GPT-5.6 Terra: OpenAI's Mid-Tier GPT-5.6 Model, Reasoning Effort, Pricing and Limits

What GPT-5.6 Terra is

GPT-5.6 Terra is a large language model from OpenAI, released on 9 July 2026 as part of the GPT-5.6 family alongside GPT-5.6 Sol and GPT-5.6 Luna. OpenAI built the family in three tiers: Sol for frontier capability, Terra for a balance of intelligence and cost, and Luna for efficient high-volume work. OpenAI says Terra roughly matches the mini tier of earlier GPT-5 families. Its API ID is gpt-5.6-terra, which is also its only snapshot, and the general gpt-5.6 alias points to Sol rather than Terra. It takes text and images as input and returns text. On LMArena's text leaderboard GPT-5.6 Terra has 1468 Elo (rank 52, xhigh effort).

Context, output and reasoning

Terra has a 1.05M-token context window, with at most 922,000 input tokens and 128,000 output tokens per request, and a knowledge cutoff of 16 February 2026. It is a reasoning model, and its reasoning effort setting accepts none, low, medium, high, xhigh and max, with medium as the default. The GPT-5.6 release also brought programmatic tool calling, explicit prompt caching controls, persisted reasoning, the max effort level and Pro mode, plus multi-agent orchestration in beta for the Responses API.

Pricing

OpenAI charges $2 per million input tokens and $12 per million output tokens, with cached input at $0.20 per million. Those prices date from 30 July 2026, when OpenAI cut Terra's price by 20% and Luna's by 80%. Prompts longer than 272K input tokens are billed at twice the input rate and 1.5 times the output rate for the whole request. Cache writes cost 1.25 times the uncached input rate. For comparison, OpenAI's own table lists GPT-5.6 Sol at $4 and $20 per million tokens and GPT-5.4 Mini at $0.75 and $4.50. From 5 August 2026, Fast mode also accepts long-context requests over 272K tokens for all three GPT-5.6 models.

Endpoints and tools

Terra works through the Chat Completions, Responses and Batch endpoints. It does not support the Realtime, Assistants, fine-tuning, embeddings, image, video or audio endpoints. Supported features include streaming, structured outputs, function calling, file search, image input, web search and prompt caching. Through the Responses API it can use web search, file search, image generation, code interpreter, hosted shell, apply patch, skills, computer use, MCP and tool search. On Amazon Bedrock it is listed as openai.gpt-5.6-terra.

Rate limits

OpenAI sets rate limits by usage tier, which rises automatically as an account sends more requests and spends more. On the standard tiers, Terra starts at 5,000 requests and one million tokens per minute on the Build tier, with a batch queue limit of three million tokens. The Launch tier allows 10,000 requests and four million tokens per minute, and the Grow tier 15,000 requests and 40 million tokens per minute, with a batch queue limit of 15 billion tokens. The Launch tier's batch queue limit is 200 million tokens.

Official Resources