← All models
GPT 5.6 Terra
gpt-5.6-terraopenaiAvailableReleased 2026-07-09GPT-5.6 mid-tier that balances intelligence and cost — roughly the former mini class. Strong default for everyday agentic coding, production workflows, and scaled API usage without flagship pricing.
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 | $2.00/M | $12.00/M | $0.200/M | $2.50/M |
| MeridianLowest | 0.3x | $0.600/M | $3.60/M | $0.060/M | $0.750/M |
| Basalt | Pending | — | — | — | — |
/v1/responsesAvailableGuides and comparisons
- Choosing a coding model: a filter, not a ranking
- Choosing among the eight OpenAI ids
- Claude Sonnet 5 vs GPT 5.6 Sol: price, context, and the switching cost
- Running Codex CLI against token-share.app
- GPT 5.6 Luna at 0.3×: when the higher multiplier still costs less
- GPT 5.6 Sol vs Terra: the same envelope at 2.5× the price
- OpenAI-compatible API setup: your first request
- The /v1/responses route: what it is and which ids use it
- Prompt caching: cutting cost on a repeated prefix
- Streaming responses across the three route shapes
- Switching from OpenAI direct: migrating an existing integration