Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
Home / Reference / Models

claude-sonnet-5

model never mined JSON

A Claude Code model, read out of the shipped bundle. No mined inventory carries it: everything below comes from what this site has written about it.

Sonnet 5's default context window is now a full million tokens, up from 967,000.

Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.247.

First seen — never in a mined build
Last seen — never in a mined build
Builds0 / 149on this box, as of v2.1.308
Written about v2.1.197 first named in a changelog, 30 Jun 2026

In the changelogs

19

Releases whose published page names claude-sonnet-5.

  1. v2.1.290
    /code-review medium now runs the high-effort recipe on most models

    On every model without its own /code-review row, Opus 5.5 included, medium now runs the eight-angle high recipe instead of a single pass. high, xhigh and Opus 5 are unchanged.

    found in this entry's text

  2. v2.1.287
    Sonnet model entries no longer mark Bedrock, Vertex and Foundry as natively 1M

    Two Sonnet model entries no longer flag Bedrock, Vertex and Foundry as supporting the 1M-token context window natively

    found in this entry's text

  3. v2.1.285
    Effort picker shows high as Recommended, and claude-sonnet-5 is listed with high effort

    The high effort option is now labelled Recommended instead of Default, and the model list includes claude-sonnet-5 set to high effort

    found in this entry's text, named in this entry

  4. v2.1.285
    Model picker updates: Sonnet 5 thinking default, new Opus 5.5 wording, Recommended badge

    claude-sonnet-5 now defaults to high effort with automatic thinking, Opus 5.5 has new wording, and the High effort badge says Recommended

    found in this entry's text

  5. v2.1.285
    Effort choices are labelled Recommended, and one model defaults to medium effort

    The effort picker labels medium and high as Recommended instead of Default, and one model's default effort drops from high to medium

    found in this entry's text

  6. v2.1.284
    Sonnet 5.5 added and made the default for the sonnet model name

    Sonnet 5.5 (claude-sonnet-5-5) is now in the model list and is what sonnet picks when using Anthropic directly

    found in this entry's text

  7. v2.1.284
    The sonnet model name now points to Sonnet 5.5 on the Anthropic API

    Choosing sonnet now selects Sonnet 5.5 instead of Sonnet 5 on the Anthropic API, while Bedrock, Vertex and other providers keep older models

    found in this entry's text

  8. v2.1.284
    Claude Code's built-in model list now points to Opus 5.5 and Sonnet 5.5

    Claude Code's built-in current models are now claude-opus-5-5 and claude-sonnet-5-5, with claude-opus-5 and claude-sonnet-5 as the previous ones

    found in this entry's text

  9. v2.1.284
    Refused requests on Sonnet 5.5 now fall back to Sonnet 5

    When a Sonnet 5.5 request is refused as cyber or frontier_llm, Claude Code now falls back to claude-sonnet-5 instead of an Opus model

    found in this entry's text

  10. v2.1.282
    Opus 5 moved to the overflow section of the built-in model list

    In the built-in model list, Opus 5 moves to the overflow section and loses its quick-select flag and description

    found in this entry's text

  11. v2.1.282
    Routine-scheduling example uses the current Sonnet model instead of a fixed one

    The example in the routine-scheduling skill now fills in whatever model "sonnet" currently points to rather than always naming claude-sonnet-5

    found in this entry's text

  12. v2.1.277
    Model catalog version bump and per-surface model reassignment

    Bundled model catalog updated to version 629 with model reassignments across ccr, ccd, and other surfaces

    found in this entry's text, named in this entry

  13. v2.1.257
    Compiled seed catalog includes Opus 5 / Sonnet 5 placeholders

    The compiled-in seed catalog used before the first fetch lists claude-opus-5, claude-sonnet-5 and claude-haiku-4-5.

    found in this entry's text, named in this entry

  14. v2.1.248
    Per-surface context limits for claude-sonnet-5

    Context limits for claude-sonnet-5 are 500,000 on two surfaces and a million elsewhere.

    found in this entry's text

  15. v2.1.247
    Sonnet 5 default context window raised to 1,000,000 tokens

    Sonnet 5's default context window is now a full million tokens, up from 967,000.

    named in this entry, found in this entry's text

  16. v2.1.201
  17. v2.1.197
    Claude Sonnet 5 Is Now the Default Model

    found in this entry's text

  18. v2.1.197
  19. v2.1.197

First cited

5

The earliest release whose published evidence quoted claude-sonnet-5 was v2.1.197, 30 Jun 2026. That is the oldest release this project wrote about it, so it is a floor on the name's age and not the release that introduced it. It is not a presence reading: which builds carried the name is the table below.

ReleaseDateThe span that was quoted
v2.1.19730 Jun 2026claude-sonnet-5
v2.1.19730 Jun 2026claude-sonnet-5" / "claude-opus-4-8
v2.1.24726 Aug 2026"claude-sonnet-5"
v2.1.28428 Sep 2026$2 = { cyber: "claude-sonnet-5", frontier_llm: "claude-sonnet-5" }
v2.1.28529 Sep 2026id: "claude-sonnet-5"

Presence across releases

0

The miner has never read a build containing this name. It is here because a changelog entry of ours names it, which is evidence that it existed and not evidence of which releases carried it. The inventory starts at v2.1.138 and everything older than that was never mined.

Read out of the published npm bundle release by release, and out of Anthropic's own documentation as this site captured it. Nothing on this page is a description anybody here wrote about what the model does. All models.

Feedback