Claude Sonnet 5.5
Claude Sonnet 5.5 is the middle model in Anthropic's 5.5 line, released 2026-09-28.
- Closed
Anthropic, 1M context, $2 in / 1M
Model by Anthropic
Claude Sonnet 5 is Anthropic's mid-tier model for agentic coding at a low price, and it fits developers who want near-Opus results without Opus bills.
Checked 2026-11-05
Loading poll...
Claude Sonnet 5 is Anthropic's mid-tier model for agentic coding at a low price, and it fits developers who want near-Opus results without Opus bills. Anthropic published it on 30 June 2026 and now marks it legacy, with Sonnet 5.5 as the current Sonnet. It has a 1 million token context window, 128 thousand tokens of output, adaptive thinking with effort levels, and a reliable knowledge cutoff of January 2026. Price is $2 per million input tokens and $10 per million output tokens. An edit dated 10 August 2026 made that introductory rate permanent, replacing the earlier $3 and $15. Anthropic says the new tokenizer can turn the same text into roughly 1.0 to 1.35 times more tokens, so compare cost per task, not per token. Setting temperature, top_p or top_k returns an error. It is available as claude-sonnet-5 on the Claude API, and Anthropic says it will not retire before 30 June 2027. Its cyber ability is lower than the Opus models. We would pick Sonnet 5.5 for new builds and keep this one for pinned workloads. Figures come from Anthropic's announcement, its model page and OpenRouter. We have not run it ourselves.
Claude Sonnet 5.5 is the middle model in Anthropic's 5.5 line, released 2026-09-28.
Anthropic, 1M context, $2 in / 1M
Claude Opus 5.5 is Anthropic's larger Claude model in the 5.5 line, released 2026-09-22.
Anthropic, 1M context, $4 in / 1M
Claude Haiku 5.5 is the smallest and cheapest model in Anthropic's 5.5 line, released 2026-10-07.
Anthropic, 1M context, $0.10 in / 1M
Anthropic's API bills per token.
Vertex AI is Google Cloud's platform for building with Gemini and other hosted models, billed through a Google Cloud account.
Checked 2026-10-31
Checked 2026-10-31
1,000,000 tokens, with up to 128,000 tokens of output.
$2 per million input tokens and $10 per million output tokens, checked 31 October 2026.
No. The weights are not published, so you use it through the maker's API or a hosting provider.
Anthropic makes it, and released it on 30 June 2026.
Loading poll...
Loading reviews…
Only members can review this page. Sign in
OpenRouter routes more than 600 models through one API key.
Claude Haiku 4.5 is Anthropic's small, fast model from late 2025, still available but now legacy, so it suits only pipelines already built around it.
Anthropic, 200K context, $1 in / 1M
Claude Opus 4.7 is Anthropic's April 2026 top-tier model for long-running agents, and it is now a legacy model: Anthropic points users to Opus 5.5.
Anthropic, 1M context, $5 in / 1M
Claude Sonnet 4.6 is Anthropic's mid-priced model for everyday coding and agent work, and it is now a legacy model, so new projects should look at Sonnet 5.5 first.
Anthropic, 1M context, $3 in / 1M
Claude Opus 4.8 is the older Opus that many agent setups still run on, and it suits teams that have not yet moved to the 5 series.
Anthropic, 1M context, $5 in / 1M
Claude Opus 5 is Anthropic's former flagship for long coding and agent work, and it suits teams that already pinned it and want steady behaviour.
Anthropic, 1M context, $5 in / 1M