πŸŽ‰ Get Free $5 on Signup！
Models
Enterprise
Subscribe
Resource
Activity
Documentation
Console

/openai/gpt-5.6-luna

O

OpenAI: GPT-5.6 Luna

GPT-5.6 Luna is OpenAI's cost-efficient GPT-5.6 model designed for high-volume production workloads. It combines long-context reasoning, multimodal image understanding, coding, structured outputs, function calling, and advanced tool use with significantly lower inference costs, making it well suited for large-scale assistants, automation, classification, extraction, and agentic workflows.

Modetext、image β†’ text
Input price$0.2 per M tokens
Output price$1.2 per M tokens
Context length1050K tokens
Listed at2026-02-16T00:00:00Z

OpenAI

Latencyβ€”
Throughputβ€”
Upload rateβ€”
Context length1050K tokens
Max output128K tokens
Input price$0.2per 1M tokens
Output price$1.2per 1M tokens
Cache readβ€”per 1M tokens
Cache writeβ€”per 1M tokens

Performance

Avg TPSβ€”
Avg latencyβ€”
Avg success rateβ€”
TPSβ€”
TTFTβ€”
Latencyβ€”
Success rateβ€”

Success rate

Speed

Code Example

curl ${API_BASE_URL}/v1/batch \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-luna",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
openai-batch

Supported Parameters

ParameterTypeDefaultDescription
stringmediumControls reasoning depth and latency. Medium is the default reasoning effort for GPT-5.6 Luna.
integer128000Controls the maximum number of output tokens.
booleanfalseEnables incremental streaming responses.

Rate Limits

GroupRPMTPMRPD

RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply by token group.

Pricing

ProviderBilling typePrice summary
O
OpenAI
Expression
Input price$0.2per 1M tokens
Completion price$1.2per 1M tokens
Cache read price$β€”per 1M tokens
Cache write price$β€”per 1M tokens
O
OpenAI-Default
Expression
Input price$0.2per 1M tokens
Completion price$1.2per 1M tokens
Cache read price$β€”per 1M tokens
Cache write price$β€”per 1M tokens