Interfaze Beta
Interfaze Beta merges specialized DNN/CNN models with an LLM to handle deterministic developer tasks like OCR, scraping, classification, structured outputs, and web extraction. It supports 1M tokens input and 32K tokens output. On AI Gateway, pay $1.5 per million input tokens and $3.5 per million output tokens.
View API reference- Input and output price
- Input $1.50, Output $3.50, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'interfaze/interfaze-beta', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Interfaze Beta by Interfaze. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Interfaze Beta
Interfaze Beta
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Interfaze Beta through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'interfaze/interfaze-beta', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Interfaze Beta request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'interfaze/interfaze-beta', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. interfaze/interfaze-beta. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Interfaze Beta supports up to 32,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 1M-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
| — | URL, base64, Uint8Array | — | — | Sent as file parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'interfaze/interfaze-beta', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['interfaze'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'interfaze/interfaze-beta', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'interfaze/interfaze-beta', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);PDF input
Attach PDFs as file parts. Their contents count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'interfaze/interfaze-beta', messages: [ { role: 'user', content: [ { type: 'text', text: 'Summarize this document.' }, { type: 'file', mediaType: 'application/pdf', data: 'https://example.com/document.pdf', }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'interfaze/interfaze-beta', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingAbout Interfaze Beta
Interfaze built Interfaze Beta around a routing layer. Each request goes to whichever specialized model fits the task. Small CNN and DNN models handle perception work like OCR and object detection. An LLM handles language reasoning. Custom tools cover web search, a code sandbox, and configurable safety guardrails. The endpoint is a single OpenAI-compatible URL.
The context window is 1M tokens and maximum output is 32K tokens. Interfaze reports 70.7% on OCRBench V2 for the native OCR path and 98 to 99% accuracy on structured output generation. Inputs accepted include text, images, audio, files, and video. Reasoning is available for harder queries.
Task coverage includes OCR and document extraction, object detection driven by natural language prompts, web scraping (with handling for sites that block bots), speech-to-text with speaker diarization, translation across many languages, classification, structured output, text-to-SQL, and multimodal question answering.
Because the underlying mix of CNNs, DNNs, and an LLM stays opaque behind one endpoint, integration looks identical to any other chat-completions model. Send a prompt with optional image, audio, or file attachments and get back a response that matches your requested schema. See for product documentation and https://interfaze.ai/ for the model page.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Interfaze Beta is a beta release. It targets workloads where deterministic, parseable output matters more than open-ended conversation. If your pipeline lives or dies by JSON schema adherence, OCR fidelity, or reliable web scraping, Interfaze Beta is built for that shape. For free-form chat, code generation, or general reasoning, a general-purpose frontier model usually fits better.
- Configuration: Call Interfaze Beta through the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. Inputs cover text, images, audio, files, and video.
- Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Interfaze Beta
Best for
- OCR Pipelines: Document extraction workloads that need high field-level accuracy on scanned content
- Structured Output: API responses that downstream systems parse against a strict schema
- Web Extraction: Scraping workflows, including sites that block typical bots
- Multimodal Classification: Tasks that mix images, audio, files, or video alongside text
- Text-to-SQL: Natural-language queries translated into runnable SQL
Consider alternatives when
- General Chat: A general-purpose frontier model fits open-ended conversation better
- Code Generation: A coding-tuned model handles long code synthesis with more depth
- Production Stability: A stable release is a safer pick than a beta for critical paths
- Creative Writing: A model tuned for long-form prose serves narrative work more naturally
Copy link to headingConclusion
Interfaze Beta packages OCR, web extraction, structured output, and multimodal reasoning behind one OpenAI-compatible endpoint. Reach for it when deterministic output matters more than open-ended conversation.
Copy link to headingFrequently Asked Questions
What is Interfaze Beta?
Interfaze Beta is a hybrid AI system from Interfaze that routes each request to a specialized DNN or CNN model when one fits, and falls back to an LLM otherwise. It targets developer tasks like OCR, scraping, classification, structured outputs, and web extraction.
What is the context window and output limit?
The context window is 1M tokens and the maximum output is 32K tokens.
Which input modalities does Interfaze Beta support?
Text, images, audio, files, and video. The API stays OpenAI Chat Completions compatible across all of them.
How do I call Interfaze Beta through AI Gateway?
Set the model to
interfaze/interfaze-betain the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. AI Gateway handles authentication and routing. See https://interfaze.ai/ for the model page.What is the pricing?
On AI Gateway, Interfaze Beta costs $1.5 per million input tokens and $3.5 per million output tokens. Current rates appear on this page.
How well does Interfaze Beta handle structured output?
Interfaze reports 98 to 99% accuracy on structured output generation, which makes Interfaze Beta a fit for pipelines that parse responses against a schema.
Does Interfaze Beta support zero data retention?
Zero Data Retention is not currently available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
Your use is subject to Interfaze's Terms & Privacy Policies.