Synthetic
Access 21 Synthetic models through Mastra's model router. Authentication is handled automatically using the SYNTHETIC_API_KEY environment variable.
Learn more in the Synthetic documentation.
SYNTHETIC_API_KEY=your-api-key
import { Agent } from "@mastra/core";
const agent = new Agent({
name: "my-agent",
instructions: "You are a helpful assistant",
model: "synthetic/hf:Qwen/Qwen2.5-Coder-32B-Instruct",
});
// Generate a response
const response = await agent.generate("Hello!");
// Stream a response
const stream = await agent.stream("Tell me a story");
for await (const chunk of stream) {
console.log(chunk);
}
OpenAI Compatibility
Mastra uses the OpenAI-compatible /chat/completions endpoint. Some provider-specific features may not be available. Check the Synthetic documentation for details.
Models
| Model | Image | Audio | Video | Tools | Streaming | Context Window |
|---|---|---|---|---|---|---|
synthetic/hf:Qwen/Qwen3-235B-A22B-Instruct-2507 | ✗ | ✗ | ✗ | ✓ | ✗ | 256,000 |
synthetic/hf:Qwen/Qwen2.5-Coder-32B-Instruct | ✗ | ✗ | ✗ | ✗ | ✗ | 32,768 |
synthetic/hf:Qwen/Qwen3-Coder-480B-A35B-Instruct | ✗ | ✗ | ✗ | ✓ | ✗ | 256,000 |
synthetic/hf:Qwen/Qwen3-235B-A22B-Thinking-2507 | ✗ | ✗ | ✗ | ✓ | ✗ | 256,000 |
synthetic/hf:meta-llama/Llama-3.1-70B-Instruct | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:meta-llama/Llama-3.1-8B-Instruct | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:meta-llama/Llama-3.3-70B-Instruct | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:meta-llama/Llama-4-Scout-17B-16E-Instruct | ✓ | ✗ | ✗ | ✓ | ✗ | 328,000 |
synthetic/hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | ✓ | ✗ | ✗ | ✓ | ✗ | 524,000 |
synthetic/hf:meta-llama/Llama-3.1-405B-Instruct | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:moonshotai/Kimi-K2-Instruct | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:moonshotai/Kimi-K2-Instruct-0905 | ✗ | ✗ | ✗ | ✓ | ✗ | 262,144 |
synthetic/hf:zai-org/GLM-4.5 | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:zai-org/GLM-4.6 | ✗ | ✗ | ✗ | ✓ | ✗ | 200,000 |
synthetic/hf:deepseek-ai/DeepSeek-R1 | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:deepseek-ai/DeepSeek-R1-0528 | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:deepseek-ai/DeepSeek-V3.1-Terminus | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:deepseek-ai/DeepSeek-V3 | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:deepseek-ai/DeepSeek-V3.1 | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:deepseek-ai/DeepSeek-V3-0324 | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
synthetic/hf:openai/gpt-oss-120b | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
Advanced Configuration
Custom Headers
const agent = new Agent({
name: "custom-agent",
model: {
url: "https://api.synthetic.new/v1",
modelId: "hf:Qwen/Qwen2.5-Coder-32B-Instruct",
apiKey: process.env.SYNTHETIC_API_KEY,
headers: {
"X-Custom-Header": "value",
},
},
});
Dynamic Model Selection
const agent = new Agent({
name: "dynamic-agent",
model: ({ runtimeContext }) => {
const useAdvanced = runtimeContext.task === "complex";
return useAdvanced
? "synthetic/hf:zai-org/GLM-4.6"
: "synthetic/hf:Qwen/Qwen2.5-Coder-32B-Instruct";
},
});