GPT-5.6 Luna
OpenAIUpdated August 2026. GPT-5.6 Luna by OpenAI: $0.2/M cache-miss input, $1.20/M output tokens. Cached input: $0.02/M. Explicit cache writes: $0.25/M. Long-context pricing above 272K input tokens: $0.4/M input, $1.80/M output. 1.1M context, 128K max output. Vision & Function Calling. Free calculator + compare 40+ models.
Input Price
$0.2
cache miss / 1M tokens
Cached Input
$0.02
per 1M tokens
Output Price
$1.20
per 1M tokens
Context Window
1.1M
tokens
Specifications
| Provider | OpenAI |
| Model ID | gpt-5.6-luna |
| Input Price | $0.2 / 1M cache-miss tokens |
| Cached Input Price | $0.02 / 1M tokens |
| Explicit Cache Write Price | $0.25 / 1M tokens |
| Output Price | $1.20 / 1M tokens |
| Long Context Threshold | 272K input tokens |
| Long Context Pricing | $0.4 / 1M cache-miss input, $0.04 / 1M cached input, $0.5 / 1M explicit cache writes, $1.80 / 1M output |
| Context Window | 1.1M tokens |
| Max Output | 128K tokens |
| Capabilities | textvisionfunction_callingstructured_output |
| Release Date | 2026-07-09 |
| Pricing Source | Official OpenAI pricing |
| Price Verified | 2026-08-01 · GPT-5.6 Terra and Luna prices reflect OpenAI's latest reductions. Sol pricing is unchanged. |
| Notes | High-volume GPT-5.6 routing model at OpenAI's reduced August 2026 price, with the same 1.05M context window and 128K maximum output as Sol and Terra. |
Monthly Cost Estimates
Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower.
| Daily Tokens | Monthly Cost | Annual Cost |
|---|---|---|
| 10K | $0.21 | $2.52 |
| 50K | $1.05 | $12.60 |
| 100K | $2.10 | $25.20 |
| 500K | $10.50 | $126.00 |
| 1.0M | $21.00 | $252.00 |
About GPT-5.6 Luna
GPT-5.6 Luna is a large language model by OpenAI. It features a 1.1M token context window with up to 128K tokens of output per request. The model supports 4 capabilities: text, vision, function_calling, structured_output.
At $0.2 per million cache-miss input tokens and $1.20 per million output tokens, GPT-5.6 Luna is positioned as a cost-effective option in the OpenAI lineup. Repeated prefix input can be charged at $0.02 per million cached tokens. Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.
GPT-5.6 Luna Key Details
- Pricing: $0.2/M cache-miss input tokens, $0.02/M cached input tokens, $0.25/M explicit cache writes, $1.20/M output tokens
- Context window: 1.1M tokens — one of the largest available
- Max output: 128K tokens per response
- Capabilities: text, vision, function_calling, structured_output
- Highlights: High-volume GPT-5.6 routing model at OpenAI's reduced August 2026 price, with the same 1.05M context window and 128K maximum output as Sol and Terra.
- Released: 2026-07-09
Other OpenAI Models
Similar Price Range
Related Tools
FAQ
How much does GPT-5.6 Luna cost?
GPT-5.6 Luna costs $0.2 per million cache-miss input tokens and $1.20 per million output tokens. Cached input costs $0.02 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $2.40/month before cache-hit savings.
What is GPT-5.6 Luna's context window?
GPT-5.6 Luna supports a context window of 1.1M tokens. This means your combined input prompt and output response can be up to 1.1M tokens. The maximum output per response is 128K tokens.
Is GPT-5.6 Luna good for my use case?
GPT-5.6 Luna supports text, vision, function_calling, structured_output. As a budget-friendly model, it works well for high-volume tasks like classification, summarization, and simple generation. Use our Pricing Calculator to compare with alternatives.