Claude Sonnet 5.5
An Anthropic Claude model with text and image inputs and text output.
- Verified facts
- 10
- Plans
- —
- Sources
- 2
- Pricing
- Metered usage
Overview
What Claude Sonnet 5.5 is for
An Anthropic Claude model with text and image inputs and text output.
Read the full editorial overview
When to shortlist it
Claude Sonnet 5.5 can be compared using its documented API identifier, modalities and standard token rates. Its model page also lists behavior changes that matter when migrating an existing application.
What to compare before choosing
Check thinking settings and tool compatibility for this exact version. Keep the standard output ceiling separate from the batch beta extension, and measure quality on your own tasks before choosing it.
The standard output ceiling is 128K tokens; the documented 300K batch option requires a separate beta header. Thinking and tool behavior are model-specific.
Evidence and buying terms
This profile summarizes the linked official documentation checked on 18 October 2026. It is not a hands-on test or a measured performance ranking. The named plans and model identifiers keep their own scope. Confirm account access, billing terms, taxes and any extra charges before buying.
Claude Sonnet 5.5: official API documentation · Evidence: documentation · Oct 18, 2026
Claude Sonnet 5.5: official API documentation · Evidence: documentation · Oct 18, 2026
Documented facts
Each fact comes from official documentation and shows when it was verified.
Who it is for
An Anthropic Claude model with text and image inputs and text output.
Coverage limits
The standard output ceiling is 128K tokens; the documented 300K batch option requires a separate beta header. Thinking and tool behavior are model-specific.
Provider
Anthropic
Provider identity is linked to the separate Anthropic Claude API entry.
API model identifier
claude-sonnet-5-5
Modalities
Text and image input; text output
Context window
1M tokens in the context window
Maximum output
128K output tokens (standard API)
Input token rate
2 USD per million base input tokens
Standard base input rate for Claude Sonnet 5.5. Prompt cache writes/reads and batch processing have separate rates; tools, service tier and taxes can change the total.
Output token rate
10 USD per million output tokens
Standard output rate for Claude Sonnet 5.5. Compare the exact consumption option; the batch discount is separate.
Availability
Active model; released 28 September 2026.
Vendor lifecycle status checked on 18 October 2026; account and platform eligibility require confirmation.
Applies to the facts above: Official documentation checked on 18 October 2026; no hands-on test.
Not confirmed in our sources
We have not confirmed these terms for Claude Sonnet 5.5 in the linked documentation. That does not mean Claude Sonnet 5.5 lacks them; confirm them before you rely on them.
- Pricing
Sources & methodology
Facts come from the linked documentation. Documentation checks are not hands-on tests, and readable sources can have incomplete coverage.
Discovered an undocumented discrepancy or pricing shift? Submit a correction request.
Submit correctionMore AI models tools
Compare documented scope side by side. Different billing units do not establish a cost winner.
Claude Sonnet 5.5 comparisons
Compare two products in the same category using their documented terms and sources.