GPT-6.1 Terra

openai/gpt-6.1-terra · by OpenAI · decoder-only-transformer

Pricing — 1 offering(s)

OpenAI

About this offering: OpenAI's GPT-6.1 Terra, the "fast and efficient" tier of the GPT-6 family between GPT-6.1 Sol and GPT-6 Luna, launched 2026-10-26 at $1 input and $5 output per 1M tokens, with cached input at $0.05. OpenAI aims it at visual reasoning, precise computer use and natural writing. Batch is half price ($0.50 / $2.50). Flex is also 50% of Standard, Fast mode is 2x Standard ($2 / $10), and regional processing adds 10% where available. Prompts over 272K input tokens cost 2x input and 1.5x output for the whole request (OpenAI pricing and model pages, checked 2026-10-26).

Input tokens

$1.00 / 1M tokens (input) Current 2026-10-26 → present

Output tokens

$5.00 / 1M tokens (output) Current 2026-10-26 → present

Standard processing, short-context rate. Prompts over 272K input tokens are billed at $7.50 per 1M output…

Standard processing, short-context rate. Prompts over 272K input tokens are billed at $7.50 per 1M output tokens for the whole request.

Cached input tokens

$0.05 / 1M tokens (cached input) Current 2026-10-26 → present

Cache writes

$1.25 / 1M tokens (cache write) Current 2026-10-26 → present

Batch input tokens

$0.50 / 1M tokens (input) Current 2026-10-26 → present

Batch output tokens

$2.50 / 1M tokens (output) Current 2026-10-26 → present

Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.

See how GPT-6.1 Terra fits into a cost-aware routing setup

Capability profile

How GPT-6.1 Terra rates across core capability dimensions, with the task-level evidence behind each rating.

context window Strong

1,050,000-token context window (922,000 max input), 128,000 max output tokens (developers.openai.com/api/docs/models/gpt-6.1-terra).

tool use Strong

OpenAI API docs: supports function calling, web search, file search, code interpreter, hosted shell, apply patch, skills, computer use, tool search and MCP via the Responses API. Chat Completions is supported, but tool calling requires the Responses API.

cost efficiency Strong

Third tier of the GPT-6 family ($1/$5 per 1M tokens, Standard, short context): half GPT-6.1 Sol, 10x GPT-6 Luna, and half the price of GPT-5.6 Terra ($2/$12). Cached input $0.05/1M; Batch $0.50/$2.50.

Ratings are estimated — limited independent data is available for this model.

Operator guidance

The fast, efficient tier of GPT-6, launched 2026-10-26 between GPT-6.1 Sol and GPT-6 Luna, and the successor to GPT-5.6 Terra at half its price. OpenAI aims it at visual reasoning, precise computer use and natural writing. Step up to GPT-6.1 Sol for complex coding and professional work, or down to GPT-6 Luna for high-volume, cost-sensitive tasks. It accepts text and image input only. Tool calling requires the Responses API.

Use cases

Visual reasoning on images, such as matching product photos to catalog entries or interpreting technical drawings, per OpenAI's model docs
Precise computer use: acting on application screens
Drafting and revising text

Limitations

Reasoning, coding, instruction-following, multilingual and speed ratings are left out. No benchmark was sourced for this entry, and none is inferred; OpenAI's positioning is a vendor description, not a cited benchmark.
Capability ratings are qualitative, not a single cited benchmark run