DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
claude-opus-5-5opus alias now selects it. Opus 5 keeps its price for history and still runs on your own Claude subscription, but Continuum inference no longer serves it.The API id is claude-opus-5-5 on the Claude API, Google Cloud, Microsoft Foundry, and Claude Platform on AWS; Amazon Bedrock uses anthropic.claude-opus-5-5. Continuum uses the bare id at the gateway and continuum/claude-opus-5-5 in cross-provider pickers.
Adaptive thinking is always on and cannot be disabled. Effort levels are low, medium, high, xhigh, and max; the API default is medium. The input context is 1,000,000 tokens, maximum output is 128,000 tokens, and the knowledge cutoff is June 2026. Input is text and images; output is text.
Anthropic positions it for long-running agentic coding and knowledge work, and its models overview now says to start with Opus 5.5 for most workloads.
Use Opus 5.5 as the Opus pick for new sessions: long coding runs, multi-step agent work, and reviews where Sonnet 5 falls short but Fable 5.1 would be more than the task needs.
Choose it instead of Opus 5 for every new session. The old id remains only so historic analytics and already-running hosted work continue to price correctly.
No independent board lists this exact SKU as of 2026-08-19.
Closest benchmarked sibling: Claude Opus 5, 74% ±4% Pass@1 at max on the DeepSWE official board. That is a score for the sibling, not for this SKU.
Boards checked: DeepSWE official (2026-08-13), Artificial Analysis Intelligence Index, vals.ai hero index. Every card that does carry a row is on the coding leaderboard.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
No Intelligence Index integer fetched for this identity. Chip omitted.
We did not open a vals.ai card for this identity. Chip omitted.
computer_20251124 computer use tool is not accepted.Get Plus to use the Continuum-hosted Opus 5.5 rail. Not a Mac download.
Anthropic does not publish Opus 5.5 weights. There is no official Hugging Face repo and no Files button on this page. Get Plus buys hosted inference, not a local checkpoint.
tool_choice values (any or a named tool) return a 400. Automatic tool selection remains available.Lab card and OpenRouter listing only. No Hugging Face Files button, because there is no official repo to point at.
Fetched OpenRouter catalog on 2026-08-19. hugging_face_id was empty.
Continuum hosts the bare gateway id claude-opus-5-5. Native Claude sessions use the same bare id on the user’s Anthropic subscription, and OpenRouter BYOK uses anthropic/claude-opus-5.5 at the same rates.
The previous claude-opus-5 row is absent from new-session menus and was retired from Continuum inference on 22 Sep 2026. Its pricing stays for history.
claude-opus-5-5
click to select
We list first-party and OpenRouter, plus Continuum only when the live public allowlist named the id. This is not a 15-host routing table.
Official pricing per million tokens: $4 input, $20 output, $0.20 cache read, $5 five-minute cache write, and $8 one-hour cache write.
Cache reads are 0.05x input rather than the 0.1x most Claude models use. There is no long-context tier: the full 1M window bills at the standard rate.
On a Claude plan? The plan picker models the weekly caps.
| Claim | Source | As of |
|---|---|---|
| API ids, context, output ceiling, adaptive thinking, default effort, knowledge cutoff, modalities, breaking changes vs Opus 5 | Anthropic Opus 5.5 overview | 2026-09-22 |
| $4 input / $20 output / $5 5m write / $8 1h write / $0.20 cache read; no long-context tier | Anthropic pricing | 2026-09-22 |
| No base OpenRouter slug on the 2026-08-19 catalog; Hugging Face unlisted | OpenRouter /api/v1/models | 2026-08-19 |
Same official DeepSWE harness (mini-swe-agent, public 113 tasks), fetched 2026-08-19. Different effort labels are the lab's own setting on that board, shown here rather than normalized.
Continue through Anthropic's model family with Claude Sonnet 5.5.
Yes for new sessions, on every lane Continuum offers. Opus 5 is delisted from pickers and retired from Continuum inference; its rate stays so historic usage still prices correctly, and it still runs on your own Claude subscription.
No. Adaptive thinking is always on. Use the effort setting to trade depth for speed and cost; medium is the API default.
No. Forced tool choice returns an error. Leave selection on automatic. Continuum drops forced choices before forwarding the request.
Lab posts pick a harness, an effort, a split, and sometimes a private eval set. DeepSWE publishes the official mini-swe-agent row with cost, tokens, and steps. Scale SWE-bench Pro only counts when the public shared-harness board has a row we can fetch. A higher lab number is usually a different test, not a better one.
Verified against the live public allowlist on 2026-08-19. Base URL is https://continuumcode.ai/v1. Keys are cont_sk_ from Settings, Account, Inference API. Personal keys need Plus or above.
curl https://continuumcode.ai/v1/chat/completions \
-H "Authorization: Bearer $CONTINUUM_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-opus-5-5","messages":[{"role":"user","content":"Review this diff."}]}'