GPT-5.4 mini vs GPT-6.1 Terra

OpenAI has replaced GPT-5.4 mini with GPT-6.1 Terra. There is no quality verdict yet: the AIGROW small-business benchmark has not run GPT-6.1 Terra. On price, GPT-5.4 mini costs less: $0.75 in and $4.50 out per million tokens, against $1 in and $5 out for GPT-6.1 Terra.

Run GPT-6.1 Terra up to 75% below list price. $25 a month brings $110 of API credit and cancels any time; $10 once buys $40. For long documents, GPT-6.1 Terra reads up to 1.05M tokens at once and GPT-5.4 mini up to 400K. US dollars, standard rate, shortest context band. Price only: the benchmark has not run both. Prices checked 18 November 2026.

+23%1,000 support replieswhat GPT-6.1 Terra costs next to GPT-5.4 mini
GPT-5.4 mini
$4.05
GPT-6.1 Terra
$5.00
GPT-5.4 mini, per M tokens
$0.75 / $4.50
GPT-6.1 Terra, per M tokens
$1 / $5
3,000 tokens in and 400 out each, at list price.

Migrating from GPT-5.4 mini to its successor GPT-6.1 Terra raises input by a third and output by 11%, while cutting cache reads by a third. 1,000 support replies cost $5.00 on GPT-6.1 Terra and $4.05 on GPT-5.4 mini, so GPT-6.1 Terra costs 23% more.

What each one costs

The API price per million tokens and the cheapest app plan with each model, from the makers’ own pages. Each name opens that model’s full price page.

GPT-5.4 mini
On the OpenAI API, GPT-5.4 mini costs $0.75 per million input tokens and $4.50 per million output tokens.
GPT-6.1 Terra
On the OpenAI API, GPT-6.1 Terra costs $1 per million input tokens and $5 per million output tokens. AIGROW API credit runs GPT-6.1 Terra at $0.25 / $1.25 per million input / output tokens, up to 75% below list price. See API credit

$25 a month brings $110 of API credit and cancels any time; $10 once buys $40.

Side by side

Each maker’s published rate for its standard tier. Cached input is what a repeated prompt prefix costs once the provider has stored it.

GPT-5.4 mini and GPT-6.1 Terra: list prices and specifications
FactGPT-5.4 miniGPT-6.1 Terra
MakerOpenAIOpenAI
TierReplaced by GPT-6.1 TerraWorkhorses
Input, per M tokens$0.75$1.00
Output, per M tokens$4.50$5.00
Cached input$0.075$0.05
Context window400K1.05M
Released17 Mar 202626 Oct 2026
WeightsClosed weightsClosed weights

What a job costs on each

1,000 runs of each job at the two list prices. The gap moves from job to job because the models price input, output and cached context differently.

Cost of 1,000 runs of three jobs on GPT-5.4 mini and GPT-6.1 Terra
JobGPT-5.4 miniGPT-6.1 TerraCheaper
Support reply3,000 in, 400 out.$4.05$5.00GPT-5.4 mini, 19% less
Document summary25,000 in, 1,000 out.$23.25$30.00GPT-5.4 mini, 23% less
Agent task80,000 in (70,000 cached), 3,000 out.$26.25$28.50GPT-5.4 mini, 8% less

The token counts are ours, chosen to look like real work; the prices are the makers’. A model with no published cache price bills the agent task’s repeated context at its full input rate.

The small print

What each base rate leaves out, from the makers’ own pages: surcharges, discounts, promotions and cache pricing.

GPT-5.4 mini
Batch 50% off. Context 400,000 with max input 272K. OpenAI’s pricing page
GPT-6.1 Terra
OpenAI pitches it as a fast, efficient model for visual reasoning, computer use and writing. Requests above 272K input tokens bill 2x input and 1.5x output ($2 / $7.50, cached $0.10). Cache write $1.25 (30 min) or $2.50 (12 h). Batch and Flex 50% off, Fast mode 2x. Data residency adds 10%. Context 1,050,000 with max input 922K. OpenAI’s pricing page

Run GPT-6.1 Terra up to 75% below list price

AIGROW API credit covers GPT-6.1 Terra at published rates never above the list prices here, and $10 buys $40 of credit.

Prices checked 18 November 2026