OpenAI

GPT 5.6 Terra

OpenAI's next-generation general-purpose model balancing intelligence and cost, featuring long-context reasoning, multimodal understanding, and full agent tooling for enterprise AI, coding, automation, and professional knowledge work.

Modalities
Chat
Starting price
From $0.15 / call
Context
1.1M context

OpenAI

README

Supported Functionality

ItemSpecification
InputText, Image
OutputText
Context1,050,000 tokens
Max Output128,000 tokens
Vision✓ Supported
Function Calling✓ Supported

Description

GPT-5.6 Terra is the balanced model in OpenAI's GPT-5.6 family, released on July 9, 2026 for production workloads that value both intelligence and cost. It roughly corresponds to the mini tier in earlier GPT-5 families.

At a lower price than the flagship tier, the model retains a 1,050,000-token context window, a 128,000-token maximum output, six reasoning-effort levels, image understanding, function calling, and Structured Outputs. As part of the GPT-5.6 family, it also supports persisted reasoning, Programmatic Tool Calling, explicit prompt caching, multi-agent orchestration in beta, and Responses API tools for retrieval, code execution, computer interaction, MCP, and Skills.

Key Capabilities

  • Balanced Deep Reasoning: Delivers strong reasoning below flagship pricing for production tasks that require consistent quality at scale.
  • Configurable Reasoning Effort: Supports none, low, medium, high, xhigh, and max to control quality, latency, and consumption by task difficulty.
  • Software Engineering and Coding: Code Interpreter, Hosted Shell, Apply Patch, and Skills support code understanding, modification, execution, and verification.
  • Long-Context Processing: A 1,050,000-token context can hold large codebases, document collections, and persistent task state, with up to 128,000 output tokens.
  • Agent and Tool Orchestration: Function calling, Programmatic Tool Calling, MCP, tool search, and multi-agent orchestration support complex automated workflows.
  • Vision Understanding: Image input and original image detail support interface screenshots, charts, scanned documents, and high-resolution material.
  • Structured and Retrieval-Augmented Work: Structured Outputs, Web Search, and File Search can transform external information into reliable JSON Schema-compliant results.

Technical Strengths

FeatureBenefit
Intelligence-Cost BalanceCurrent rates of $2 per million input tokens and $12 per million output tokens provide strong capability for production deployments with quality and budget requirements.
Six Reasoning LevelsSimple tasks can use less reasoning for speed, while difficult tasks can receive more reasoning effort for higher quality.
1.05M-Token ContextProcesses large codebases and long source collections in one request, reducing information loss and engineering overhead from chunking.
Persisted ReasoningReuses reasoning state across turns and consecutive tool calls, reducing repeated computation and improving workflow continuity.
Programmatic Tool CallingAllows tools to be invoked during code execution, shortening round trips in complex agent tasks.
Broad Hosted Tool EcosystemWeb Search, File Search, Hosted Shell, Computer Use, MCP, and Skills cover a complete retrieval-to-action workflow.

Pricing

Tiered by input prompt tokens (incl. cache): once over the threshold, the whole request is billed at the higher tier.

Token Type
Short context
≤272K
Long context
>272K
input$1.5$2-25%$3$4-25%
output$9$12-25%$13.5$18-25%
cache_read$0.15$0.2-25%$0.3$0.4-25%
cache_write$1.875$2.5-25%$3.75$5-25%

More from OpenAI