​

OpenAI GPT-5.6

​

Migration quickstart

1. Choose the fixed Sol, Terra, or Luna model that matches the workload.
2. Swap only the model ID and keep the rest of the request stable.
3. Re-test reasoning effort, structured outputs, tools, latency, and task cost.
4. Canary the new route with your previous GPT-5 model available as a fallback.

​

Choose a model

​

What’s new

• GPT-5.6 adds the new Sol/Terra/Luna split instead of one default GPT route.
• All three GPT-5.6 tiers support reasoning.effort: "max" for the highest reasoning budget.
• GPT-5.6 supports reasoning.mode: "pro" without switching to a separate Pro model slug.
• GPT-5.6 adds persisted reasoning controls through reasoning.context.
• GPT-5.6 adds beta multi-agent support and Programmatic Tool Calling for eligible tool-heavy workflows.
• Prompt caching is priced with separate uncached input, cache read, cache write, and output meters.
• Explicit prompt caching is supported through prompt_cache_options; OpenAI currently recommends prompt_cache_options.ttl instead of prompt_cache_retention.

​

Update your request

{
  "model": "openai/gpt-5.6-terra",
  "input": "Summarize the rollout risks in this migration plan.",
  "reasoning": {
    "effort": "medium"
  }
}

{
  "model": "openai/gpt-5.6-sol",
  "input": "Review this multi-service incident report and propose a rollback plan.",
  "reasoning": {
    "effort": "max"
  }
}

{
  "model": "openai/gpt-5.6-sol",
  "messages": [
    {
      "role": "user",
      "content": "Design a test plan for this agent workflow."
    }
  ],
  "reasoning_effort": "max"
}

​

Review pricing

​

Use prompt caching deliberately

{
  "model": "openai/gpt-5.6-sol",
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Stable policy document...",
          "cache_control": {
            "type": "ephemeral",
            "ttl": "1h"
          }
        },
        {
          "type": "input_text",
          "text": "Apply the policy to this new customer request."
        }
      ]
    }
  ],
  "prompt_cache_options": {
    "mode": "explicit",
    "ttl": "24h"
  }
}

​

What to test

​

Reasoning and output quality

• Sol, Terra, and Luna at the effort levels you expect to expose to users, including max where quality-first workflows justify it
• standard mode versus reasoning.mode: "pro" on difficult tasks where quality matters more than latency
• structured outputs and schema pass rate at each effort level
• tool-call selection and argument quality

​

Cost and latency

• latency at each reasoning effort
• output token growth relative to your current production baseline
• cache read/write mix on repeated prompts
• cost per successful task, not just price per token

​

Rollback

• keep your previous GPT-5.x route available as a fallback
• keep max behind a config flag or preset until it is proven on production-like prompts
• monitor cache write volume separately from cache read volume
• move GPT-5.6 into default routing only after your own evals confirm task success, cost, and latency

​

Sources

• OpenAI GPT-5.6 preview announcement
• OpenAI GPT-5.6 model guidance
• OpenAI model catalog
• GPT-5.6 preview system card
• AI Stats prompt caching guide