OpenAI: GPT-6.1 Terra
gpt-6.1-terra- Input / Output-70%
- $1.00 / $5.00$0.30 / $1.50
- Context
- 1.05M
- Max output
- 128K
- Modalities
- VisionChat
- Capabilities
- Tool usePrompt CacheReasoning
About GPT-6.1 Terra
GPT-6.1 Terra is OpenAI's model for visual reasoning and clear writing. It is designed to interpret screenshots, match images to catalog entries, and explain technical drawings, while also drafting and revising text. Reasoning can be turned off for straightforward work or increased for harder tasks, which makes it useful when one workflow mixes quick edits with closer visual analysis.
Where it works well
- Interpret screenshots and technical drawings while following a text instruction.
- Draft and revise prose with explicit guidance about tone and meaning.
- Choose reasoning effort from none through max according to the task.
When to choose another model
- It returns text rather than generated images, so image creation needs an image model.
- Audio and video inputs are outside this model's documented modalities.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Text to textResponses APIPOST/v1/responsesAPI format:curl https://api.tokenlab.sh/v1/responses \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-xxx" \ -d '{ "model": "gpt-6.1-terra", "input": "Hello!" }'
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Input tokens <= 272K
per 1M tokens- Official price
- Input $1.00 / Output $5.00 / Cache read $0.05 / Cache write $1.25
- Verified price
- Input $0.30 / Output $1.50 / Cache read $0.015 / Cache write $0.375
- Discount
- -70%
Input tokens 272K-1.05M
per 1M tokens- Official price
- Input $2.00 / Output $7.50 / Cache read $0.10 / Cache write $2.50
- Verified price
- Input $0.60 / Output $2.25 / Cache read $0.03 / Cache write $0.75
- Discount
- -70%
Cache read
- Official price
- $0.05
- Verified price
- $0.015
- Discount
- -70%
Cache write
- Official price
- $1.25
- Verified price
- $0.375
- Discount
- -70%
Charged per call, only when the model uses the tool.
Web search
- Official price
- $0.01/search
- Verified price
- $0.003/search
- Discount
- -70%
| Official priceper 1M tokens | Verified priceper 1M tokens | Discount | |
|---|---|---|---|
| Input tokens <= 272K | Input $1.00 / Output $5.00 / Cache read $0.05 / Cache write $1.25 | Input $0.30 / Output $1.50 / Cache read $0.015 / Cache write $0.375 | -70% |
| Input tokens 272K-1.05M | Input $2.00 / Output $7.50 / Cache read $0.10 / Cache write $2.50 | Input $0.60 / Output $2.25 / Cache read $0.03 / Cache write $0.75 | -70% |
| Prompt cache pricing | |||
| Cache read | $0.05 | $0.015 | -70% |
| Cache write | $1.25 | $0.375 | -70% |
| Tool feesCharged per call, only when the model uses the tool. | |||
| Web search | $0.01/search | $0.003/search | -70% |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open GPT-6.1 Terra in Console with a prompt ready to edit or send.
Help me try gpt-6.1-terra with a short message at /v1/responses. Show the reply, latency, and cost.
Use cases
Best for- Vision
- Reasoning
Visual catalog matching
Compare a product photo with reference entries and explain which visible details support the closest match.
Technical drawing review
Read a diagram together with its written notes and explain the parts relevant to a specific question.
Focused text revision
Revise a draft for clarity and tone while preserving its facts, intended meaning, and stated length constraints.
Prompt examples
Compare this product photo with the supplied catalog images. Identify the closest match and explain the visible differences.
Explain this technical drawing in plain language. Separate what you can read from any details that remain unclear.
Revise this draft for a customer update. Keep the facts and requested action, and remove vague wording.
This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.
FAQ
What is GPT-6.1 Terra designed for?
It is designed for visual reasoning and clear writing. OpenAI lists image matching, technical drawing interpretation, and text revision among its uses. Choose it for work that combines visual material with a written instruction.
Can it read images and screenshots?
Yes. The documented input modalities include text and images, with text as the output. You can provide a screenshot or picture alongside a question; the response explains the visual content rather than creating an image.
Can I turn its reasoning off?
Yes. Its reasoning settings include none, low, medium, high, xhigh, and max. Use none for a straightforward task, or test a higher setting when the request requires a more careful analysis of the supplied material.
What kinds of output does it produce?
It produces text. Use it to explain visual information or write and revise prose. It does not provide image generation, speech output, or video output through its documented text response modality.
How much does GPT-6.1 Terra cost?
On TokenLab, GPT-6.1 Terra costs Input $0.30 / Output $1.50 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
What are the context window and output limit of GPT-6.1 Terra?
GPT-6.1 Terra accepts up to 1,050,000 tokens of context and returns up to 128,000 tokens in one response.
Which endpoint should GPT-6.1 Terra use?
Use https://api.tokenlab.sh/v1/responses for GPT-6.1 Terra. The request example below shows the matching code shape.
Which operations does GPT-6.1 Terra support?
GPT-6.1 Terra supports Text to text. Select an operation above to see its endpoint and request example.
Compare GPT-6.1 Terra
Sources
Reviewed Oct 28, 2026
