Model detail
GPT-6.1 Terra
GPT-6.1 Terra is an OpenAI reasoning model released on October 26, 2026, aimed at efficient visual reasoning, computer use and writing. It accepts text and images and returns text. Reasoning effort is configurable, and tool-calling workloads use the Responses API.
Model specs
- Model ID
-
gpt-6.1-terra
- Context length
- 1.05M
- Max output
- 128K
- I/O modalities
- Released
- 2026-10
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
OpenAI-compatible
/v1/chat/completionsPOST
03
Tiered pricing
Unit: /1M Tokens
| Tier | Input /1M Tokens | Output /1M Tokens | Cache read /1M Tokens | Cache write /1M Tokens |
|---|---|---|---|---|
| standard Length ≤ 272K | $1.0000 | $5.0000 | $0.0500 | $1.2500 |
| long_context Length > 272K | $2.0000 | $7.5000 | $0.1000 | $2.5000 |
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
OpenAI reasoning model released on October 26, 2026
GPT-6.1 Terra is an OpenAI reasoning model released on October 26, 2026, aimed at efficient visual reasoning, computer use and writing. It accepts text and images and returns text. Reasoning effort is configurable, and tool-calling workloads use the Responses API.
What should you check before using it?
1,050,000 context, 128,000 output tokens
GPT-6.1 Terra supports reasoning, tool calling, structured output, streaming, prompt caching, vision input and the OpenAI SDK. Knowledge cutoff: 2026-06-01. Released 2026-10-26.
Why use it through MixRoute?
GPT-6.1 Terra runs tools and structured output here
Tool calling and structured output run on that route as well. MixRoute serves GPT-6.1 Terra on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID gpt-6.1-terra and re-run your integration tests.
07
Capabilities & compatibility
Unconfirmed capabilities stay "Unknown," no guesses
Tool calling
GPT-6.1 Terra supports function and tool calls.
tools definition; the response returns tool_calls to execute and feed results back.
Structured output
GPT-6.1 Terra can produce JSON-formatted output on demand.
response_format: { type: "json_schema" } forces valid JSON output.
Streaming
GPT-6.1 Terra supports streamed responses.
stream: true streams tokens incrementally, so chat UIs render as they arrive.
Prompt caching
GPT-6.1 Terra supports prompt caching under supported routing conditions.
Vision input
GPT-6.1 Terra can process image inputs alongside text.
image_url content part alongside text messages.
OpenAI SDK
Call GPT-6.1 Terra through MixRoute's OpenAI-compatible endpoint.
base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.
08
Token cost estimator
Live estimate from this page's pricing, not an actual bill
Share of the same prefix read repeatedly, up to 100%
09
FAQ
Recorded results for GPT-6.1 Terra: aa_intelligence_index 48.0; aa_intelligence_index 45.0; aa_intelligence_index 44.0. Benchmark positions are a coarse filter only — run your own prompts against the candidate models before you commit, because ranking shifts with task shape and prompt style.
One endpoint, a testable decision
Test this model and alternate routes with the same request format
Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.