Mistral

​

Chat models

​

Other modalities

• audio — 4 models
• embeddings — 4 models
• moderation — 1 models
• OCR / document processing — 7 models
• speech-to-text — 3 models
• text-to-speech — 2 models

​

Quickstart

import { Verlon } from '@verlon-ai/sdk';

const verlon = new Verlon({ apiKey: process.env.VERLON_API_KEY });

const response = await verlon.chat({
  gateId: process.env.GATE_ID,
  model: 'mistral-large-latest', // optional — overrides the gate's configured model
  data: {
    messages: [{ role: 'user', content: 'Hello!' }],
  },
});

console.log(response.content);

​

SDK compatibility

​

Streaming

for await (const chunk of verlon.chatStream({
  gateId: process.env.GATE_ID,
  data: { messages: [{ role: 'user', content: 'Tell me a joke.' }] },
})) {
  process.stdout.write(chunk.content ?? '');
}

​

What’s supported

​

How it works

1. You send a request in your chosen SDK’s format
2. Verlon receives — validates the gate, applies routing rules
3. Verlon translates to Mistral’s native format and dispatches to Mistral’s API
4. Mistral responds with its raw response
5. Verlon normalizes back to your SDK’s expected shape
6. You receive a response in the format your code already handles, with an added cost field

​

Errors

try {
  await verlon.chat({
    gateId: process.env.GATE_ID,
    data: { messages: [{ role: 'user', content: 'Hello!' }] },
  });
} catch (error) {
  // error.message carries the API's message,
  // e.g. 'Gate with ID "…" not found'
  console.error(error.message);
}

​

Full non-chat model list

​

Audio

​

Embeddings

​

Moderation

​

OCR / document processing

​

Speech-to-text

​

Text-to-speech

​

Related

• OpenAI · Anthropic · Google
• Verlon SDK reference — one SDK across every provider and modality
• Gates — set up routing rules and model configuration
• Bring your own key — use your own Mistral account for provider costs
• Mistral’s official docs ↗