Managed Inference and Agents API with Claude Opus 5.5

Table of Contents [expand]

When to Use This Model
Usage
Example curl Requests

Last updated October 14, 2026

Claude Opus 5.5 is a large language model (LLM) in Anthropic’s Claude family that supports conversational chat, tool-calling, and adaptive thinking. It’s Anthropic’s Opus model for long-running agents. The model offers deep reasoning for advanced coding, complex professional work, and multi-step agent tasks.

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

When to Use This Model

Claude Opus 5.5 is built for long-running agentic coding and knowledge work. Use this model when a task is multi-step and hard to specify up front. The model is also useful for apps that benefit from deeper reasoning that involves advanced coding, complex analysis, and agents that run many turns. For high-volume or latency-sensitive work, a faster model such as Claude Sonnet 5.5 or Claude Haiku 5.5 is usually the better fit.

Usage

Claude Opus 5.5 follows our Claude /v1/chat/completions API schema.

To provision access to the model, attach a Managed Inference and Agents add-on to your app $APP_NAME:

heroku addons:create heroku-inference:standard -a $APP_NAME

Using config variables, you can invoke the model in various ways:

Heroku CLI ai plugin (heroku ai:models:call)
curl
Python
Ruby
Javascript

Multimodal Support

Supported inputs: text, image
Supported outputs: text

Rate Limits

Maximum requests per minute: 50
Maximum tokens per minute: 300,000

Prompt Caching

Prompt caching is supported for system prompts and tools. The minimum tokens required for prompt caching is 512.

Example curl Requests

Text to Text

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": "claude-opus-5-5",
  "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

Image to Text

curl -X POST $INFERENCE_URL/v1/chat/completions \
  -H "Authorization: Bearer $INFERENCE_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Forwarded-Proto: https" \
  -d @- <<EOF
{
  "model": "claude-opus-5-5",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "What do you see in this image?"},
      {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/0/09/A_chinstrap_penguin_%28Pygoscelis_antarcticus%29_on_Deception_Island_in_Antarctica.jpg/960px-A_chinstrap_penguin_%28Pygoscelis_antarcticus%29_on_Deception_Island_in_Antarctica.jpg"}}
    ]
  }]
}
EOF

Categories