# Claude Opus 5.5 API — pricing & specs

Claude Opus 5.5 is an Anthropic text and image model with always-on adaptive thinking and effort controls. On KeepRouter, Claude Opus 5.5 costs $8.00 per 1M input tokens and $20.00 per 1M output tokens, billed pay-as-you-go with no monthly fee; actual request cost depends on measured token usage. Call it through a compatible KeepRouter endpoint supported by its active route, with the model id `claude-opus-5-5`.

| Spec | Value |
|---|---|
| Maker | Anthropic |
| Modality | Text, vision |
| Context window | 1,000,000 tokens |
| Max output | 128,000 tokens |
| Knowledge cutoff | 2026-06 |
| Input price | $8.00 per 1M tokens |
| Output price | $20.00 per 1M tokens |
| Cached input | $0.2000 per 1M tokens |
| Capabilities | Vision (image input), Chat completions, Streaming where supported, Tool calling where supported |
| Endpoint | POST /v1/messages or POST /v1/chat/completions |
| Model id | `claude-opus-5-5` |

## Call it via /v1/messages

Use POST /v1/chat/completions or, on compatible chat routes, POST /v1/messages; streaming and tool support depend on the model's active route.

### cURL

```bash
curl https://keeprouter.com/v1/messages \
  -H "x-api-key: $KEEPROUTER_KEY" -H "anthropic-version: 2023-06-01" -H "Content-Type: application/json" \
  -d '{"model":"claude-opus-5-5","messages":[{"role":"user","content":"Reply with one short greeting."}],"max_tokens":1024,"output_config":{"effort":"low"}}'
```

### Python

```python
import os
from anthropic import Anthropic
client = Anthropic(base_url="https://keeprouter.com", api_key=os.environ["KEEPROUTER_KEY"], max_retries=0)
r = client.messages.create(model="claude-opus-5-5", messages=[{"role": "user", "content": "Reply with one short greeting."}], max_tokens=1024, output_config={"effort": "low"})
```

### JavaScript

```js
const res = await fetch("https://keeprouter.com/v1/messages", {
  method: "POST",
  headers: { "x-api-key": process.env.KEEPROUTER_KEY, "anthropic-version": "2023-06-01", "Content-Type": "application/json" },
  body: JSON.stringify({"model":"claude-opus-5-5","messages":[{"role":"user","content":"Reply with one short greeting."}],"max_tokens":1024,"output_config":{"effort":"low"}}),
});
```

## Estimate API costs

At the current KeepRouter customer price, an example workload of 1,000 total input tokens, no cached input, and 500 output tokens per request costs approximately $0.0180 per request. At 100 requests per day, that is $54.00 over 30 days. This is a usage estimate, excluding processing fees, taxes, retries and application infrastructure. Actual usage, cache hits and supported generation durations need their own checks.

[Adjust quantities in the API cost calculator](/tools/api-cost-calculator?model=claude-opus-5-5).

## Model identity and official sources

Sources checked 2026-10-03.

### Bounded generation checked

On October 3, 2026, this exact ID returned HTTP 200, visible text and final token usage through /v1/messages. These small checks do not establish task accuracy, full-context capacity, media compatibility or sustained throughput.

[KeepRouter · API reference](https://keeprouter.com/api/docs)

### Model and evaluation task

Claude Opus 5.5 supports a one-million-token context and up to 128,000 output tokens. Evaluate it on coding or document workflows that require preserved conversation state; do not assume an older Claude request can be copied unchanged.

[Anthropic · model documentation](https://platform.claude.com/docs/en/models/opus-5-5/overview)

### API contract and migration

Preserve complete thinking and tool blocks between turns. Forced tool choice is restricted when adaptive thinking is enabled. Non-default temperature, top_p and top_k are not supported by these 5.5 models.

[Anthropic · model documentation](https://platform.claude.com/docs/en/models/opus-5-5/overview)

### Customer price and verification scope

The live prices above are KeepRouter customer rates. One fixed input rate covers ordinary input and the supported cache-write or long-context ceiling; no extra cache-write fee is added. Cache hits use the separate cached-input rate. These are not the maker's short-context base prices. Maker specifications and catalog checks do not certify every generation workflow.

