.

Parameters
claude-sonnet-5-5$0.70 in · $3.50 out per 1M tokens
Thinking mode
Effort
Thinking display

Check compatibility notes before using advanced options.

Conversation total$0.000000
Ready

Example prompts

Uses your balance. Failed requests are free.

Claude Sonnet 5.5 output

Unedited answer at default effort.

Explain a database index to a new backend developer in three concise sentences. Include one trade-off.

A database index is a separate data structure (typically a B-tree) that stores the values of one or more columns in sorted order along with pointers to the corresponding rows, so the database can find matching rows without scanning the entire table. Think of it like a book's index: instead of reading every page to find a topic, you look it up and jump straight to the right place. The trade-off is that indexes speed up reads but slow down writes (INSERT, UPDATE, DELETE) and consume extra storage, because every change to the table must also be applied to each relevant index.

October 1, 2026: 65 input, 170 output tokens. Results vary.

Claude Sonnet 5.5 pricing

Claude Sonnet 5.5 prices match your account rates.

Example request2,000 input, 1,000 output tokens
$0.0049per request
Thinking tokens count as output.
What $20.00 buysOutput at the current rate
5,714,285output tokens
Output only; input and cache tokens cost extra.

Illustrative sizes; charges follow reported usage.

CategoryDefaultclaude-sonnet-5-5AWSBclaude-sonnet-5-5:claude-0.7Officialclaude-sonnet-5-5:claude-0.95
Price · 1M tokensPrice · 1M tokensPrice · 1M tokens
Input$0.70$1.40$1.90
Output$3.50$7.00$9.50
Cache read$0.035$0.07$0.095
Cache write, 5 minutes$0.875$1.75$2.375
Cache write, 1 hour$1.40$2.80$3.80

What is Claude Sonnet 5.5?

Claude Sonnet 5.5 is Anthropic's coding and document model, with 1M context and 128K output limits.

Claude Sonnet 5.5 defaults to high-effort adaptive thinking. Between-tools skips up-front thinking. Advanced features have compatibility limits.

Text, images and PDFs in; text out.

Model ID
claude-sonnet-5-5
Context window
1M tokens
Max output
128K tokens
Effort levels
low to max
Input
Text, images, PDFs

Connect your app or coding agent

Connect Claude Sonnet 5.5 to your backend or coding agent.

API

Call it from your backend

For apps and services

Call Claude Sonnet 5.5 with the Anthropic SDK and your SeedRouter key.

  1. 1Create an API key
  2. 2Set https://api.seedrouter.ai as base URL
  3. 3Choose claude-sonnet-5-5
Agent

Hand it to your coding agent

For coding agents

Ask your agent to prepare a Claude Sonnet 5.5 request and cost estimate for approval.

  1. 1Copy the prompt
  2. 2Paste it into your agent
  3. 3Approve the request

Work with code and documents

Give Claude Sonnet 5.5 a task with context you can verify.

Review code

Find edge cases with Claude Sonnet 5.5 and request tests.

Compare sources

Compare reports and request section references for each conclusion.

Read files

Ask about screenshots or PDFs; verify details against the original.

Call tools

Give Claude Sonnet 5.5 tools, inspect arguments and return results.

Choose thinking

Compare Claude Sonnet 5.5 thinking modes; higher effort alone proves no improvement.

Reuse context

Cache repeated Claude Sonnet 5.5 instructions for five minutes or one hour.

Build around your workflow

Code reviews

Draft findings with Claude Sonnet 5.5; keep a developer reviewing.

Support drafts

Ground Claude Sonnet 5.5 replies in your help articles. Review before sending.

Document extraction

Extract JSON with Claude Sonnet 5.5; check values against the document.

Start with Claude Sonnet 5.5

  1. 01

    Create a key

    Create a key and add credit for Claude Sonnet 5.5.

  2. 02

    Set the base URL

    Anthropic: https://api.seedrouter.ai. OpenAI: append /v1.

  3. 03

    Choose your model

    Set claude-sonnet-5-5 and max_tokens for your Claude Sonnet 5.5 request.

  4. 04

    Review usage

    Review Claude Sonnet 5.5 tokens and charges in usage records.

Get an API key

Claude Sonnet 5.5 at a glance

Tested limits are in the API reference.

