StackLift
OpenAI · updated Nov 22, 2026, 4:07 PM UTC

GPT-6.1 Terra API pricing.

GPT-6.1 Terra by OpenAI costs $1.00 per million input tokens and $5.00 per million output tokens, with a 1.1M-token context window. That puts it in the mid-range range of the models we track. A support chatbot handling 10,000 conversations a month would cost about $40.00 a month in API fees.

Price

What GPT-6.1 Terra costs per token

List prices, checked every hour. Blended assumes three input tokens for every output token. This model sits in the mid-range range of the models we track.

ModelProviderInput / 1MOutput / 1MBlended / 1MContext
GPT-6.1 TerraOpenAI$1.00$5.00$2.001.1M

Source: GPT-6.1 Terra in the OpenRouter model catalog. Check it against OpenAI's API pricing.

Specs

What GPT-6.1 Terra can do

From GPT-6.1 Terra's entry in the OpenRouter model catalog.

Reads
files (PDFs and documents), images and text
Writes
text
Context window
1.1M tokens
Longest answer
128K tokens
Tool calling
Yes: it can call functions and APIs you define
Structured output
Yes: answers can follow a JSON schema
Reasoning
Yes: it can think through steps before answering
Cached input
$0.05 per 1M tokens (95% off the input price)
Prompts over 272K tokens
$2.00 in / $7.50 out per 1M
Open weights
No: API access only

Monthly cost

What common workloads cost on GPT-6.1 Terra

API fees only, at list price. The assumptions are shown, so you can scale them to your own volume.

Customer support chatbot

$40.00 / month

10,000 conversations a month, ~1,500 in and ~500 out each: 15M input and 5M output tokens.

Knowledge-base Q&A (RAG)

$120 / month

20,000 questions a month, ~4,000 in and ~400 out each: 80M input and 8M output tokens.

Document summaries and extraction

$32.00 / month

2,000 documents a month, ~12,000 in and ~800 out each: 24M input and 1.6M output tokens.

Coding assistant for a team of 10

$60.00 / month

10 developers a month, 3.0M in and 0.6M out each: 30M input and 6M output tokens.

Hosting, a vector database, monitoring and the build itself are extra. The free StackLift estimate adds them for your exact scope.

Per request

What one request costs on GPT-6.1 Terra

A request costs its input tokens times the input price plus its output tokens times the output price. A typical assistant turn of 2,000 input and 500 output tokens on GPT-6.1 Terra: 2,000 × $1.00 ÷ 1M + 500 × $5.00 ÷ 1M = $0.0045.

RequestInput / output tokensOne request1,000 requests
Short chat reply500 / 200$0.0015$1.50
Typical assistant turn2,000 / 500$0.0045$4.50
Long document task20,000 / 1,500$0.028$27.50

As you grow

GPT-6.1 Terra cost at ten times less and ten times more

The same workloads at a tenth and at ten times the volume, at GPT-6.1 Terra's list price.

WorkloadA tenthTypicalTen times
Customer support chatbot$4.001,000 conversations$40.0010,000 conversations$400100,000 conversations
Knowledge-base Q&A (RAG)$12.002,000 questions$12020,000 questions$1,200200,000 questions
Document summaries and extraction$3.20200 documents$32.002,000 documents$32020,000 documents

Same price

GPT-6.1 Terra vs GPT-6.1 Terra Pro

Both cost $1.00 per million input tokens and $5.00 per million output tokens, so every figure above is the same for both. What differs:

  • GPT-6.1 Terra was added to the catalog on Oct 26, 2026, GPT-6.1 Terra Pro on Oct 26, 2026.

GPT-6.1 Terra Pro API pricing

Fit

When GPT-6.1 Terra is the right choice

GPT-6.1 Terra sits in the middle on price, a common default for assistants and agents that need solid reasoning at a predictable monthly cost.

Its 1.1M-token context window fits long contracts, codebases or document sets in one request, though sending that much text on every call raises the bill quickly.

GPT-6.1 Terra reads files (PDFs and documents) and images as well as text and can call tools and APIs, return structured JSON and reason through multi-step problems, so it can drive agents that act in your systems.

