GPT-6 Luna API Pricing & Monthly Cost Simulator
Verified 2026 unit economics for OpenAI GPT-6 Luna (openai/gpt-6-luna): $0.1/1M uncached input, $0.01/1M cached prefix read, and $0.5/1M output across a 1,050,000-token context window (released 2026-09-22).
Uncached Input (/1M)
$0.1
Cached Prompt Read (/1M)
$0.01 (-90%)
Output Completion (/1M)
$0.5
50% Batch API (In / Out)
$0.05 / $0.25
Interactive 30-Day Monthly Spend Simulator
Live Unit-Cost & Prompt Cache Slider (GPT-6 Luna)
openai/gpt-6-luna
Estimated 30-day spend
$18.60/mo
Cost per 1,000 calls
$0.6200
Monthly savings vs 0% cache
$5.40/mo
Technical Limits & API Capabilities
Context window
1,050,000
Max output tokens
128,000
Workload tier
Coding & Agent
Input modalities
text, file, image
Tool Calling: Yes
JSON Schema Strict: Yes
Reasoning Tokens: Supported
50% Batch API: Available
Same-Category 2026 Model Alternatives (Coding & Agent)
| Model | Provider | Input / Cached ($/1M) | Output ($/1M) | Context / Max Out |
|---|---|---|---|---|
| GPT-6 Luna | OpenAI | $0.1 / $0.01 | $0.5 | 1,050,000 / 128,000 |
| Gemini 4 Hydrogen | $1.5 / $0.075 | $7.5 | 1,048,576 / 943,718 | |
| Gemini 4 Carbon | $2 / $0.1 | $10 | 1,048,576 / 943,718 | |
| Muse Ember | Meta | $0.1 / $0.004 | $0.5 | 1,048,576 / 943,718 |
| GPT-6.1 Terra | OpenAI | $1 / $0.05 | $5 | 1,050,000 / 128,000 |
| MiniMax M3.1 Flash | MiniMax | $0.15 / $0.015 | $0.6 | 1,048,576 / 524,288 |
| Muse Spark Open | Meta | $1.25 / $0.15 | $4.25 | 1,048,576 / 943,718 |
Head-to-Head Matchups Featuring GPT-6 Luna
- GPT-6.1 Terra Pro vs GPT-6 Luna — $1 vs $0.1 / 1M
- DeepSeek V4.1 Flash vs GPT-6 Luna — $0.3 vs $0.1 / 1M
Frequently Asked Questions
How much does GPT-6 Luna cost per 1 million tokens in 2026?
GPT-6 Luna by OpenAI is billed at $0.1 per 1M uncached input tokens, $0.01 per 1M cached input read tokens (90% cache discount), and $0.5 per 1M output tokens.
What are the context window and max output token limits for GPT-6 Luna?
GPT-6 Luna supports a 1,050,000-token input context window and up to 128,000 completion output tokens per request, accepting text, file, image inputs.
Does GPT-6 Luna support strict JSON Schema outputs, tool calling, and Batch API?
GPT-6 Luna capability profile: tool calling = Supported, strict JSON Schema structured outputs = Supported, reasoning mode = Supported, and 50% asynchronous Batch API = Supported.