Verified November 2026

Home › Models › GPT-6.1 Terra

GPT-6.1 Terra API pricing

GPT-6.1 Terra is a model from OpenAI with a 1,050,000-token context window. Rates below are per 1,000,000 tokens, verified November 2026.

$1Input / 1M tokens
$5Output / 1M tokens
$0.05Cached input / 1M
1,050,000Context window

Price list

GPT-6.1 Terra rates in USD per 1M tokens, November 2026
Token classRate / 1MNotes
Input$1Prompt tokens not served from cache
Cached input$0.0595% below base input
Cache write$1.25Charged once when the prefix is stored
Output$55.0× the input rate
Long context input$2Above 272,000 input tokens
Long context output$7.50Same threshold
Batch API−50%Input and output, results within 24 h

Middle tier of the GPT-6.1 family: half the input price of GPT-6.1 Sol for lighter production traffic.

What GPT-6.1 Terra costs at three real workloads

Sticker prices rarely match the invoice. These three workloads use the rates above, with cache writes charged once per job and the batch discount applied only where the provider offers it.

WorkloadRequestsTokensEstimated cost
Support chat1,0004K in / 600 out$7
RAG with caching1,00050K in (45K cached) / 1K out$12.30
Nightly batch job10,00010K in / 2K out$100

Caching the 45K-token prefix saves about 78% on the RAG workload versus sending it uncached every call ($55 → $12.30). Batch mode halves the nightly job.

Where GPT-6.1 Terra sits in the market

Out of 45 models in this dataset, GPT-6.1 Terra ranks #19 cheapest by input rate, #21 by output rate, and #20 on a blended 1M-input-plus-250K-output workload.

ModelProviderInputOutputBlended
GPT-6.1 TerraOpenAI$1$5$2.25
Grok 4.3xAI Grok$1.25$2.50$1.88
Claude Haiku 4.5Anthropic$1$5$2.25
GPT-5.4 miniOpenAI$0.75$4.50$1.88

Blended cost = 1M input tokens + 250K output tokens at list price.

FAQ

How much does GPT-6.1 Terra cost per 1M tokens?

$1 per 1M input tokens and $5 per 1M output tokens on the standard tier, rising to $2 / $7.50 above 272,000 input tokens.

Is prompt caching cheaper on GPT-6.1 Terra?

Yes. Cached input bills at $0.05 per 1M tokens, 95.0% below the $1 base input rate, with a one-off cache write at $1.25 per 1M.

Does GPT-6.1 Terra support the Batch API?

Yes. Batch requests bill at roughly half the standard input and output rates: the nightly job above costs $200 at list price and about $100 in batch mode.

Keep reading

Run these numbers in the calculator