Many products mix models: a cheaper one for simple steps and a stronger one where quality matters. Test a shortlist on your own examples before you commit.

Save

Ways to pay less for GPT-6.1 Terra

  1. 1. Cache repeated instructions

    GPT-6.1 Terra charges $0.05 per million cached input tokens instead of $1.00. A 4,000-token system prompt sent with 10,000 requests a month costs $40.00 at the list price and about $2.00 when cached.

  2. 2. Route by difficulty

    Send simple requests to a cheaper model and keep the stronger one for the steps that need it.

  3. 3. Stay under 272K tokens a prompt

    Above 272K prompt tokens, GPT-6.1 Terra charges $2.00 per million input tokens instead of $1.00. Retrieve the passages a question needs rather than sending whole documents.

  4. 4. Ask for shorter answers

    Output costs 5 times as much as input on GPT-6.1 Terra, so a tight answer format (bullet points, JSON, a word limit) cuts the bill more than a shorter prompt.

Alternatives

Models priced closest to GPT-6.1 Terra

From other providers, nearest on blended price. Quality and speed differ by task: test the shortlist on your own examples.

ModelProviderInput / 1MOutput / 1MBlended / 1MContext
GPT-6.1 TerraOpenAI$1.00$5.00$2.001.1M
Qwen4 MaxQwen$1.43$4.28$2.141M
Gemini 3.8 FlashGoogle$0.825$4.13$1.651M
Gemini 4 HydrogenGoogle$1.50$7.50$3.001M
Mistral Medium 3.5Mistral$1.50$7.50$3.00262K
Qwen3.8 2.4T A95BQwen$2.00$6.00$3.001M

OpenAI

Other OpenAI models

The same provider's newest models, for a quicker or more capable option.

ModelProviderInput / 1MOutput / 1MBlended / 1MContext
GPT-6.2 Astra ProOpenAI$8.00$40.00$16.001.1M
GPT-6.2 AstraOpenAI$8.00$40.00$16.001.1M
GPT-6.2 Sol ProOpenAI$2.00$10.00$4.001.1M

Questions about GPT-6.1 Terra pricing

How much does GPT-6.1 Terra cost per 1,000 tokens?

$0.0010 per 1,000 input tokens and $0.0050 per 1,000 output tokens, from the list price of $1.00 and $5.00 per million.

Is GPT-6.1 Terra cheaper than Qwen4 Max?

Yes, on list price. GPT-6.1 Terra averages $2.00 per million tokens (3 parts input to 1 output) against $2.14 for Qwen4 Max. Quality and speed differ by task, so test both on your own examples.

What is GPT-6.1 Terra's context window?

1.1M tokens: the most text the model reads and writes in one request. Long documents beyond that are split, or retrieved in parts with RAG.

How much would a chatbot cost on GPT-6.1 Terra?

About $40.00 a month for 10,000 conversations a month, ~1,500 in and ~500 out each. Caching repeated instructions and routing simple questions to a cheaper model lower it further.

Does GPT-6.1 Terra support tool calling?

Yes. GPT-6.1 Terra can call functions and APIs you describe to it, which is what lets an AI agent look up data or take actions. It can also return answers that follow a JSON schema.

Can GPT-6.1 Terra read images or documents?

Yes. Besides text, GPT-6.1 Terra reads files (PDFs and documents) and images.

How long can GPT-6.1 Terra's answers be?

Up to 128K tokens per answer (about 96,000 words), within a 1.1M tokens context window.

Does GPT-6.1 Terra have prompt caching?

Yes. Input read from the cache costs $0.05 per million tokens, 95% less than the $1.00 list price, which suits long system prompts and shared context.

How do I estimate the AI cost of my own product?

Count the requests a month and the tokens in and out of each, then multiply by the prices here. StackLift's free estimate does this for your exact scope, alongside the cost to build it.

Build with it

Scope a product on GPT-6.1 Terra

Pick your features and integrations; the estimate returns the build cost, timeline and team, and the model's monthly running cost. Free, no signup.