OpenAI 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...
OpenAI GPT-6 Luna costs $0.10 per 1M input tokens and $0.50 per 1M output tokens at the standard tier, the lowest default-region price among the 3 providers SF·SIX tracks, from OpenAI. Cached input reads cost $0.01 per 1M tokens. Updated ; prices checked .
- Developer
- OpenAI
- Input modalities
- file, image, text
- Output modalities
- text
- Context tokens
- 1,050,000
- Latest price observation
- 2026-10-17
- Lowest paired standard token quote
- $0.10 input / $0.50 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| AzureOpenRouter | $0.10 | $0.50 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| OpenAIOpenRouter | $0.10 | $0.50 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Amazon BedrockOpenRouter · us-east-1 region | $0.11 | $0.55 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| AzureOpenRouter · EU region | $0.11 | $0.55 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| AzureOpenRouter · US region | $0.11 | $0.55 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| OpenAIOpenRouter · Fast tier | $0.20 | $1.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| OpenAIOpenRouter · Flex tier | $0.05 | $0.25 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
Batch and free variants
- GPT-6 Luna (batch) · from $0.05 input / $0.25 output per 1M tokens
Prices by service tier
| Tier | Input / 1M | Output / 1M | Cache read / 1M | Cheapest provider | vs standard (blended) |
|---|---|---|---|---|---|
| Standard | $0.10 | $0.50 | $0.01 | OpenAI | 100% |
| BatchBatch endpoint | $0.05 | $0.25 | $0.005 | OpenRouter (auto-routed) | 50% |
| Flex | $0.05 | $0.25 | $0.005 | OpenAI | 50% |
| Fast | $0.20 | $1.00 | $0.02 | OpenAI | 200% |
Each tier’s cheapest endpoint. Standard is the default-region headline; flex and batch trade speed or latency for a lower price, priority and fast cost more for faster service.
Regional endpoints
| Provider and region | Input / 1M | Output / 1M |
|---|---|---|
| Amazon Bedrockus-east-1 region | $0.11 | $0.55 |
| AzureEU region | $0.11 | $0.55 |
| AzureUS region | $0.11 | $0.55 |
Data-residency endpoints in a named region; they are never used as the headline while a default-region price exists.
Conditional pricing
- Prompts over 272,000 tokens: $0.20 input / $0.75 output per 1M tokens (OpenAI).
Speed by provider
| Provider and terms | Throughput | Latency | Uptime | Input / 1M |
|---|---|---|---|---|
| OpenAIFast tier | 106 tok/s | 1.08 s | 100.0% | $0.20 |
| OpenAIFlex tier | 91 tok/s | 2.24 s | 100.0% | $0.05 |
| Amazon Bedrockus-east-1 region | 84 tok/s | 950 ms | 100.0% | $0.11 |
| OpenAI | 71 tok/s | 2.63 s | 100.0% | $0.10 |
| AzureEU region | 53 tok/s | 849 ms | 100.0% | $0.11 |
| Azure | 43 tok/s | 5.47 s | 100.0% | $0.10 |
| AzureUS region | 28 tok/s | 6.32 s | 100.0% | $0.11 |
Previous 30 minutes; reported by OpenRouter. Fastest first.
Usage on OpenRouter
| UTC day | Tokens |
|---|---|
| 2026-10-10 | 868,303,635,762 |
| 2026-10-11 | 725,903,254,266 |
| 2026-10-12 | 856,178,804,934 |
| 2026-10-13 | 1,023,174,468,753 |
| 2026-10-14 | 1,066,569,516,870 |
| 2026-10-15 | 969,454,323,236 |
| 2026-10-16 | 988,368,486,336 |
OpenRouter rankings (CC BY 4.0), named daily rows. Most-used AI models
Benchmarks
Artificial Analysis Intelligence Index 38.1, coding index Not reported, agentic index Not reported (Artificial Analysis via OpenRouter, CC BY 4.0; not an SF·SIX measurement).
Prediction markets
OpenAI GPT-6 Luna meets the rule for SF·SIX usage ladders. Open OpenAI GPT-6 Luna markets (Hedera testnet, test funds only) · How AI prediction markets work
Compare and estimate
Sources and method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Prices from OpenRouter; each row below links its source and observation date. Methodology and editorial policy.
Frequently asked questions
How much does OpenAI GPT-6 Luna cost per 1M tokens?
$0.10 per 1M input tokens and $0.50 per 1M output tokens at the standard tier, the lowest default-region price SF·SIX tracks, from OpenAI. The cheapest batch price is $0.05 input and $0.25 output per 1M tokens.
Which providers offer OpenAI GPT-6 Luna?
3 providers with 7 priced endpoints: Amazon Bedrock, Azure, OpenAI.
What is the context window of OpenAI GPT-6 Luna?
1,050,000 tokens; prompts over 272,000 tokens: $0.20 input / $0.75 output per 1M tokens (OpenAI).
How fast is OpenAI GPT-6 Luna?
The fastest measured endpoint is OpenAI (Fast tier) at 106 tok/s, as reported by OpenRouter for the previous 30 minutes.
How much is OpenAI GPT-6 Luna used?
988,368,486,336 tokens on 2026-10-16 (UTC) through OpenRouter, per OpenRouter’s public rankings. This is OpenRouter traffic only, not all usage.
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.