GPT-6 Luna pricing and routing profile
GPT-6 Luna from OpenAI lists at $0.10 per million input tokens and $0.50 per million output tokens, with a 1,050,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.
Tool callingStructured outputReasoning control
Cost per 1,000 requests
| Request shape | List cost |
|---|---|
| Classification or routing (600 tokens in, 10 out) | $0.065 |
| Chat reply (2,000 in, 400 out) | $0.40 |
| Retrieval-augmented answer (8,000 in, 500 out) | $1.05 |
Before prompt caching. Try your own shape in the cost calculator.
Can Gimbix route to it first?
Not as a first-answer model through OpenRouter: no host returns token log probabilities for GPT-6 Luna. It can still be the model Gimbix falls back to when a cheaper model is unsure.
Measured by Gimbix
On 400 real BANKING77 customer messages, GPT-6 Luna answered 320 correctly (95% interval 75.8%–83.6%), with 0 invalid answers, at $0.0556 per 1,000 requests and a median of 902 ms. See all 22 models.
Who serves GPT-6 Luna
| Host | Input / output per 1M | Log probabilities | Uptime, last 30 min |
|---|---|---|---|
| OpenAI | $0.05 / $0.25 | no | 100.0% |
| OpenAI | $0.10 / $0.50 | no | 99.9% |
| Azure | $0.10 / $0.50 | no | 100.0% |
| Azure | $0.11 / $0.55 | no | 100.0% |
| Azure | $0.11 / $0.55 | no | 100.0% |
| Amazon Bedrock | $0.11 / $0.55 | no | — |
| OpenAI | $0.20 / $1.00 | no | 100.0% |
A host that lists log probabilities may still omit them; Gimbix checks each one before relying on it.
Cheaper models that can answer first
Models priced below GPT-6 Luna that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.
| Model | Input / output per 1M | Cheaper on a chat reply |
|---|---|---|
| Ternary Bonsai 2 27B | $0.075 / $0.50 | 13% |
| Nemotron 3 Super | $0.08 / $0.45 | 15% |
| Gemma 3 27B | $0.08 / $0.45 | 15% |
| Gemma 4 31B | $0.09 / $0.34 | 21% |
| Qwen3 235B A22B Instruct 2507 | $0.0875 / $0.35 | 21% |
| Mistral Small 3.2 24B | $0.0938 / $0.25 | 28% |
Compare GPT-6 Luna
- GPT-6 Luna vs Claude Opus 5.5
- GPT-6 Luna vs Claude Sonnet 5
- GPT-6 Luna vs Claude Fable 5.1
- GPT-6 Luna vs Claude Opus 5
- GPT-6 Luna vs GPT-6 Sol
- GPT-6 Luna vs GPT-6 Astra
- GPT-6 Luna vs GPT-5.6 Sol
- GPT-6 Luna vs GPT-5.6 Terra
- GPT-6 Luna vs GPT-5.5
- GPT-6 Luna vs GPT-5.4
- GPT-6 Luna vs Gemini 3.1 Pro Preview
- GPT-6 Luna vs Gemini 3.8 Flash
- GPT-6 Luna vs Grok 4.7
- GPT-6 Luna vs Qwen3.8 Max (0902)
- GPT-6 Luna vs Kimi K3
- GPT-6 Luna vs GLM 5.3
- GPT-6 Luna vs DeepSeek V4 Pro 0423
- GPT-6 Luna vs Mistral Large 3 2512
- GPT-6 Luna vs Nova Premier 1.0
- GPT-6 Luna vs Command A
- GPT-6 Luna vs GPT-5.6 Luna
- GPT-6 Luna vs GPT-5.4 Mini
- GPT-6 Luna vs GPT-5.4 Nano
- GPT-6 Luna vs GPT-4.1 Mini
- GPT-6 Luna vs gpt-oss-120b
- GPT-6 Luna vs gpt-oss-20b
- GPT-6 Luna vs Claude Haiku 4.5
- GPT-6 Luna vs Gemini 3.5 Flash Lite
- GPT-6 Luna vs Gemma 4 31B
- GPT-6 Luna vs DeepSeek V4.1 Flash
- GPT-6 Luna vs DeepSeek V4 Flash 0731
- GPT-6 Luna vs GLM 5.3 Flash
- GPT-6 Luna vs Hy4 preview
- GPT-6 Luna vs MiMo-V2.6-Flash
- GPT-6 Luna vs Nemotron 3.5 Lightning
- GPT-6 Luna vs Nemotron 3 Ultra
- GPT-6 Luna vs Qwen3.8 Flash
- GPT-6 Luna vs Qwen3.7 Flash
- GPT-6 Luna vs Qwen3.8 27B
- GPT-6 Luna vs MiniMax M3
- GPT-6 Luna vs Kimi K2.6
- GPT-6 Luna vs Mistral Small 4
- GPT-6 Luna vs Ministral 3 8B 2512
- GPT-6 Luna vs Llama 4 Maverick
- GPT-6 Luna vs Llama 3.3 70B Instruct
- GPT-6 Luna vs Nova Lite 1.0
- GPT-6 Luna vs Nova Micro 1.0
- GPT-6 Luna vs Command R7B (12-2024)
- GPT-6 Luna vs Phi 4
Questions
How much does GPT-6 Luna cost?
GPT-6 Luna lists at $0.10 per million input tokens and $0.50 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.40 per 1,000 requests.
What is the context window of GPT-6 Luna?
1,050,000 tokens.
Can a cheaper model replace GPT-6 Luna?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match GPT-6 Luna on one half of your requests and make at most three answers worse on the other.