OpenAI API pricing

GPT-6.1 terra API pricing

GPT-6.1 terra costs $1.00 per million input tokens and $5.00 per million output tokens on the OpenAI API, and $0.050 per million cached input tokens. Context window: 922k tokens. Updated .

Price per 1M tokensUS dollars
Input$1.00
Cached input$0.050
Output$5.00

What it costs in practice

  • One chat or extraction call (2,000 tokens in, 500 out): $0.0045
  • 1,000 such calls: $4.50
  • 1 million tokens at a typical 80% input / 20% output mix: $1.80

Abilities: image input, tool use, reasoning, JSON schema output. Batch, long-context, priority and regional prices differ; check the full table and the provider’s own pricing page before you commit.

Cheapest alternatives from other providers

ModelInputOutputContextTypical call ×1,000
Gemini 2.5 Flash Lite
Google
$0.10$0.401.0M$0.40
Claude Haiku 5.5
Anthropic
$0.10$0.501M$0.45
Qwen3.8 Flash
Alibaba (Qwen)
$0.15$0.47992k$0.54
Qwen3.8 Omni Flash
Alibaba (Qwen)
$0.15$0.47992k$0.54
GLM 5.3 Flash
Zhipu (GLM)
$0.15$0.501.0M$0.55
Zai GLM 5.3 Flash
Mistral
$0.15$0.501.0M$0.55

Other OpenAI models

ModelInputOutputContextTypical call ×1,000
GPT-5 nano
OpenAI
$0.050$0.40272k$0.30
GPT-6 luna
OpenAI
$0.10$0.50922k$0.45
GPT-4o mini
OpenAI
$0.15$0.60128k$0.60
GPT-4o mini search preview
OpenAI
$0.15$0.60128k$0.60
GPT-5.6 luna
OpenAI
$0.20$1.20922k$1.00
GPT-5.4 nano
OpenAI
$0.20$1.25272k$1.02

Questions

How much does GPT-6.1 terra cost?

GPT-6.1 terra costs $1.00 per million input tokens and $5.00 per million output tokens on the OpenAI API; cached input is $0.050 per million. A typical call with 2,000 tokens in and 500 out costs about $0.0045.

What is the context window of GPT-6.1 terra?

GPT-6.1 terra accepts up to 922,000 input tokens and returns up to 128,000 output tokens.

Is there a cheaper alternative to GPT-6.1 terra?

For a typical call, Gemini 2.5 Flash Lite (Google, $0.0004 per call), Claude Haiku 5.5 (Anthropic, $0.0004 per call), Qwen3.8 Flash (Alibaba (Qwen), $0.0005 per call) cost less and also support image input, tool use, reasoning, JSON schema output. Quality differs, so test on your own prompts.

Source: the open LiteLLM model price map (MIT), checked daily (data file).