AnthropicLLM
Claude Sonnet 5 API
anthropic/claude-sonnet-5Anthropic's Claude Sonnet 5 on the OpenAI-compatible chat completions API, with a 1,000,000 token context, vision, tools and reasoning.
- 1M context
- Tools
- Vision
- Reasoning
Run Claude Sonnet 5 in the playground
Send a chat request with your account and see the exact token charge. Code needs an API key.
Parameters
Request preview
{"model": "anthropic/claude-sonnet-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 Sonnet 5 with your account.
Usage and charge appear here after a reply.
Claude Sonnet 5 pricing
USD per 1M tokens. The tier is chosen by the prompt size of each request.
- 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.
- 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.
- 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 Sonnet 5 can do
Anthropic’s Claude Sonnet 5 model page describes this model as a previous-generation Sonnet with a 1M-token context and adaptive thinking. Its native Claude API features are not automatically equivalent to options supported by the Hermes OpenAI-compatible route.
Claude Sonnet 5 is called with the OpenAI chat completions format: send anthropic/claude-sonnet-5 as the model to the Hermes base URL with your API key. The catalog lists a context window of 1,000,000 tokens and support for tools, vision and reasoning; JSON schema output is not listed for this model.
Billing is per token from prepaid credits, with a separate cache-read rate for cached prompt tokens.
Use cases
Coding and review
Long files and diffs fit in the 1,000,000 token context.
Tool-using agents
Function tools pass through unchanged.
Reading images
Send screenshots or scans as image_url parts.
Call Claude Sonnet 5 from code
Any OpenAI SDK works: set the base URL and your Hermes key.
- 1
Create an API key
In the dashboard, with the chat:create scope. API keys - 2
Point your SDK at Hermes
Base URLhttps://api.hermes-ai.net/api/v1 - 3
Send a chat completion
POST /chat/completionswithanthropic/claude-sonnet-5
Code examples
Set HERMES_API_KEY in your environment.
export HERMES_API_KEY=your_api_keycurl https://api.hermes-ai.net/api/v1/chat/completions \
-H "Authorization: Bearer $HERMES_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-sonnet-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.
| Field | Type | Notes |
|---|---|---|
| model | string | anthropic/claude-sonnet-5 |
| messages | array | OpenAI chat messages: system, user, assistant and tool roles; text and image_url parts. |
| stream | boolean | Server-sent events with a final usage chunk. |
| max_tokens | integer | Output cap; also sizes the credit reservation. |
| tools / tool_choice | array / object | Function tools only. |
| response_format | object | JSON mode and JSON schema where the model supports it. |
| temperature, top_p, stop, seed, reasoning_effort | Passed through unchanged. |
Response
| Field | Notes |
|---|---|
| choices[].message / delta | The OpenAI chat completion shape. |
| usage | prompt_tokens, completion_tokens and prompt_tokens_details.cached_tokens as reported by the model. |
| hermes.charged_micros | Exact charge in USD micro-units (JSON responses). Streams expose it on GET /api/v1/chat/requests. |
| x-hermes-request | Request id header, also used in the billing ledger. |
| error.code | Documented Hermes error code; branch on it, not on the message. |
Claude Sonnet 5 API FAQ
Answers built from the model's catalog entry and the Hermes AI API contract.
Do I need the Anthropic SDK?
No. Hermes AI API serves Claude Sonnet 5 through the OpenAI-compatible endpoint, so the OpenAI SDK with the Hermes base URL works.
Does Claude Sonnet 5 support structured outputs?
The catalog does not list JSON schema output for this model. Ask for JSON in the prompt and validate it in your code.
What is the Claude Sonnet 5 API on Hermes AI?
Claude Sonnet 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-sonnet-5.
What is the context window of Claude Sonnet 5?
1,000,000 tokens, shared by the prompt and the output.
Does Claude Sonnet 5 support vision, tools and JSON output?
Supported: Tools, Vision and Reasoning. Not supported: JSON and Audio. Streaming works with stream: true.
How is Claude Sonnet 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 Sonnet 5?
Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send anthropic/claude-sonnet-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 Sonnet 5?
Create one under API keys in the dashboard with the chat:create scope, then add credits on the Billing page.