Anthropic Messages API
Native format; tested limits apply
OpenAI Chat Completions
Basic requests verified
OpenAI Responses
Basic requests verified
Image and PDF input
Base64 examples verified
Prompt caching
5-minute and 1-hour
Forced tool use
Unsupported by this model
Failed requests
Not charged

Claude Sonnet 5.5 batch processing and fast mode are not offered here.

Limits and compatibility to check

Context and output

Claude Sonnet 5.5 lists 1M context and 128K output; these ceilings remain untested here.

Thinking restrictions

Claude Sonnet 5.5 rejects disabled/manual thinking. Between-tools accepts low, medium or high effort.

Sampling restrictions

Omit sampling settings; accepted compatibility values are documented separately.

Prewarming and stops

Claude Sonnet 5.5 tests rejected zero-output prewarming and continued past a stop string.

Signed compaction

The compaction test returned ordinary text without a signed block.

Instructions and history

Per-message effort recall and conflicting system-instruction tests found issues.

Why use SeedRouter?

One key

Call Claude Sonnet 5.5 with Messages or basic OpenAI-format requests.

Pay as you go

Spend your balance across models. No subscription.

Failures are free

Claude Sonnet 5.5 requests that return errors are not charged.

Live prices

Claude Sonnet 5.5 prices come from billing data.

Prompt caching

Claude Sonnet 5.5 passed both cache-usage checks; official minimum: 512 tokens.

Images and PDFs

Image and PDF examples passed; full media boundaries remain unverified.

Streaming

Stream Claude Sonnet 5.5 output; handle thinking, tools and errors.

Related models

Compare Claude Sonnet 5.5 with other available models.

Claude Fable 5
claude-fable-5

Call Claude Fable 5 with the Anthropic or OpenAI SDK. Deep reasoning, 1M-token context, forced tool use, live per-token pricing and a playground to test it.

View pricing
Claude Fable 5.1
claude-fable-5-1

Call Claude Fable 5.1 with the Anthropic or OpenAI SDK. Deep reasoning, 1M-token context, cheap cached reads, live pricing and a playground to try it today.

View pricing
Claude Fable 5.2
claude-fable-5-2

Try Claude Fable 5.2 for coding and problem solving with a 1M-token context. Compare live token prices and model tiers, then test it in the playground.

View pricing
Claude Haiku 5.5
claude-haiku-5-5

Try Claude Haiku 5.5 for classification, extraction and summaries. See live token prices, test your prompts, and connect your app with the Messages API.

View pricing
Claude Mythos 5
claude-mythos-5

Try Claude Mythos 5 for complex reasoning and research with a 1M-token context. Compare live token prices and model tiers, then test it in the playground.

View pricing
Claude Mythos 5.1
claude-mythos-5-1

Try Claude Mythos 5.1 for research and agent workflows with a 1M-token context. Compare live token prices and model tiers, then test it in the playground.

View pricing

Claude Sonnet 5.5 FAQ

What is Claude Sonnet 5.5?

Claude Sonnet 5.5 is Anthropic's coding and document model. It accepts text and images, returning text or tool requests.

How does it compare with Opus 5.5?

Claude Sonnet 5.5 defaults to high effort and offers between-tools thinking. Opus defaults to medium. Compare both on your workload.

What does Claude Sonnet 5.5 cost?

Claude Sonnet 5.5 costs $0.70 / 1M input and $3.50 / 1M output. Cache rates appear above; charges follow reported tokens.

Can I disable thinking?

Claude Sonnet 5.5 rejects disabled thinking. Between-tools skips up-front thinking at low, medium or high effort.

When was Claude Sonnet 5.5 released?

Claude Sonnet 5.5 launched September 28, 2026, with a June 2026 knowledge cutoff. The release guide covers changes.

Which model ID do I use?

Use claude-sonnet-5-5 for Claude Sonnet 5.5. Messages requires model, max_tokens and messages. Keep keys server-side.

Does Claude Sonnet 5.5 support OpenAI SDKs?

Basic Claude Sonnet 5.5 Chat Completions and Responses requests passed testing. Use Messages for native Claude parameters.

Are failed requests charged?

Claude Sonnet 5.5 requests that return errors are not charged, including Playground requests.

Put Claude Sonnet 5.5 to work

Try one task in the Playground, then connect your application.