GPT-6 Luna
by OpenAIopenai/gpt-6-luna
GPT-6 Luna at a glance
- Context length
- 1,050,000 tokens
- Maximum output
- 128,000 tokens
- Accepts
- Text, Image, File
- Returns
- Text
- Features
- ReasoningJSON outputTool callingPrompt cachingImage input
- Reasoning effort levels
maxxhighhighmediumlownoneReasoning can be turned off.- Released
- 22 Sep 2026
- Knowledge cutoff
- Not published
Model facts synced from the OpenRouter model list on 21 Oct 2026.
GPT-6 Luna pricing by route
A route is the service LLMCompare calls to reach the model. GPT-6 Luna has 2 routes. Prices are in US dollars.
| Route | On LLMCompare | Inputper 1M tokens | Outputper 1M tokens | Cache readper 1M tokens | Cache writeper 1M tokens | Price verified on | Source |
|---|---|---|---|---|---|---|---|
| OpenAI (direct)Default | Runnable now | $0.10 | $0.50 | $0.01 | $0.125 | openai.com/api/pricing | |
| OpenRouter | Not configured | $0.10 | $0.50 | $0.01 | $0.125 | openrouter.ai/openai/gpt-6-luna |
The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.
Cost calculator
Estimate what a batch of calls to GPT-6 Luna costs. The starting numbers are examples. Change them to match your task.
Part of the input tokens above, billed at the cache read price.
Billed in addition to the output tokens.
- Cost per call
- $0.00035
- 1 credits
- Cost of 100 calls
- $0.035
- 100 credits
Calculated from the OpenAI (direct) prices verified on 30 Sep 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.
Parameters you can set
All 2 routes accept the same parameters.
| Parameter | Type | Range or options | Default |
|---|---|---|---|
max_tokens | Integer | 1 to 128,000 | Provider default |
reasoning_effort | One of | maxxhighhighmediumlownone | medium |
seed | Integer | -2,147,483,648 to 4,294,967,295 | Provider default |
response_format | One of | textjson_object | Provider default |
About GPT-6 Luna
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...
Description as published for this model. LLMCompare has not edited it.
Models to compare with GPT-6 Luna
Text models from the same provider and models at the nearest price. The order is not a ranking.
| Add to comparison | Model | Context | Max output | Input priceper 1M tokens | Output priceper 1M tokens | Features | Released | On LLMCompare |
|---|---|---|---|---|---|---|---|---|
GPT-6 Luna ProOpenAIopenai/gpt-6-luna-pro | 1.05M | 128k | $0.10 | $0.50 | ReasoningJSONToolsCacheVision | No route yet | ||
GPT-4.1 NanoOpenAIopenai/gpt-4.1-nano | 1.05M | 32.8k | $0.10 | $0.40 | JSONToolsCacheVision | No route yet | ||
gpt-oss-120bOpenAIopenai/gpt-oss-120b | 131k | 65.5k | $0.15 | $0.60 | ReasoningJSONToolsCache | No route yet | ||
Claude Haiku 5.5Anthropicanthropic/claude-haiku-5.5 | 1M | 128k | $0.10 | $0.50 | ReasoningJSONToolsCacheVision | No route yet | ||
Gemma 4 31BGooglegoogle/gemma-4-31b-it | 262k | 16.4k | $0.20 | $0.40 | JSONToolsVision | No route yet | ||
Qwen3.8 Omni FlashQwenqwen/qwen3.8-omni-flash | 1M | 131k | $0.15 | $0.47 | JSONToolsCacheVision | No route yet |
Questions about GPT-6 Luna
- How much does GPT-6 Luna cost?
- On the OpenAI (direct) route, GPT-6 Luna costs $0.10 per 1 million input tokens and $0.50 per 1 million output tokens, in US dollars. Input tokens that GPT-6 Luna reads from the prompt cache cost $0.01 per 1 million tokens. LLMCompare verified this price on 30 Sep 2026.
- What is the context length of GPT-6 Luna?
- GPT-6 Luna has a context length of 1,050,000 tokens and returns up to 128,000 output tokens in one call.
- What inputs does GPT-6 Luna accept?
- GPT-6 Luna accepts these inputs: Text, Image, File. GPT-6 Luna returns: Text.
- Which reasoning effort levels does GPT-6 Luna support?
- GPT-6 Luna supports these reasoning effort levels: max, xhigh, high, medium, low, none. Reasoning can be turned off for GPT-6 Luna.
- Can I test GPT-6 Luna on my own data?
- Yes. LLMCompare can run GPT-6 Luna now. You add your own test cases, select GPT-6 Luna and the models you want to compare it with, and LLMCompare records every output with its cost and response time.