# Interfaze 1

> Interfaze 1 is the flagship Interfaze model for deterministic tasks such as OCR, extraction, and long documents. It takes text, images, audio, files, and video, and it returns text. The context window is 1,000,000 tokens.

**ID**: `interfaze/interfaze-1`  
**Creator**: interfaze  
**Category**: multimodal  
**Context**: 1M tokens  
**Input**: $1.50/M  
**Output**: $3.50/M  
**Released**: 2025-08-28  
**Web page**: https://anyrouter.dev/model/interfaze/interfaze-1

**Input modalities**: text, image, audio, file, video  
**Output modalities**: text  

**Tokenizer**: GPT

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

**Supported parameters**: max_tokens, temperature, top_p, top_k, tools, tool_choice, response_format, reasoning, reasoning_effort

## 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": "interfaze/interfaze-1",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| interfaze | $1.50/M | $3.50/M |
| interfaze-byok | $0 | $0 |

## Model card

- Native context: 1000000 tokens [1,4]
- License: Interfaze Terms of Service [2,5]

### Strengths [1,2]

- Highest-accuracy Interfaze model, with a 1,000,000-token context window for long documents and many files.
- Leads the smaller Interfaze model on OCRBench V2, GPQA Diamond, MMMLU, and text-to-SQL, per the vendor comparison.
- Accepts text, images, audio, files, and video, and returns text.

### Known limits [1,2]

- Reasoning is available and off unless the request turns it on.
- Max output is 32,000 tokens.
- Weights are not published.

### Use cases [2]

- OCR on dense or degraded documents, where the vendor says to pick this model.
- Long inputs such as large PDFs, long transcripts, or many files in one request.
- Structured extraction into a JSON schema through the chat completions API.

### API notes [1,4]

- OpenAI-compatible chat at https://api.interfaze.ai/v1 with Authorization Bearer.
- Wire id interfaze-1. It is the default model in the Interfaze SDK.
- Tools, structured output, and reasoning_effort are listed on GET /v1/models.

### Links

- announcement: https://interfaze.ai/blog/intefaze-beta-v1
- model card: https://interfaze.ai/docs/models/interfaze-1
- paper: https://arxiv.org/abs/2602.04101
- docs: https://interfaze.ai/docs/api/chat-completion
- pricing: https://interfaze.ai/pricing

### Sources

1. [interfaze-1 model card](https://interfaze.ai/docs/models/interfaze-1) (accessed 2026-11-22)
2. [Interfaze models](https://interfaze.ai/docs/models) (accessed 2026-11-22)
3. [Interfaze pricing](https://interfaze.ai/pricing) (accessed 2026-11-22)
4. [Interfaze GET /v1/models](https://api.interfaze.ai/v1/models) (accessed 2026-11-22)
5. [Interfaze Terms of Service](https://interfaze.ai/legal/terms) (accessed 2026-11-22)

## Source

- Upstream docs: https://interfaze.ai/docs/models/interfaze-1
