minirouter.sh
Open navigation
Get a key

OpenAI

GPT-6.1 Terra

OpenAI's Terra update for everyday writing, document tasks and code.

Get a MiniRouter keySee the evidence
successor to gpt-5.6-terratext inputtext output

Replaces GPT 5.6 Terra: input $2.1 → $1.05 per 1M (-50%), output $12.6 → $5.25 per 1M (-58%), same context window.

Run this model

openai/gpt-6.1-terra

Use an endpoint supported by this model.

Get a key for this setup →
Thinking guide →
const response = await fetch('https://api.minirouter.sh/v1/responses', {  method: 'POST',  headers: {    Authorization: `Bearer ${process.env.MINIROUTER_KEY}`,    'Content-Type': 'application/json',  },  body: JSON.stringify({    model: 'openai/gpt-6.1-terra',    input: 'Why is the sky blue?',    max_output_tokens: 1024,  }),}) const data = await response.json()console.log(data.output)
Read docs →

MiniRouter accepts text input for this launch. Use Responses for tool calling. Start with an explicit output budget; reasoning and the answer share that budget. Check the route's supported parameters before migrating.

Higher rates above 272K input tokensPrices shown include MiniRouter's markup. Above 272,000 input tokens, OpenAI charges twice the input and cache rates and 1.5 times the output rate for the full request. Reasoning counts as output. Final charges follow provider-reported usage. Source ↗

Model overview

Input / 1M
$1.05
All-in MiniRouter rate
Output / 1M
$5.25
All-in MiniRouter rate
Context
1.1M
1,050,000 tokens
Max output
128K
tokens
Route effort
none → high
medium by default
Tools
Responses
Tool calling requires Responses
Announced
26 Oct 2026
publisher release
Evaluate completed work

Give Terra a task you can check.

Start with a proposal, document excerpt or small coding task. Keep the input and acceptance checks focused so you can compare the result with your current model.
Read the release analysis

A practical evaluation

Documents
Verify the detailsCompare extracted fields with the original text.
Writing
Check the briefReview accuracy, tone and missing information.
Workload focus: OpenAI announcement ↗. Evaluation suggestions are MiniRouter's.
View chart data
Suggested Terra workload checks
TaskProvideVerify
Extract document fieldsSource text and the required fieldsAmounts, dates and missing information
Write a small functionRequirements and edge casesRun tests and inspect error handling
Revise a proposalA draft, audience and constraintsFacts, clarity and coverage of the brief
Request options

Choose effort for the task.

Start with none, low, medium or high reasoning effort, as advertised by the route. Medium is the publisher default. Tool calling requires Responses.
OpenAI model documentation
  1. [ 01 ]

    Begin with a bounded request

    Measure a short task before increasing the input or output budget. Compare correct results, latency and total cost.

  2. [ 02 ]

    Supply the execution environment

    Your application runs tool calls and returns their results. Provide the tools, permissions and acceptance checks the task needs.

  3. [ 03 ]

    Compare against your current model

    Keep prompts and acceptance checks consistent. For difficult coding or research, also evaluate Sol or Astra.

Route

One route, standard clients.

Authenticate with a MiniRouter bearer key. Caller-provided upstream credentials are not used on this route.
Read model setup docs
Base URLhttps://api.minirouter.sh/v1
Model IDopenai/gpt-6.1-terra
Endpoints/v1/chat/completions/v1/messages/v1/responses
Parametersmax_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning
Structured outputNot enforced; a requested format is dropped and the answer is plain text.
ModalitiesInput: text · Output: text

Configured providers. Priority follows the live catalog order.

ProviderPriorityInput / 1MOutput / 1MParametersAccess
vercel
1$1.05$5.25max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoningMiniRouter balance

Every model, one key.

Get an API keyRead the docs