Primary use stated or inferred cautiously from official documentation.
O
OPENAI / gpt-6.1-terra
GPT‑6.1 Terra
Proprietary OpenAI model released on October 26, 2026 for interpreting images, using applications and writing text. It accepts text and images and returns text; generating images through a tool is not a native output modality. It is available through the API as gpt-6.1-terra and in ChatGPT Work and Codex depending on the plan. It is not released as a downloadable checkpoint.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | gpt-6.1-terra |
|---|---|
| Model type | Text and reasoning · Code · Vision and documents |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 26 OCT 2026 |
| Knowledge cutoff | 01 JUN 2026 |
| Entrance | Text · Image |
| Exit | Text |
| Context window | 1,050,000 tokens |
| maximum output | 128,000 tokens |
| Reasoning | none, low, medium, high, xhigh, and max effort |
| Published tools | Features · Web search · File search · Code execution · Computer use · MCP |
| Structured Outings | Supported |
| Batch processing | Compatible · 50% discount |
| Prompt cache | Supported |
| Fine-tuning | Not compatible |
| Verified platforms | OpenAI API |
Reading invoices, comparing photographs, interpreting drawings and automating bounded tasks. The default effort is medium; none disables configurable reasoning. The documentation lists a 1,050,000-token context and up to 128,000 output tokens. Compare accuracy, latency and cost per task using the same documents and tools.
Tool calling requires the Responses API. Native audio and video modalities and fine-tuning are not supported. Computer-executor permissions should be limited to the task; interpreting a screen does not guarantee successful action completion. The stated knowledge cutoff is June 1, 2026, rather than the release date.
03 / CAPABILITIES
What it can do
Orientation
Reading invoices, comparing photographs, interpreting drawings and automating bounded tasks. The default effort is medium; none disables configurable reasoning. The documentation lists a 1,050,000-token context and up to 128,000 output tokens. Compare accuracy, latency and cost per task using the same documents and tools.
Context
1.050.000 tokens · 128.000 tokens
Tools and integration
Functions · Web search · File search · Code execution · Computer use · MCP
Access
OpenAI API · Responses and Chat Completions
Input modalities
TextImage
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 1.00 USD / 1 M tokens | Standard API rate |
| Cached input | USD 0.05 / 1M tokens | Reading reused prefixes |
| Cache write or storage | USD 1.25 / 1M tokens | The condition varies by provider |
| Standard output | 5.00 USD / 1 M tokens | May include reasoning tokens |
| Batch input | 0.50 USD / 1 M tokens | Asynchronous processing |
| Batch output | 2.50 USD / 1 M tokens | Asynchronous processing |
Standard prices per million tokens: USD 1 input, USD 0.05 cached input and USD 5 output. Cache writes cost USD 1.25 for 30 minutes and USD 2.50 for 12 hours. Above 272,000 input tokens, the entire request is charged at 2× input and cache rates and 1.5× output rates. Batch and Flex cost 50% less; Fast costs twice as much. Regional processing adds 10%, and tools may incur additional charges.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
OpenAI reports 50.3% on Terminal-Bench 4.0 at max effort. This is a provider evaluation, not an Inferama reproduction or a guarantee for every repository. Model comparisons require the same harness, tools and effort. The system card documents safeguards and limitations; error rates from internal tests are not general accuracy measures.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| Terminal-Bench 4.0 | 50,3 % | Accuracy | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
GPT‑6.1 Terra
Version added to Inferama's verified catalog.
07 / SOURCES