Chat ● Operational Service status →

Claude Opus 5.5

⧉

claude-opus-5-5

Claude Opus 5.5 is the newest model in Anthropic's Opus line and the successor to Claude Opus 5, built for long-horizon agentic coding and knowledge work: a 1M-token context window, up to 128K output tokens per request, and adaptive thinking that is always on. It supports image input, tool calling, prompt caching and streaming. KovAPI serves it through both the OpenAI-compatible API and the native Anthropic Messages API (/anthropic), so Claude Code connects directly; the five effort levels (low to max), thinking summaries, structured output and PDF input are available on the native API. Pay as you go; failed calls are never billed.

ChatCodeAgents1M contextNative Anthropic API

Get API Key → API Docs

Service Highlights

The newest model in Anthropic's Opus line, succeeding Opus 5
1M-token context, up to 128K output per request
Five effort levels (low to max) and thinking summaries on the native API
Image and PDF input, tool calling, prompt caching
Priced below Anthropic's list on both ends ($4 / $20)

Measured on real calls

Customer requests over the last 30 days

Success rate89.1%

Pricing

Input$2.5 / 1M tokens

Output$12.5 / 1M tokens

List price~~$4.0 / $20.0 / 1M~~

You save ↓38%

View detailed pricing

Why this model

Anthropic's next Opus · 1M context · adaptive thinking

Highlights

The newest model in Anthropic's Opus line, succeeding Opus 5
1M-token context, up to 128K output per request
Five effort levels (low to max) and thinking summaries on the native API
Image and PDF input, tool calling, prompt caching
Priced below Anthropic's list on both ends ($4 / $20)

Price vs. official list

KovAPIList price Input$2.5$4 Output$12.5~~$20~~

Per 1M tokens, USD · You save ↓38%

Live Test · Playground

Try out Claude Opus 5.5 right here (available after login).

Input

Model

Advanced

temperature 1.0 max_tokens 2048

Web search

Memory · multi-turn

Thinking

Conversation

Start a conversationType a message below to begin

About Claude Opus 5.5

Claude Opus 5.5 is the newest model in Anthropic's Opus line and the successor to Claude Opus 5, with the list price cut from $5 / $25 to $4 / $20 per million tokens. It is built for long-horizon agentic coding and knowledge work: a 1M-token context window, up to 128K output tokens per request, and thinking that is always on, with the model deciding how long each problem deserves. KovAPI offers two ways in. The OpenAI-compatible API: point base_url at KovAPI and set model to claude-opus-5-5, with no change to existing OpenAI SDK code. The native Anthropic Messages API: point ANTHROPIC_BASE_URL in Claude Code or any Anthropic SDK at KovAPI's /anthropic, where effort (output_config.effort), thinking summaries, structured output, PDF input and cache_control work as documented. Pay as you go; failed calls are never billed.

Use cases

Long-horizon agentic coding

Feature work, refactors and debugging across many files, with tool calls in long agent loops; raise the effort to high or max for the hard problems.

Large codebases and long documents

A 1M-token context holds an entire codebase or hundreds of pages at once; in our test a 217K-token input still surfaced the detail buried in the middle.

Claude Code, connected directly

Point ANTHROPIC_BASE_URL at KovAPI's /anthropic and use your gateway key as x-api-key to run Opus 5.5 in Claude Code.

Images and PDFs

Q&A over screenshots, charts, contracts and financial reports; send PDFs as document blocks on the native API.

How to choose

Choose Claude Opus 5.5 for the strongest reasoning, coding and long-horizon agent work; choose Claude Sonnet 5.5 for speed and cost on high-volume everyday tasks: it also has a 1M-token context, at half the price of Opus 5.5. Switching is just the model field.

FAQ

How is it different from Claude Opus 5?

Opus 5.5 is the newer model in the Opus line, listed by Anthropic 20% below Opus 5 ($4 / $20 against $5 / $25), with a 1M-token context and up to 128K output tokens per request. On KovAPI it is priced below the official list on both ends.

Can I set the effort? Does it return its thinking?

Yes. On the native API, set output_config.effort to low, medium, high, xhigh or max: higher means deeper, slower and more tokens. Add thinking: {"type": "adaptive", "display": "summarized"} and the response carries a summary of the thinking. Thinking tokens bill at the output rate. On the OpenAI-compatible API the model thinks at its default effort, reasoning_effort has no effect, and no thinking content is returned.

Which parameters work, and what are the limits?

messages, streaming, stop, tools and image input all work. Thinking cannot be turned off (thinking set to disabled is ignored); a forced tool choice (any, or a named tool) is treated as auto; temperature, top_p and top_k are ignored. For strict JSON output use output_config.format on the native API; response_format on the OpenAI-compatible API is not guaranteed to take effect.

How do I send images and PDFs?

Images work on both APIs: image_url on the OpenAI format, an image block on the native API, as base64 or a public link. Send PDFs as base64 document blocks on the native API.

Am I charged for failed calls?

No. Only calls that return normally are settled, at actual usage; upstream errors and timeouts never touch your balance.