Skip to content

AnthropicLLM

Claude Opus 5.5 API

Model IDanthropic/claude-opus-5.5

Claude Opus 5.5 for long-context and tool-using workflows.

  • 1M context
  • Tools
  • Vision
  • Reasoning
  • JSON

Run Claude Opus 5.5 in the playground

Send a chat request with your account and see the exact token charge. Code needs an API key.

Parameters

Model
model
anthropic/claude-opus-5.5
messages[].content
messages[0].content
max_tokens
temperature

Request preview

{"model": "anthropic/claude-opus-5.5","messages": [],"stream": true,"max_tokens": 1024}

The web playground sends this body with your signed-in session. From code, send the same body with an API key.

Result

Send a message to run Claude Opus 5.5 with your account.

Usage and charge appear here after a reply.

Claude Opus 5.5 pricing

USD per 1M tokens. The tier is chosen by the prompt size of each request.

Loading price…
  1. ReserveWhen a request is accepted, Hermes reserves credits for the estimated prompt plus max_tokens of output (8,192 when you set none). Set max_tokens to keep the reservation small.
  2. SettleWhen the response finishes, the reservation is replaced by the exact charge from the usage the model reports: prompt tokens at the input rate, cached prompt tokens at the cache-read rate, completion tokens at the output rate. The remainder is released immediately.
  3. FailuresIf the model rejects the request nothing is charged. If a stream is interrupted after tokens were generated, the generated text is estimated and charged.

What Claude Opus 5.5 can do

Anthropic positions Opus 5.5 for long-running agentic coding and knowledge work, including large refactors and vision-heavy tasks. See Anthropic's model page for its native platform's specifications, limitations and migration information. Anthropic's hosted agents and native API controls are separate from the Hermes chat route.

Hermes lists anthropic/claude-opus-5.5 with a 1,000,000-token context, vision, reasoning, tools and streaming. Structured output is listed in the current Hermes catalog. Check the model's current status and token pricing before making a request.

Use cases

  1. Analyze long materials

    Work with documents or code while leaving space for the response.

  2. Build tool-using workflows

    Process function calls and validate the resulting actions in your application.

  3. Review visual information

    Combine supported image input with written instructions.

Call Claude Opus 5.5 from code

Any OpenAI SDK works: set the base URL and your Hermes key.

  1. 1

    Create an API key

    In the dashboard, with the chat:create scope. API keys
  2. 2

    Point your SDK at Hermes

    Base URL https://api.hermes-ai.net/api/v1
  3. 3

    Send a chat completion

    POST /chat/completions with anthropic/claude-opus-5.5

Code examples

Set HERMES_API_KEY in your environment.

shell
export HERMES_API_KEY=your_api_key
Full chat API reference
curl https://api.hermes-ai.net/api/v1/chat/completions \
  -H "Authorization: Bearer $HERMES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-5.5",
    "messages": [{"role": "user", "content": "Say hello in one sentence."}],
    "max_tokens": 200
  }'

Request

POST https://api.hermes-ai.net/api/v1/chat/completions API key with the chat:create scope, or your signed-in session.

FieldTypeNotes
modelstringanthropic/claude-opus-5.5
messagesarrayOpenAI chat messages: system, user, assistant and tool roles; text and image_url parts.
streambooleanServer-sent events with a final usage chunk.
max_tokensintegerOutput cap; also sizes the credit reservation.
tools / tool_choicearray / objectFunction tools only.
response_formatobjectJSON mode and JSON schema where the model supports it.
temperature, top_p, stop, seed, reasoning_effortPassed through unchanged.

Response

FieldNotes
choices[].message / deltaThe OpenAI chat completion shape.
usageprompt_tokens, completion_tokens and prompt_tokens_details.cached_tokens as reported by the model.
hermes.charged_microsExact charge in USD micro-units (JSON responses). Streams expose it on GET /api/v1/chat/requests.
x-hermes-requestRequest id header, also used in the billing ledger.
error.codeDocumented Hermes error code; branch on it, not on the message.

Claude Opus 5.5 API FAQ

Answers built from the model's catalog entry and the Hermes AI API contract.

Are Anthropic's native tools included in Hermes chat?

Not automatically. Anthropic's product documentation describes its native platform; use the Hermes API contract and validate the behavior of the selected route.

What is the Claude Opus 5.5 API on Hermes AI?

Claude Opus 5.5 by Anthropic is served through the OpenAI-compatible chat completions endpoint, https://api.hermes-ai.net/api/v1/chat/completions, with the model ID anthropic/claude-opus-5.5.

What is the context window of Claude Opus 5.5?

1,000,000 tokens, shared by the prompt and the output.

Does Claude Opus 5.5 support vision, tools and JSON output?

Supported: Tools, Vision, Reasoning and JSON. Not supported: Audio. Streaming works with stream: true.

How is Claude Opus 5.5 billed?

Per token, from prepaid credits. When a request is accepted, credits are reserved for the estimated prompt plus max_tokens of output (8,192 when you set none); when it finishes, the exact charge is taken from the usage the model reports and the rest is released. A rejected request is not charged. Rates are in the pricing table.

Can I use the OpenAI SDK with Claude Opus 5.5?

Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send anthropic/claude-opus-5.5 as the model. Chat completions, streaming, tools and JSON output work unchanged.

What happens when I hit a rate limit?

Too many requests per minute return 429 RATE_LIMITED and too many in flight return 429 CONCURRENCY_LIMITED. If the model provider rate limits, you get 429 UPSTREAM_RATE_LIMITED and nothing is charged. Retry with backoff.

How do I get an API key for Claude Opus 5.5?

Create one under API keys in the dashboard with the chat:create scope, then add credits on the Billing page.