Claude Opus 5.5 API: $4/$20 Pricing and Setup
Claude Opus 5.5 is $4/$20 per 1M tokens. API id claude-opus-5-5, released 22 Sep 2026. Live on RouterPlex at list price, 0% markup.
Model releases·Published ·Checked ·By RouterPlex·6 min
claude-opus-5-5 is live on RouterPlex at vendor list price, 0% markup, $0 top-up fee.

On this page
Claude Opus 5.5 is Anthropic's Opus-tier model released 22 September 2026. The API id is claude-opus-5-5. Claude Opus 5.5 API pricing is $4 per 1M input tokens and $20 per 1M output tokens, with cache reads at $0.20 per 1M.
Opus 5.5 is listed on RouterPlex as claude-opus-5-5 at $4 / $20: vendor list price, 0% markup, $0 top-up fee, prepaid balance, hard spend limit. Create a RouterPlex account and the same key reaches Claude Opus 5 at $5 / $25, Claude Fable 5 at $10 / $50, and the rest of the 60+ models.

Sources: Anthropic's Claude Opus 5.5 announcement (22 September 2026), the Opus 5.5 overview, and the system card, checked 28 September 2026. Scores below are the publisher named in each row. They are not RouterPlex measurements.
Claude Opus 5.5 API pricing
USD per 1M tokens. The announcement's cache-write cell of $5 is the 5-minute rate. The overview also lists a 1-hour cache write at $8.
| Line | Opus 5.5 | Opus 5, Anthropic sheet |
|---|---|---|
| Input | $4.00 | $5.00 |
| Output | $20.00 | $25.00 |
| Cache read | $0.20 | $0.50 |
| 5-minute cache write | $5.00 | $6.25 |
| 1-hour cache write | $8.00 |
A 40,000-in / 2,000-out turn with no cache is $0.20 on the Opus 5.5 sheet ($0.16 input + $0.04 output). The same shape on live RouterPlex claude-opus-5 at $5 / $25 is $0.25.
Anthropic's batch discount is 50% off input and output on the Anthropic platform. The minimum cacheable prompt is 512 tokens. Fast mode, in Claude Code and the Claude Platform, is up to 2.5x speed at $8 / $40 per 1M. Anthropic calls that a research preview on the Claude API. It is not a RouterPlex rate, and it is not something a third-party gateway bills unless that gateway lists the SKU.
Anthropic's own cost claim: about 40% less than Opus 5 on typical workloads at default settings, from token rates that are 20% lower plus fewer tokens, and cache reads 60% lower ($0.20 vs $0.50). Output is more than 30% faster than Opus 5. Those are vendor tests.
Specs and breaking changes
| Claude Opus 5.5 | |
|---|---|
| Claude API id | claude-opus-5-5 |
| Bedrock id | anthropic.claude-opus-5-5 |
| Released | 22 September 2026 |
| Context / max output | 1M / 128K |
| Batch beta output | 300K with output-300k-2026-03-24 |
| Latency | Moderate |
| Thinking | Adaptive, always on. Cannot be disabled |
| Default effort | medium |
| Knowledge cutoff | June 2026 |
| Retirement | Not sooner than 22 September 2027 |
| On RouterPlex | claude-opus-5-5, $4 / $20 |
Four breaks versus Opus 5, from the overview. Thinking cannot be disabled. Forced tool use returns an error. Thinking blocks are tied to the model and the conversation. On the Claude API and Google Cloud, computer_20251124 is not accepted. The first three also apply on Fable 5.1. Text between tool calls comes back in thinking blocks whose text is empty at the default display setting.
Sonnet 5.5, at $2 / $10, shipped on 28 September 2026 as the everyday companion. Haiku 5.5 shipped on 7 October 2026 at $0.10 / $0.50 per 1M for prompts up to 100,000 tokens, and $0.50 / $2.50 when the prompt is over that line. The 22 September Opus page had only said it was coming. Haiku 5.5 is not listed on this marketplace.
Vendor benchmarks
Unless noted, Anthropic reports adaptive thinking at max effort. Terminal-Bench 4.0 is Opus 5.5 at xhigh and GPT-6 Astra at high. Safeguards were on: cyber tasks fell back to Opus 4.8, and biology or frontier-LLM tasks fell back to Opus 5, which Anthropic says likely lowers these scores.
| Benchmark | Opus 5.5 | Fable 5.1 | Opus 5 | GPT-6 Astra | GPT-5.6 Sol |
|---|---|---|---|---|---|
| Terminal-Bench 4.0 | 66.4% | 55.8% | 52.3% | 57.9% | 37.3% |
| FrontierCode v1.1 Main | 54.4 | 50.3 | 48.0 | 53.3 | 47.5 |
| CursorBench 4.0 | 57.8 | 51.8 | 46.6 | 41.7 | |
| GDPval-AA v2.1 | 1846 | 1735 | 1708 | 1542 | 1588 |
| AutomationBench | 40.0% | 31.4% | 26.9% | 41.4% | 28.8% |
| HLE, with tools | 67.7% | 65.6% | 63.6% | 57.2% | |
| Terminal-Bench-Science 0.1 | 58.7 | 52.6 | 29.0 | 64.6 | 22.4 |
| OSWorld 2.1, partial | 81.8 | 80.7 | 74.0 | ||
| Chartography, with tools | 89.0 | 88.4 | 83.4 |
Terminal-Bench 4.0 standard error is ±2.6 points for Opus 5.5. The public leaderboard lists Opus 5 at 51.8%. Anthropic's setup reproduced 52.3%. AutomationBench was run by Zapier without fallback models, so safeguard hits counted as failures. Terminal-Bench-Science standard error is ±3.5 to 5 points.
