Skip to main content
Providers

Synthetic

Use synthetic/<model> with VoltAgent's model router.

Quick start​

import { Agent } from "@voltagent/core";

const agent = new Agent({
  name: "synthetic-agent",
  instructions: "You are a helpful assistant",
  model: "synthetic/hf:MiniMaxAI/MiniMax-M2",
});

Environment variables​

  • SYNTHETIC_API_KEY

Provider package​

@ai-sdk/openai-compatible

This provider uses the OpenAI-compatible adapter.

Default base URL​

https://api.synthetic.new/v1

You can override the base URL by setting SYNTHETIC_BASE_URL.

Provider docs​

Models​

Show models (25)
  • hf:MiniMaxAI/MiniMax-M2
  • hf:MiniMaxAI/MiniMax-M2.1
  • hf:Qwen/Qwen2.5-Coder-32B-Instruct
  • hf:Qwen/Qwen3-235B-A22B-Instruct-2507
  • hf:Qwen/Qwen3-235B-A22B-Thinking-2507
  • hf:Qwen/Qwen3-Coder-480B-A35B-Instruct
  • hf:deepseek-ai/DeepSeek-R1
  • hf:deepseek-ai/DeepSeek-R1-0528
  • hf:deepseek-ai/DeepSeek-V3
  • hf:deepseek-ai/DeepSeek-V3-0324
  • hf:deepseek-ai/DeepSeek-V3.1
  • hf:deepseek-ai/DeepSeek-V3.1-Terminus
  • hf:deepseek-ai/DeepSeek-V3.2
  • hf:meta-llama/Llama-3.1-405B-Instruct
  • hf:meta-llama/Llama-3.1-70B-Instruct
  • hf:meta-llama/Llama-3.1-8B-Instruct
  • hf:meta-llama/Llama-3.3-70B-Instruct
  • hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
  • hf:meta-llama/Llama-4-Scout-17B-16E-Instruct
  • hf:moonshotai/Kimi-K2-Instruct-0905
  • hf:moonshotai/Kimi-K2-Thinking
  • hf:openai/gpt-oss-120b
  • hf:zai-org/GLM-4.5
  • hf:zai-org/GLM-4.6
  • hf:zai-org/GLM-4.7

Table of Contents