GPT-5.6 Luna pricing
OpenAI · API id gpt-5.6-luna · verified 2026-10-18
| Input | $0.20 |
| Cached input (cache hit) | $0.02 |
| Cache write | $0.25 |
| Output | $1.20 |
| Batch discount | 50% |
| Context window | 1,050,000 tokens |
| Max output | 128,000 tokens |
| Above 272K prompt tokens | $0.40 in / $1.80 out |
USD per 1M tokens unless noted. Official source
Estimate your workload on GPT-5.6 Luna →
What GPT-5.6 Luna costs for real workloads
| Workload | GPT-5.6 Luna | Ministral 3 8B | Claude Haiku 5.5 | GPT-6 Luna | Mistral Small 4 |
|---|---|---|---|---|---|
| 10,000 chatbot replies 2,000 input + 400 output tokens each, 50% of the prompt cached | $7.00 | $2.25 | $3.10 | $3.10 | $4.05 |
| One 30-step coding agent run 12K system + tools prompt, 1K output and 3K tool result per step, caching on | $0.11 | $0.05 | $0.12 | $0.05 | $0.07 |
| 1M documents classified (batch) 600 input + 20 output tokens each, batch API where available | $72.00 | $46.50 | $35.00 | $35.00 | $51.00 |
Compared with the cheapest other small models. Change the numbers in the calculator.
Billing notes
Previous generation. Long context: prompts >272K input tokens bill the whole request at 2x input/cache and 1.5x output. Reasoning tokens billed as output. Regional/data-residency endpoints +10%.
Where GPT-5.6 Luna ranks by use case
Position by cost among all models that fit each workload (1 = cheapest).
- Cheapest LLM for coding agents: #5 of 36 (Per run (cached): $0.11)
- Cheapest LLM for RAG chatbots: #5 of 36 (Per 1,000 answers: $1.41)
- Cheapest LLM for batch classification and extraction: #5 of 36 (Classify 1M docs: $72.00)
- Long-context document analysis (400K tokens): #6 of 29 (10 questions, cached: $0.38)
- Cheapest LLM for high-volume customer support: #5 of 36 (Per 1,000 replies: $0.59)
Counting tokens for a prompt? The token counter estimates GPT-5.6 Luna tokens (OpenAI (o200k_base) tokenizer) and input cost.
Other OpenAI models
- GPT-6 Astra: $10.00 / $50.00
- GPT-5.5: $5.00 / $30.00
- GPT-5.6 Sol: $4.00 / $20.00
- GPT-6.1 Sol: $2.00 / $10.00
- GPT-6 Sol: $2.00 / $10.00
- GPT-5.6 Terra: $2.00 / $12.00
- GPT-5.4 mini: $0.75 / $4.50
- GPT-6 Luna: $0.10 / $0.50
FAQ
How much does GPT-5.6 Luna cost per 1M tokens?
GPT-5.6 Luna costs $0.20 per 1M input tokens and $1.20 per 1M output tokens at standard rates (verified 2026-10-18).
Does GPT-5.6 Luna support prompt caching?
Yes. Cached input is billed at $0.02 per 1M tokens, and writing to the cache costs $0.25 per 1M tokens.
Is there a batch discount for GPT-5.6 Luna?
Yes. The batch API is 50% cheaper than standard requests.
What is the context window of GPT-5.6 Luna?
1,050,000 tokens, with up to 128,000 output tokens. Prompts over 272,000 tokens are billed at $0.40 input and $1.80 output for the whole request.