Managed Inference and Agents API with Claude Opus 4.5

Table of Contents [expand]

Last updated December 17, 2025

Claude Opus 4.5 is a large language model (LLM) in Anthropic’s Claude family that supports conversational chat, tool-calling, autonomous coding, effort control, and enhanced reasoning for complex tasks with extended thinking. It offers a highly intelligent, fast, and practical solution you can use to power your AI apps.

  • Model ID: claude-opus-4-5
  • Region: us, eu

When to Use This Model

Claude Opus 4.5 supports a variety of use cases, including advanced software development, complex agentic workflows, and enterprise operations. It’s optimized to combine maximum intelligence and capability with functional performance.

Usage

Claude Opus 4.5 follows our Claude /v1/chat/completions API schema.

To provision access to the model, attach claude-opus-4-5 to your app $APP_NAME:

heroku ai:models:create -a $APP_NAME claude-opus-4-5

Using config variables, you can invoke claude-opus-4-5 in a variety of ways:

Rate Limits

  • Maximum requests per minute: 150
  • Maximum tokens per minute: 800,000

Prompt Caching

Prompt caching is supported for system prompts and tools. The minimum tokens required for prompt caching is 4,096.

Example curl Request

Get started quickly with an example request:

export INFERENCE_MODEL_ID=$(heroku config:get -a $APP_NAME INFERENCE_MODEL_ID)
export INFERENCE_KEY=$(heroku config:get -a $APP_NAME INFERENCE_KEY)
export INFERENCE_URL=$(heroku config:get -a $APP_NAME INFERENCE_URL)

curl $INFERENCE_URL/v1/chat/completions \
-H "Authorization: Bearer $INFERENCE_KEY" \
-d @- <<EOF
{
  "model": "$INFERENCE_MODEL_ID",
  "messages": [
    { "role": "user", "content": "Hello!" },
    { "role": "assistant", "content": "Hi there! How can I assist you today?" },
    { "role": "user", "content": "What's the weather like in Portland, Oregon right now?" }
  ],
  "temperature": 0.5,
  "max_tokens": 100,
  "stream": false,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Fetches the current weather for a given city.",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {
              "type": "string",
              "description": "The name of the city to get weather for."
            }
          },
          "required": ["city"]
        }
      }
    }
  ],
  "tool_choice": "auto",
  "top_p": 0.9
}
EOF