← All models
GPT 6 Astra
gpt-6-astraopenaiAvailableReleased 2026-09-05OpenAI's GPT-6 tier for complex reasoning, coding, computer use, research, and document creation. Supports a 1.05M context window, adaptive reasoning, tools, and structured outputs.
TextToolsThinkingThinking: low, medium, high, xhigh, max
Pricing comparison
Each route's consumer price, and what multiple of the official list price it charges. Requests start at the cheapest route and only move to the next one when it fails, so you normally pay the top rate here. Lowest ready quote is marked. USD per million tokens.
| Route | Rate | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| Official | 1x | $10.00/M | $50.00/M | $1.00/M | $12.50/M |
| MeridianLowest | 0.2x | $2.00/M | $10.00/M | $0.200/M | $2.50/M |
| Basalt | 0.25x | $2.50/M | $12.50/M | $0.250/M | $3.13/M |
/v1/messagesAvailableGuides and comparisons
- Choosing a coding model: a filter, not a ranking
- Choosing among the eight OpenAI ids
- Claude Opus 5 vs GPT 6 Astra Stable: 4× the price for 5% more context
- GPT 6 Astra Stable: 1,050,000 tokens, on an Anthropic-shaped route
- Largest context models: who reaches 1M, and what it costs to use it
- Models for agents: tool calling, context growth and the bill
- Models for large codebases: when context size is the deciding factor
- The /v1/responses route: what it is and which ids use it
- Stable lanes explained: what stable-* buys and what it costs
- Tool calling compared: 27 models, three request shapes