More vendor claims from the same announcement, each one Anthropic's or the named customer's: a 680,000-line migration in under a day. A load-time test at 39 of 40 pages. A 200,000-line audit in under 3 hours, where Opus 5 took over 20 hours and 2.5x the tokens. An internal HAProxy C-to-Rust port in 9.5 hours versus 12 hours for Fable 5.1, at 51% less cost. An earnings-research test where 16 of 18 Opus 5.5 reports cleared the bar. A fictional merger model in 63 minutes versus 93 for Opus 5, at 50% less cost. At default effort on FrontierCode, Anthropic says it beats GPT-6 Astra at roughly 20% of the cost per task. The announcement gives that as a ratio, not a dollar figure.
Mario Rodriguez, GitHub's Chief Product Officer, said Opus 5.5 used among the fewest tokens and steps in Copilot CLI and VS Code, and in VS Code solved more terminal tasks than Opus 5 in less than half the steps. Carl Bennett, CIO at Deloitte Consulting LLP, cited 72% of known bugs caught at the lowest effort setting versus 56% for Opus 5 at high effort. Gray Swan, named by Anthropic, tied Opus 5.5 with Fable 5.1 for the lowest prompt-injection success rate in that firm's test. Frontier Design and METR are named as evaluators on the system card.
Call Opus 5.5 on RouterPlex
claude-opus-5-5 bills $4 / $20 per 1M. Cache writes bill at the $4 input rate, below Anthropic's $5 five-minute write. Cache reads are $0.425 per 1M, above Anthropic's $0.20, because RouterPlex prices cache reads from what its upstream charges, the same rate as claude-opus-5. Fast mode is first-party only and is not this gateway's SKU.
curl https://api.routerplex.com/v1/chat/completions \-H "Authorization: Bearer $ROUTERPLEX_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "claude-opus-5-5","messages": [{"role": "user", "content": "List the three risks in moving this service from Opus 5 to Opus 5.5."}]}'
The Anthropic Messages endpoint works too, so Claude Code can use it directly:
export ANTHROPIC_BASE_URL=https://api.routerplex.comexport ANTHROPIC_AUTH_TOKEN=$ROUTERPLEX_API_KEYclaude --model claude-opus-5-5
Same key, OpenAI-compatible endpoint, full catalog. If Opus 5.5 is unavailable upstream, requests fall back to claude-opus-5 and then claude-opus-4-8, billed at the model that answered.
Common questions
Frequently asked questions
How much does the Claude Opus 5.5 API cost?
Anthropic lists Claude Opus 5.5 at $4 per 1M input tokens and $20 per 1M output tokens. Cache reads are $0.20 per 1M. A 5-minute cache write is $5 per 1M and a 1-hour cache write is $8 per 1M. On RouterPlex, claude-opus-5-5 bills $4/$20, cache writes at $4 per 1M (the input rate) and cache reads at $0.425 per 1M.
What is the Claude Opus 5.5 model ID?
claude-opus-5-5 on the Claude API, Vertex AI, Microsoft Foundry, and Claude Platform on AWS. Amazon Bedrock uses anthropic.claude-opus-5-5. The RouterPlex id is the same: claude-opus-5-5.
Is Claude Opus 5.5 on RouterPlex?
Yes, since 5 October 2026, as claude-opus-5-5 on both the OpenAI-compatible /v1/chat/completions endpoint and the Anthropic /v1/messages endpoint. It works with Claude Code by pointing ANTHROPIC_BASE_URL at RouterPlex.
What is Opus 5.5 fast mode pricing?
Anthropic's fast mode in Claude Code and the Claude Platform is up to 2.5x speed at $8 input and $40 output per 1M tokens. Anthropic labels it a research preview on the Claude API. That is not a RouterPlex price.
Can I disable thinking on Opus 5.5?
No. Adaptive thinking is always on. Control depth with the effort parameter. The default effort is medium. Forced tool use returns an error. Thinking blocks are tied to the model and the conversation.
How does Opus 5.5 compare with Opus 5 and Fable 5 on price?
Opus 5.5's vendor sticker is $4/$20, and RouterPlex bills claude-opus-5-5 at the same $4/$20. RouterPlex bills claude-opus-5 at $5/$25 and claude-fable-5 at $10/$50. Anthropic says Opus 5.5 performs at the level of Claude Fable 5.1 on most work. Fable 5.1's own platform price on the Sonnet 5.5 overview table is $10/$50.
Run the smallest paid test.
Add $5, cap the key, and verify the result with your own workload. No subscription, and credit never expires — a first top-up of $25+ is matched with $25 extra.



