Aller au contenu

AnthropicLLM

Claude Haiku 5.5 API

Model IDanthropic/claude-haiku-5.5

Claude Haiku 5.5 for high-volume text work, with the Hermes channel's own context and capability limits.

  • 200K context
  • Outils
  • JSON

Lancez Claude Haiku 5.5 dans le playground

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

Paramètres

Modèle
model
anthropic/claude-haiku-5.5
messages[].content
messages[0].content
max_tokens
temperature

Aperçu de la requête

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

Le playground web envoie ce corps avec votre session connectée. Depuis votre code, envoyez le même corps avec une clé d’API.

Résultat

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

Usage and charge appear here after a reply.

Tarifs de Claude Haiku 5.5

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

Chargement du prix…
  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.

Ce que Claude Haiku 5.5 sait faire

Anthropic positions Claude Haiku 5.5 for latency-sensitive classification, extraction, routing and agent subtasks. Anthropic's native platform describes adaptive thinking and a 1M-token context, but the Hermes catalog currently lists a 200,000-token context and does not list vision or reasoning support for this channel. Follow the Hermes limits rather than assuming all native features are available.

The Hermes model ID is anthropic/claude-haiku-5.5. The catalog lists tools, streaming and structured output. Check current availability and token pricing before making a request.

Cas d’usage

  1. Classify and route

    Sort text requests into categories for downstream workflows.

  2. Extract structured data

    Ask for a schema-constrained response and validate it in your application.

  3. Process batches of short tasks

    Evaluate latency, cost and quality against your workload.

Appelez Claude Haiku 5.5 depuis votre code

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

  1. 1

    Créez une clé d’API

    In the dashboard, with the chat:create scope. Clés d’API
  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-haiku-5.5

Exemples de code

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-haiku-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.

ChampTypeRemarques
modelstringanthropic/claude-haiku-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.

Réponse

ChampRemarques
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.

FAQ de l’API Claude Haiku 5.5

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

Why does the context differ from Anthropic's documentation?

The manufacturer documents its native model; Hermes currently lists a 200,000-token limit for this route. Leave room within that limit for output and other request tokens.

Can I send images?

Vision is not listed for this Hermes model, even though the manufacturer describes image input on its own platform. Use a Hermes model whose catalog lists vision when you need image input.

What is the Claude Haiku 5.5 API on Hermes AI?

Claude Haiku 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-haiku-5.5.

What is the context window of Claude Haiku 5.5?

200,000 tokens, shared by the prompt and the output.

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

Supported: Outils et la JSON. Not supported: Vision, Reasoning et la Audio. Streaming works with stream: true.

How is Claude Haiku 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 Haiku 5.5?

Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send anthropic/claude-haiku-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 Haiku 5.5?

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