GPT-6.1 Terra
GPT-6.1 Terra is OpenAI's fast, cost-efficient GPT-6 model for visual reasoning, computer use, and everyday professional workflows.
Overview
Released October 26, 2026. Terra accepts text and image input, supports reasoning efforts from none to max, and has a 1.05M-token context window with up to 128K output tokens. Tool calling requires the Responses API. Its standard text-token rates are half those of GPT-6.1 Sol; actual costs depend on context length, cache retention, service tier, and tool use.
Model specifications
- Family
- GPT-6
- Context
- 1,050,000 tokens
- Input
- Text, Image
- Output
- Text
- Open weights
- No
- Capabilities
- Reasoning, Vision, Tool Use, Function Calling, Structured Output, Web Search, Code Execution, Computer Use, Image Generation
Recorded API token pricing
Reference rates in USD per 1 million tokens. Actual charges depend on the provider, service tier, context length, tools, and region.
- Input
- USD 1 / 1M tokens
- Cached input
- USD 0.05 / 1M tokens
- Output
- USD 5 / 1M tokens
Pricing caveats
Standard USD rates per 1M text tokens. Cache writes: $1.25 (30 min), $2.50 (12 h). For prompts above 272K input tokens, 2x input/cache and 1.5x output pricing apply to the full request. Batch/Flex 0.5x, Fast 2x, eligible regional processing +10%; tool fees may be separate.
Reviewed Oct 27, 2026 · Verify with provider documentation →