AnthropicLLM
Claude Haiku 4.5 API
anthropic/claude-haiku-4.5Claude Haiku 4.5 through the Hermes chat catalog.
- 200K context
- Tools
- JSON
- Saver channel
Run Claude Haiku 4.5 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-haiku-4.5","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 Haiku 4.5 with your account.
Usage and charge appear here after a reply.
Claude Haiku 4.5 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 Haiku 4.5 can do
Anthropic presents Haiku 4.5 as a smaller, fast model. See Anthropic's documentation for manufacturer details. Native Claude API features and lifecycle do not necessarily match this Hermes route.
The Hermes catalog lists anthropic/claude-haiku-4.5 with a 200,000-token context. Vision is not listed for this entry, even where Anthropic describes visual capabilities for its native model. Check the exact channel's tool and output flags, current availability and price before calling it.
Use cases
Work with text and code
Evaluate the model on representative tasks and reserve context for output.
Build an application workflow
Use documented request fields and validate results.
Compare options
Measure response quality, latency and cost for your workload.
Call Claude Haiku 4.5 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-haiku-4.5
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-haiku-4.5",
"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-haiku-4.5 |
| 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 Haiku 4.5 API FAQ
Answers built from the model's catalog entry and the Hermes AI API contract.
Are all native Claude features available on this channel?
Not necessarily. Anthropic describes its own platform. Use the exact Hermes entry's capability flags and API contract when selecting inputs and controls.
What is the Claude Haiku 4.5 API on Hermes AI?
Claude Haiku 4.5 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-haiku-4.5.
What is the context window of Claude Haiku 4.5?
200,000 tokens, shared by the prompt and the output.
Does Claude Haiku 4.5 support vision, tools and JSON output?
Supported: Tools and JSON. Not supported: Vision, Reasoning and Audio. Streaming works with stream: true.
How is Claude Haiku 4.5 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 Haiku 4.5?
Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send anthropic/claude-haiku-4.5 as the model. Chat completions, streaming, tools and JSON output work unchanged.
What is the Claude Haiku 4.5 saver channel?
The same model on a lower-priority upstream route, with its own model ID (anthropic/claude-haiku-4.5-saver) and its own price. Pick it in the variant switch on this page.
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 Haiku 4.5?
Create one under API keys in the dashboard with the chat:create scope, then add credits on the Billing page.