Claude Sonnet 4.6

claude-sonnet-4-6

Use the Claude Sonnet 4 6 API for chat and coding. Send conversation messages and include tool definitions on supported routes. Use it to work through multi-step coding tasks or review longer technical material. Compare the available provider routes, request examples, and usage prices on OpenAny.

Published price: From $2.897 / 1M tokens
Billing unit: / 1M tokens
Context / Max output: 1000K / 128K
Listed routes: 1

Auto route · $2.897 / 1M tokens

Provider	Pricing	Latency	Uptime	Supply	Route
Live	Input $2.897 / 1M tokens Output $14.483 · Cache $0.290	1269ms	—	Verified

Selected pricing · AnthropicUSD / 1M tokens

Input: $2.897
Output: $14.483
Cache read: $0.290
Cache write: $3.621

Source: the selected provider route in OpenAny's public model catalog. A price update timestamp is not supplied.

messages

Other parameters (11)

max_tokensMaximum number of tokens to generate. This is required by Anthropic and is a hard limit for total output, including thinking and visible response content.metadataMetadata object. Can include user_id to identify the end user for abuse monitoring and tracing. Example: {"user_id":"user-123"}.stop_sequencesCustom stop sequences. Supports up to 4 strings. Generation stops when any sequence is produced, and the stop sequence is not included in the output.streamWhether to enable Server-Sent Events streaming output.systemtemperatureSampling temperature from 0.0 to 1.0. Higher values make output more random; lower values make output more deterministic. Prefer changing only one of temperature, top_p, or top_k.thinkingExtended thinking configuration for supported models.tool_choiceControls tool use behavior. Use {"type":"auto"}, {"type":"any"}, or {"type":"tool","name":"tool_name"}.toolsTools available to the model. Each tool should define name, description, and input_schema.top_kSample only from the top K most likely tokens. Prefer changing only one of temperature, top_p, or top_k.top_pNucleus sampling threshold from 0.0 to 1.0. Prefer changing only one of temperature, top_p, or top_k.

Result preview

Anthropic · 1269ms

Response example. Run to see the actual response.

{
  "id": "msg_bdrk_01Bg1KUdHeA2Nf2TMgxsQ2P2",
  "model": "claude-sonnet-4-6",
  "usage": {
    "input_tokens": 0,
    "total_tokens": 31,
    "output_tokens": 0,
    "prompt_tokens": 8,
    "completion_tokens": 23,
    "input_tokens_details": null,
    "prompt_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0,
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0,
      "reasoning_tokens": 0
    },
    "claude_cache_creation_1_h_tokens": 0,
    "claude_cache_creation_5_m_tokens": 0
  },
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How are you doing? Is there something I can help you with today? 😊"
      },
      "finish_reason": "stop"
    }
  ],
  "created": 1784810011,
  "openmodels_cost": 380
}

Request example

POST /v1/messages

curl 'https://api.openany.si/v1/messages' \
  -H "Authorization: Bearer $OPENANY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "max_tokens": 1024,
  "messages": [
    {
      "content": "hello",
      "role": "user"
    }
  ],
  "model": "claude-sonnet-4-6",
  "stream": false,
  "temperature": 1,
  "tool_choice": {
    "type": "auto"
  }
}'

Model API questions

How do I call Claude Sonnet 4.6 through OpenAny?

Use model ID claude-sonnet-4-6 with an OpenAny key and the operation published in this model's API tab. The model API base is https://api.openany.si/v1. Confirm the protocol and request schema; model availability does not imply every OpenAI API operation is supported.

How is Claude Sonnet 4.6 billed?

Compare the published rate and billing unit of the selected provider route. Input, output and cache token rates may differ. Image, audio and video models can use other units. Recorded usage determines the charge under that route's billing contract.

Are Community and Verified routes the same as an official publisher API?

No. Inspect the provider name and supply classification for the specific route. A marketplace listing or a supply label is not a claim of publisher endorsement, identical service or measured uptime. Different route prices may reflect different supply and conditions.

Where do these prices come from, and when were they updated?

Rates come from the provider routes in OpenAny's public model catalog, not an independent quote from the model publisher. The catalog does not supply a price update timestamp. A page or catalog snapshot date is not a price revision date. Compare supply, billing units, tiers and conditions; a lower listed rate alone does not establish equivalent service or explain the price difference.

Use Claude Sonnet 4.6 with your agent

Inspect endpoint contracts and confirm availability and pricing before a paid call.