Inference API Overview

Ultra-fast inference for open-source and third-party models including DeepSeek V4.1 Flash, GLM 5.3, GLM 5.3 Flash, and Gemini 3.8 Flash with up to 1M context windows.

MatterAI provides ultra-fast inference for open-source and third-party models through a single, unified API. Access DeepSeek V4.1 Flash, GLM 5.3, GLM 5.3 Flash, and Gemini 3.8 Flash — all with up to 1M context windows, native tool calling, and automatic discounts.

Available Models

DeepSeek V4.1 Flash

Fast, cost-efficient model with 1M context, vision support, and strong coding performance.

GLM 5.3

Z.ai’s frontier open model for complex coding tasks and long-running agents.

GLM 5.3 Flash

Fast, low-cost open model for everyday coding tasks.

Gemini 3.8 Flash

Google’s fast, low-cost model for everyday coding tasks.

Key Features

• 1M Context Windows: Process documents, codebases, and conversations of any length
• Native Tool Calling: Built-in support for function calling and structured outputs
• Automatic Discounts: Automatic discounts on token costs across models
• Prompt Caching: Automatic caching of repeated prompt prefixes for up to 70% cost reduction
• Regional Data Residency: Your data never leaves your chosen region

Getting Started

Get API Key

Get API Key

Generate a new API key

API & SDK Integration

cURL

curl --request POST \
  --url https://api.matterai.so/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer MATTER_API_KEY' \
  --data '{
  "model": "zai/glm-5.3-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "What is Rust?"
    }
  ],
  "stream": false,
  "max_tokens": 1000,
  "temperature": 0,
  "top_p": 1
}'

Data Privacy

MatterAI never trains on your inputs. Your data is temporary, deleted automatically, and never leaves your chosen region.