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

claude-opus-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.

Opus 5 is now the default Opus, with a 1M-context option in the model picker.

Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.219.

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 v2.1.219 first named in a changelog, 24 Jul 2026

In the changelogs

37

Releases whose published page names claude-opus-5.

  1. v2.1.304
    Bundled default model changes to Opus 5.5 at medium effort

    The model catalog shipped with Claude Code now defaults to claude-opus-5-5 at medium effort instead of claude-opus-5 at high effort

    found in this entry's text

  2. v2.1.302
    claude-opus-5 joins a model list used in a capability check

    Claude Code now lists claude-opus-5 alongside other models in a list that one of its checks looks at

    found in this entry's text

  3. 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

  4. 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

  5. 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

  6. v2.1.283
    Admins can block specific models and require exact version matches

    Managed settings gain deniedModels to block models and availableModelsMatch to stop an allowed ID covering later versions

    found in this entry's text

  7. v2.1.283
    Opus 5.5 can fall back to Opus 5 for one more refusal type

    When claude-opus-5-5 refuses a request in the frontier_llm category, Claude Code can now fall back to claude-opus-5

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

  8. 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, named in this entry

  9. v2.1.281
    Bundled model catalog adds claude-opus-5-5 ("Opus 5.5"), which replaces Opus 5 in the Opus picker slot

    Opus 5.5 (claude-opus-5-5) replaces Opus 5 in the model picker's Opus slot, with default effort "medium" on the cc surface

    found in this entry's text

  10. v2.1.281
    Bundled model catalog: 'Opus 5' quick-select entry is now 'Opus 5.5'

    In the bundled model catalog, the "Opus" quick-select entry now points to Opus 5.5 instead of Opus 5

    found in this entry's text

  11. v2.1.281
    Bundled model-preset config: chat preset thinking effort for claude-opus-5-5 set to medium

    A bundled model config now lists claude-opus-5-5 at medium thinking effort for the chat preset, alongside claude-opus-5 at high

    found in this entry's text

  12. v2.1.281
    Model selector config: always_on dropped, min version bumped to 2.1.280

    One model entry in the bundled model selector config drops always_on thinking and now requires Claude Code 2.1.280 or later

    found in this entry's text

  13. v2.1.281
    Bundled model-selector sample defaults Opus 5.5 to medium effort

    Built-in model data now sets Opus 5.5 to medium effort and marks Medium as Default for Opus 5.5 and Fable 5.1

    found in this entry's text

  14. v2.1.280
    Fast mode's default model resolution changed in prompt and code

    Fast mode's system-prompt wording and its default-model fallback in code both changed

    found in this entry's text

  15. v2.1.280
    Fast mode no longer restricted to Opus 5/4.8 in the system prompt

    The system prompt no longer says fast mode is limited to Opus 5/4.8, and now lists Opus 5.5 in the model catalog

    found in this entry's text

  16. v2.1.280
    Opus renamed to Opus 5.5 as the latest-per-family model

    Opus model catalog entry renamed from 'Opus 5' to 'Opus 5.5' as the latest in its family

    found in this entry's text

  17. v2.1.280
    New cheaper cost table for claude-opus-5-5

    A new, cheaper token-cost tier now applies to the claude-opus-5-5 model id

    found in this entry's text

  18. v2.1.280
    Safety-classification model routing table gains a 'frontier_llm' entry

    Safety-classification model routing gains a new 'frontier_llm' category mapped to claude-opus-5

    found in this entry's text

  19. 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

  20. v2.1.275
    Offline/fallback model catalog switches ccr/ccd default model from Sonnet 4.6 to claude-opus-5

    Fallback model list now defaults 'ccr' and 'ccd' to claude-opus-5 instead of Sonnet 4.6 when the live catalog is unreachable

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

  21. v2.1.267
    thinking_disabled_effort_cap follows the same gate-precedence rework

    The thinking_disabled_effort_cap flag can now override the claude-opus-5 hardcoded default in either direction

    found in this entry's text

  22. v2.1.263
    Effort-medium nudge generalized to multiple models and effort levels

    The effort-downgrade nudge now works per model instead of just one, but each model needs its own flag turned on.

    found in this entry's text

  23. v2.1.263
    Effort-medium nudge generalized to per-model remote-config gates

    The effort-downgrade nudge was rebuilt to support multiple models, each hidden behind its own remote switch.

    found in this entry's text

  24. 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

  25. v2.1.251
    Effort cap when thinking is off, tied to a specific model

    Some models cap reasoning effort when thinking is off, matched by name or capability.

    found in this entry's text

  26. v2.1.248
    Model tables extended to Opus 4.7, 4.8 and Opus 5

    Model tables now list claude-opus-4-7, claude-opus-4-8 and claude-opus-5.

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

  27. 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

  28. v2.1.246
    The claude-api skill's documents moved out of the bundle, unchanged

    The claude-api skill's documents moved to separate files with identical content and paths.

    found in this entry's text

  29. v2.1.223
    Thrifty-sonic narrowed to one model; plan artifacts moved to its own gate

    Plan artifacts now have their own switch instead of riding along with an unrelated experiment.

    found in this entry's text

  30. v2.1.220
    Opus 5 is skipped when the client cannot see model entitlements

    If your session has no model access info cached, Claude won't fall back to Opus 5.

    found in this entry's text

  31. v2.1.220
    Refusal fallback no longer picks Opus 5 when entitlements are unknown

    When a refusal triggers a model switch and entitlements are unknown, you get Opus 4.8 instead of Opus 5.

    found in this entry's text

  32. v2.1.219
    Opus 5 replaces Opus 4.8 as the default Opus model

    Opus 5 is now the default Opus, with a 1M-context option in the model picker.

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

  33. v2.1.219
    The API skill's model placeholders now resolve to Claude Opus 5, with the previous Opus kept as a separate placeholder

    The API skill's model placeholders now render Opus 5, keeping the previous Opus named separately.

    found in this entry's text

  34. v2.1.219
    Code-review prompt tuned for Opus 5

    Code reviews on Opus 5 use a tighter prompt: one diff pass, at most fifteen findings.

    found in this entry's text

  35. v2.1.219
    Model-downgrade chain and effort tables know about Opus 5

    Model fallbacks and reasoning-effort settings now handle Opus 5, stepping down to Opus 4.8 when needed.

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

  36. v2.1.219
    Opus 5 wired through region env vars, refusal fallbacks and pricing copy

    An Opus 5 model is wired through region variables, fast mode, 1M context and pricing text.

    found in this entry's text

  37. v2.1.219
    Effort profile added for claude-opus-5

    A reasoning-effort table now includes settings for a model named claude-opus-5, with new medium and high profiles.

    found in this entry's text

First cited

6

The earliest release whose published evidence quoted claude-opus-5 was v2.1.219, 24 Jul 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
v2.1.21924 Jul 2026OPUS_ID: "claude-opus-5"
v2.1.2636 Sep 2026"claude-opus-5": { flag: "tengu_radiant_island", from: ["high"] }
v2.1.2636 Sep 2026claude-opus-5": { flag: "tengu_radiant_island", from: ["high"] }
v2.1.28022 Sep 2026frontier_llm: "claude-opus-5",
v2.1.28123 Sep 2026id: "claude-opus-5",
v2.1.28325 Sep 2026frontier_llm: "claude-opus-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