GPT-5.6 Terra
LLM Provider / Model · Everyday work where intelligence and cost both matter
At a glance
| Input price | $2 |
| Output price | $12 |
| Cache price | $0.20 |
| Price tier | Mid |
| Context window | 1M+ |
| Max output | 128K |
| Context tier | 500K+ |
| Speed tier | Standard |
| Latency | medium |
| Knowledge cutoff | Feb 2026 |
| Modality | Multimodal (vision) |
| Model ID | gpt-5.6-terra |
| Provider | OpenAI |
| Benchmark | Balanced tier of the GPT-5.6 family |
| Released | Jul 2026 |
| Hosting | Closed/API |
| Capabilities | Vision, Tool use, Reasoning effort control, Streaming, Structured output, Prompt caching |
What GPT-5.6 Terra does
Vision, Tool use, Reasoning effort control, Streaming, Structured output, Prompt caching
Best for
Everyday work where intelligence and cost both matter
Works well with
Integration
Agent / Orchestration
Conflicts & caveats
- Kiro's spec mode is tuned for Claude models — GPT-5.6 Terra may work but spec-driven flows are best with Claude.
- Gemini CLI is locked to Google Gemini models — your LLM is GPT-5.6 Terra.
- Claude Code only works with Claude models — your LLM is GPT-5.6 Terra.
- Devin uses Cognition's proprietary model internally — your selected GPT-5.6 Terra will be ignored.
- OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected GPT-5.6 Terra will be ignored.
- Jules runs Gemini models internally — your selected GPT-5.6 Terra will be ignored.
- The Claude Code SDK is tuned for Claude models — GPT-5.6 Terra may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
- Lovable uses a fixed internal model — your selected GPT-5.6 Terra will be ignored.
- Replit Agent 3 uses its own model selection internally — your selected GPT-5.6 Terra will be ignored.
Build a full stack around GPT-5.6 Terra — Flowpicker shows compatibility warnings before you commit.
Open the stack planner →