Docs

Running a model

Anthropicllm

Anthropic Claude Haiku 4.5

Fast multimodal language model for low-latency agents and scaled reasoning workloads

POSTauray-serverless/model/anthropic-claude-haiku-4-5
openapi.jsonllms.txt

One of Auray's catalogue models: the same key, the same credits, the same job lifecycle as every other address.

Its request shape is published below. Whether it runs right now is GET /v1/catalogue's word, with no key needed: its addresses say connected for an address that runs, and a submit to any other is refused before anything is charged — described answers 501 model_not_connected, paused 503 model_disabled.

Category llm · Scope text:write (or external:write on an older key) · Price Credits per million tokens: 83.3334 for the prompt and 416.6667 for the answer, its reasoning included. Quoted when you submit at the prompt as estimated — its UTF-8 bytes over 4, 1100 tokens an image, and for a request that sends a document the model's whole context window, 200000 tokens, since a document's length is not known until it is read — and at the whole answer settings.maxTokens asks for, 4096 when it names none. A prompt the request asks to cache (settings.cache) is counted 1.25 times. The charge settles to the tokens the model was billed for and never above the quote. The submit's answer carries the quote as credits_quoted, and credits_charged says what has been taken.

#Input

FieldTypeRequiredDefaultDescription
inputsobjectno—
inputs.documentsstring[]no—Array of document inputs (an http(s) URL; upload a local file first and send its read URL). Documented range: 1 or more.
inputs.imagesstring[]no—Array of image inputs (an http(s) URL; upload a local file first and send its read URL). Documented range: 1 or more.
settingsobjectno—
settings.systemPromptstringno—System-level instruction that guides the model's behavior and output style across the entire generation. Documented range: 1 to 200,000 characters.
settings.cacheobjectno—
settings.cache.scopestringno"system+history"Controls which parts of the request are cached. One of "system", "system+history".
settings.cache.ttlstringno"5m"Time-to-live for the cache. One of "5m", "1h".
settings.maxTokensintegerno4096Maximum number of tokens to generate in the response. Left out, a call is sent and quoted for the default here — the model's own where it is smaller than 8,192; a larger value, up to the maximum, is quoted for that answer. Documented range: 1 to 64,000.
settings.stopSequencesstring[]no—Array of sequences that will cause the model to stop generating further tokens when encountered.
settings.thinkingLevelstringno—Controls the depth of internal reasoning the model performs before generating a response. One of "off", "low", "medium", "high".
messagesobject[]yes—
messages[].rolestringyes—Role of the message author. One of "user", "assistant".
messages[].contentstringyes—Text content of the message. Documented range: 1 or more characters.
outputFormatstringno"TEXT"Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities. - `JPG`: Best for photorealistic images with smaller file sizes (no transparency). - `PNG`: Lossless compression, supports high quality and transparency (alpha channel). - `WEBP`: Modern format providing superior compression and transparency support. - `MP4`: Widely supported video container (H.264), recommended for general use. - `WEBM`: Optimized for web delivery. - `MOV`: QuickTime format, common in professional workflows (Apple ecosystem). - `GIF`: Animated image format (no audio), suitable for short loops or previews. - `MP3`: Compressed audio, smaller file size. - `WAV`: Uncompressed, high-quality audio. - `FLAC`: Lossless compression. - `OGG`: Open-source compressed audio format (Vorbis codec). - `SVG`: Scalable Vector Graphics. - `TIFF`: High-quality output supporting layers. - `GLB`: Binary glTF format for 3D models, including geometry, textures, and PBR materials. > [!NOTE] > **Transparency**: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., `PNG`, `WEBP`, `TIFF`). `JPG` does not support transparency. One of "TEXT".
includeUsagebooleanno—Include token usage statistics in the response.
idempotency_keystringno—Your own name for this request. Send the same one twice and the second call is answered with the first request rather than charged again. Idempotency-Key: as a header is accepted as an alias — that is the spelling a retrying proxy replays, and the one to use when running a model on auray.run, where a request that outlives its connection is answered 504 and recovered by replay. Omit it and the platform mints one. 1 to 64 characters.

#Rules

Across fields, as the model's documentation states them. Each is judged before anything is charged — warned with a Deprecation header until enforcement starts — and listed as JSON Schema under x-auray-rules in the openapi.json.

  • messages is required.
  • messages must hold at least 1 item. In every item of messages: messages[].role and messages[].content are required.
  • When settings.thinkingLevel is one of "low", "medium", "high", settings.maxTokens must be at least 1025.

#Example

curl -X POST https://queue.auray.run/auray-serverless/model/anthropic-claude-haiku-4-5 \
  -H "Authorization: Bearer $AURAY_API_KEY" \
  -H "content-type: application/json" \
  -d '{
  "messages": [
    {
      "role": "user",
      "content": "In one sentence, what does a brass orrery show?"
    }
  ]
}'

The same body on https://auray.run runs synchronously and answers the result — unless it usually takes longer than a run may hold its connection, which is refused 400 model_not_synchronous before anything is charged. Options — ?webhook=, ?wait=, priority and timeout headers — are on Submit a request.

#Machine contracts

  • openapi.json — this page as an OpenAPI 3.1 document, public.
  • llms.txt — the same, written for an agent.

Start typing to search every page of the documentation.

Up arrow Down arrow to moveEnter to openEscape to close