GPT-6.1 Terra Pro

Provider: OpenAI US Official API price

Input price
$0.50
/ 1M tokens
Output price
$2.50
/ 1M tokens
Cache price
$0.025
/ 1M tokens (read)
Batch API
$0.50 / $2.50
input / output per 1M tokens
Context
1.05M tokens
Max output 128K tokens

Overview

OpenAI flagship reasoning model featuring built-in thinking mode and a 1050k context window for complex logic tasks.

Strengths

  • 1,050,000 token maximum context window
  • 128,000 token maximum output length
  • Supports vision, function-calling, and json-mode
  • Cached input drops to $0.025 per million tokens

Best use cases

  • Complex reasoning tasks requiring high output fidelity
  • Analyzing large codebases within the 1M context
  • Structured data extraction using json-mode
  • Multimodal analysis over extended documents

Pricing position

Priced at $0.50 input and $2.50 output per million tokens, matching DeepSeek R1 0528 input costs.

Caveats

Pro reasoning mode consumes significantly more tokens and cost per request than standard variants.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
128K tokens
Listed on OpenRouter
2026-10-26
Tracked since
2026-10-27
Last updated
2026-11-10

Features

Image inputFunction callingJSON outputReasoning

Price history

  • 2026-10-27 Added

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.17
1M (small app) 1 0.5 $1.75
10M (mid scale) 10 5 $17.50
100M (large) 100 50 $175.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from OpenAI

Similar-priced models

Source: OpenRouter API (openai/gpt-6.1-terra-pro)