GPT-5.6 Luna (batch)
- Input / output
- $0.10 / $0.60
- Providers
- 3
- Spread
- 4.0×
- 7 days
- 0%
- 30 days
- 0%
- Context
- 1.1M
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
| $0.10 | $0.60 | $0.225 | ref | ||||
Amazon Bedrockglobal | $0.20 | $1.20 | $0.45 | +100% | |||
| $0.20 | $1.20 | $0.45 | +100% | ||||
| $0.20 | $1.20 | $0.45 | +100% | ||||
OpenAIfast | $0.40 | $2.40 | $0.90 | +300% |
- OpenAICheapestflex$0.225$0.10 in · $0.60 outref vs ref1.1M ctx100% uptime
- global$0.45$0.20 in · $1.20 out+100% vs ref1.1M ctx100% uptime
- $0.45$0.20 in · $1.20 out+100% vs ref1.1M ctx89.9% uptime
- $0.45$0.20 in · $1.20 out+100% vs ref1.1M ctx100% uptime
- fast$0.90$0.40 in · $2.40 out+300% vs ref1.1M ctx100% uptime
Blended = (3 × input + output) / 4. Ref $0.225 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
No provider has changed its price since tracking began on Oct 3, 2026.
Long-context pricing
| Offered by | Prompt size | Input | Output |
|---|---|---|---|
| OpenAI (flex) | base | $0.10 | $0.60 |
| > 272K | $0.20 | $0.90 | |
| Amazon Bedrock (global), Azure +1 | base | $0.20 | $1.20 |
| > 272K | $0.40 | $1.80 | |
| OpenAI (fast) | base | $0.40 | $2.40 |
| > 272K | $0.80 | $3.60 |
Other pricing
| Offered by | Cache read | Cache write | Web search |
|---|---|---|---|
| OpenAI (flex) | $0.01 | $0.125 | $0.01 |
| Amazon Bedrock (global), Azure +1 | $0.02 | $0.25 | $0.01 |
| OpenAI (fast) | $0.04 | $0.50 | $0.01 |
Changes
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
- ListedNow served,Listed
About
The cheapest provider for GPT-5.6 Luna (batch) is OpenAI at $0.225 per 1M tokens (blended), charging $0.10 per 1M input and $0.60 per 1M output tokens. 3 providers serve it; the most expensive charges 4.0× the typical price. Context window: 1.1M tokens. Prices tracked since Oct 3, 2026.
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...
- Released
- Jul 9, 2026
- First tracked
- Oct 3, 2026
- Canonical slug
- openai/gpt-5.6-luna-20260709