BATCHIN MODEL CATALOG · OPEN & MOE REASONING MATRIX · OPENAI-COMPATIBLE APIREALTIME BENCHMARKS · CRYPTOGRAPHIC RECEIPTS

Open & MoE Model Matrix · High-Throughput Gateway

Next-Gen Open & MoE Model Catalog

Use the models shown as available in the live catalog through documented compatible endpoints, with cryptographic proof when the request returns a receipt.

OpenAI-Compatible Gateway EndpointLive

https://api.batchin.tech/v1

Showing 4 listed models (availability is shown on each card)

ByteDance

doubao-seedance-2-0-260128

Available

Doubao Seedance 2.0 Turbo

Turbo Video

⚡ Direct GPU⏱ Async Queue

💎 Pro🚀 Turbo💰 Economy🛡️ Failover

Accelerated Seedance 2.0 video generation engine with high rendering speed and crisp visual consistency.

Context: Prompt & Keyframe
Max Output: 1080p Video
Public Pricing: $0.055 / second

Proprietaryvideodoubaofast

View Model & Endpoints

Kling AI

kling-v3

Available

Kling v3

Physical Dynamics

⚡ Direct GPU⏱ Async Queue

💎 Pro🚀 Turbo💰 Economy🛡️ Failover

Kuaishou Kling v3 video generation model featuring complex physics simulation and fluid real-world mechanics.

Context: Prompt & Keyframe
Max Output: 1080p Video
Public Pricing: $0.063 / second

Vendor Commercial Licensevideoklingflagship

View Model & Endpoints

Kling AI

kling-v3-omni

Available

Kling v3 Omni

Audio-Visual Omni

⚡ Direct GPU⏱ Async Queue

💎 Pro🚀 Turbo💰 Economy🛡️ Failover

Omni-modal video model synthesizing synchronized sound effects and motion pictures in one unified pass.

Context: Prompt & Keyframe
Max Output: 1080p Video with Audio
Public Pricing: $0.066 / second

Vendor Commercial Licensevideoklingomni

View Model & Endpoints

MiniMax

minimax-h3

Available

MiniMax H3 Video

Digital Human

⚡ 320+ t/s⏱ 140ms TTFT

💎 Pro🚀 Turbo💰 Economy🛡️ Failover

MiniMax H3 video synthesis engine specializing in realistic character performance and natural facial expressions.

Context: Prompt & Image
Max Output: 1080p Video
Public Pricing: $0.043 / second

Proprietaryvideominimaxavatar

View Model & Endpoints

1-Minute Drop-In Integration

Zero Codebase Refactoring. Point baseURL to Switch.

Compatible with documented OpenAI API routes. Drop into Next.js, LangChain, Cursor IDE, and LlamaIndex where the endpoint contract matches your workload.

app/api/chat/route.tstypescript

import { createOpenAI } from '@ai-sdk/openai';
import { streamText } from 'ai';

// Drop-in replace baseURL & apiKey
const batchin = createOpenAI({
  baseURL: 'https://api.batchin.tech/v1',
  apiKey: process.env.BATCHIN_API_KEY,
});

export async function POST(req: Request) {
  const { messages } = await req.json();

  const result = streamText({
    model: batchin('deepseek-v4-pro'),
    messages,
  });

  return result.toDataStreamResponse();
}

🔒

Zero Data Retention (ZDR) Enforced by DefaultYour code and prompts are processed strictly in ephemeral GPU memory. We never log, store, or train on proprietary inputs.

SOC-2 / GDPR Ready·RAM-Only Execution

import { createOpenAI } from '@ai-sdk/openai'; import { streamText } from 'ai'; // Drop-in replace baseURL & apiKey const batchin = createOpenAI({ baseURL: 'https://api.batchin.tech/v1', apiKey: process.env.BATCHIN_API_KEY, }); export async function POST(req: Request) { const { messages } = await req.json(); const result = streamText({ model: batchin('deepseek-v4-pro'), messages, }); return result.toDataStreamResponse(); }