Synthetic
Access 20 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);
}
Mastra uses the OpenAI-compatible /chat/completions
endpoint. Some provider-specific features may not be available. Check the Synthetic documentation for details.
Models
Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
---|---|---|---|---|---|---|---|---|
synthetic/hf:Qwen/Qwen3-235B-A22B-Instruct-2507 | 256K | $0.20 | $0.60 | |||||
synthetic/hf:Qwen/Qwen2.5-Coder-32B-Instruct | 33K | $0.80 | $0.80 | |||||
synthetic/hf:Qwen/Qwen3-Coder-480B-A35B-Instruct | 256K | $2 | $2 | |||||
synthetic/hf:Qwen/Qwen3-235B-A22B-Thinking-2507 | 256K | $0.65 | $3 | |||||
synthetic/hf:meta-llama/Llama-3.1-70B-Instruct | 128K | $0.90 | $0.90 | |||||
synthetic/hf:meta-llama/Llama-3.1-8B-Instruct | 128K | $0.20 | $0.20 | |||||
synthetic/hf:meta-llama/Llama-3.3-70B-Instruct | 128K | $0.90 | $0.90 | |||||
synthetic/hf:meta-llama/Llama-4-Scout-17B-16E-Instruct | 328K | $0.15 | $0.60 | |||||
synthetic/hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | 524K | $0.22 | $0.88 | |||||
synthetic/hf:meta-llama/Llama-3.1-405B-Instruct | 128K | $3 | $3 | |||||
synthetic/hf:moonshotai/Kimi-K2-Instruct | 128K | $0.60 | $3 | |||||
synthetic/hf:moonshotai/Kimi-K2-Instruct-0905 | 262K | $1 | $1 | |||||
synthetic/hf:zai-org/GLM-4.5 | 128K | $0.55 | $2 | |||||
synthetic/hf:deepseek-ai/DeepSeek-R1 | 128K | $0.55 | $2 | |||||
synthetic/hf:deepseek-ai/DeepSeek-R1-0528 | 128K | $3 | $8 | |||||
synthetic/hf:deepseek-ai/DeepSeek-V3.1-Terminus | 128K | $1 | $1 | |||||
synthetic/hf:deepseek-ai/DeepSeek-V3 | 128K | $1 | $1 | |||||
synthetic/hf:deepseek-ai/DeepSeek-V3.1 | 128K | $0.56 | $2 | |||||
synthetic/hf:deepseek-ai/DeepSeek-V3-0324 | 128K | $1 | $1 | |||||
synthetic/hf:openai/gpt-oss-120b | 128K | $0.10 | $0.10 |
Advanced Configuration
Custom Headers
const agent = new Agent({
name: "custom-agent",
model: {
url: "https://api.synthetic.new/v1/chat/completions",
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:Qwen/Qwen2.5-Coder-32B-Instruct"
: "synthetic/hf:Qwen/Qwen3-235B-A22B-Instruct-2507";
}
});