[KeepRouter · pricing and usage](https://keeprouter.com/models) · [KeepRouter · workload calculator](https://keeprouter.com/tools/api-cost-calculator)

## How to evaluate Claude Opus 5.5

Claude Opus 5.5 is listed on KeepRouter as text, vision under the exact id `claude-opus-5-5`. Use /v1/messages for the listed route; a maker's upstream features do not automatically apply to this gateway endpoint. The published context window is 1,000,000 tokens and the published output limit is 128,000 tokens. These are limits, not a recommended request size.

**First workload:** Start with a text question plus one representative image, then repeat the same question with text only. Compare answer quality, latency and billed input/output tokens.

**Before production:** For agent use, test tool calls and structured output on this exact model route before production; an OpenAI-compatible chat endpoint alone does not prove either feature.

### Agent setup paths

### Anthropic SDK (Messages)

Use the SDK's messages.create operation with the exact model `claude-opus-5-5`. In an agent product, select an adapter that emits /v1/messages; a Chat Completions configuration is not an equivalent tool integration. Preserve complete returned conversation items between tool turns. [Official setup](https://platform.claude.com/docs/en/models/opus-5-5/overview).

```python
import os
from anthropic import Anthropic
client = Anthropic(base_url="https://keeprouter.com", api_key=os.environ["KEEPROUTER_KEY"], max_retries=0)
r = client.messages.create(model="claude-opus-5-5", messages=[{"role": "user", "content": "Reply with one short greeting."}], max_tokens=1024, output_config={"effort": "low"})
```


These are documented configuration paths; model-specific tool, streaming and multimodal behavior still needs a real request test.

## Public model usage evidence

No public, exact-variant usage figure has been verified for this KeepRouter model id. Missing data is not zero usage; family-level or maker-wide traffic is not presented as this model's traffic.

## Published examples and cases

No exact-model customer case has been verified for this entry. The workload above is an evaluation recipe, not a claim of a public deployment.

## Source and verification boundary

[Official Claude Opus 5.5 documentation](https://platform.claude.com/docs/en/models/opus-5-5/overview). KeepRouter's live catalog is authoritative for the customer price and enabled endpoint shown here; the maker remains authoritative for upstream model capabilities and limits.

## Pricing and implementation guides

- [Claude 5.5: thinking, tool history and cache costs](https://keeprouter.com/blog/claude-sonnet-opus-5-5-api-migration)
- [Claude API cost and prompt caching](https://keeprouter.com/blog/claude-api-cost-prompt-caching)
- [Calculate your API workload cost](https://keeprouter.com/tools/api-cost-calculator)
- [KeepRouter API keys: move from free to paid models](https://keeprouter.com/blog/keeprouter-api-key-free-to-paid)

## Guides

- [Call Claude Opus 5.5 with the OpenAI SDK](https://keeprouter.com/use-cases/openai-sdk.md)
- [Claude Code gateway setup and support boundaries](https://keeprouter.com/use-cases/claude-code.md)

## Related models

- [Claude Sonnet 4.6](https://keeprouter.com/models/claude-sonnet-4-6.md) by Anthropic — $3.00 per 1M input tokens and $15.00 per 1M output tokens
- [Claude Opus 4.8](https://keeprouter.com/models/claude-opus-4-8.md) by Anthropic — $5.00 per 1M input tokens and $25.00 per 1M output tokens
- [Claude Sonnet 5.5](https://keeprouter.com/models/claude-sonnet-5-5.md) by Anthropic — $4.00 per 1M input tokens and $10.00 per 1M output tokens
- [Claude Opus 4.7](https://keeprouter.com/models/claude-opus-4-7.md) by Anthropic — $5.00 per 1M input tokens and $25.00 per 1M output tokens
- [Claude Fable 5](https://keeprouter.com/models/claude-fable-5.md) by Anthropic — $10.00 per 1M input tokens and $50.00 per 1M output tokens
- [Claude Opus 4.6](https://keeprouter.com/models/claude-opus-4-6.md) by Anthropic — $5.00 per 1M input tokens and $25.00 per 1M output tokens

## More

- [All models & pricing](https://keeprouter.com/models.md)
- [Quickstart](https://keeprouter.com/docs/quickstart.md)
- [Get an API key](https://keeprouter.com/login?returnTo=%2Fconsole%2Fkeys%3Fmodel%3Dclaude-opus-5-5)

_Catalog facts and prices last changed 2026-10-03._
_Page content reviewed 2026-10-03._