# GPT-6.1 Terra

> GPT-6.1 Terra is OpenAI's fast, efficient model for visual reasoning, precise computer use and clear, natural writing. It has configurable reasoning, tool use, image input and a 1.05M-token context window.

**ID**: `openai/gpt-6.1-terra`  
**Creator**: OpenAI  
**Category**: multimodal  
**Context**: 1.1M tokens  
**Input**: $0.10/M (was $1.00/M, 90% off)  
**Output**: $0.50/M (was $5.00/M, 90% off)  
**Released**: 2026-10-26  
**Web page**: https://anyrouter.dev/model/openai/gpt-6.1-terra

**Input modalities**: text, image  
**Output modalities**: text  

**Tokenizer**: GPT

**Capabilities**: chat, reasoning, streaming, function-calling, vision

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "openai/gpt-6.1-terra",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| openai-byok | $0 | $0 |
| vercel-byok | $0 | $0 |
| openrouter-byok | $0 | $0 |
| nousresearch-byok | $0 | $0 |
| beatapi-byok | $0 | $0 |
| tokenharbor-byok | $0 | $0 |
| aihubmix-byok | $0 | $0 |
| zenmux-byok | $0 | $0 |
| llmgateway-byok | $0 | $0 |
| requesty-byok | $0 | $0 |
| phala-byok | $0 | $0 |
| infron-byok | $0 | $0 |
| getvibe-byok | $0 | $0 |
| aimlapi-byok | $0 | $0 |
| llamport | $0.10/M (was $1.00/M, 90% off) | $0.50/M (was $5.00/M, 90% off) |
| llamport-byok | $0 | $0 |
| opengateway-byok | $0 | $0 |
| nano-gpt-byok | $0 | $0 |
| edenai-byok | $0 | $0 |
| ofox-byok | $0 | $0 |
| abacus-byok | $0 | $0 |
| fluence-byok | $0 | $0 |
| cortecs-byok | $0 | $0 |
| jiekou-byok | $0 | $0 |

## Benchmarks

- **GPQA Diamond**: 0.9
- **SciCode**: 0.6
- **OTIS Mock AIME**: 1.0
- **SimpleQA (verified)**: 0.6

Benchmark data from [Epoch AI](https://epoch.ai/benchmarks) (CC-BY 4.0).

## Model card

- Native context: 1050000 tokens [1]
- Training cutoff: 2026-06 [1]

### Strengths [1]

- Visual reasoning such as matching product photos and reading technical drawings
- Precise computer use, acting on application screens
- Clear, natural writing and revision

### Known limits [1]

- Tool calling requires the Responses API
- No audio or video input

### Use cases [1]

- Screenshot and drawing interpretation
- Computer-use agents
- Drafting and revising text

### API notes [1]

- reasoning.effort supports none, low, medium (default), high, xhigh, max
- Prompts over 272K input tokens are priced at 2x input and 1.5x output

### Links

- docs: https://developers.openai.com/api/docs/models/gpt-6.1-terra
- pricing: https://developers.openai.com/api/docs/pricing

### Sources

1. [GPT-6.1 Terra model page](https://developers.openai.com/api/docs/models/gpt-6.1-terra) (accessed 2026-10-27)

## Source

- Upstream docs: https://developers.openai.com/api/docs/models/gpt-6.1-terra
