stepping stone AG
Access 15 stepping stone AG models through Mastra's model router. Authentication is handled automatically using the STONEY_API_KEY environment variable.
Learn more in the stepping stone AG documentation.
.env
STONEY_API_KEY=your-api-key
src/mastra/agents/my-agent.ts
import { Agent } from "@mastra/core/agent";
const agent = new Agent({
id: "my-agent",
name: "My Agent",
instructions: "You are a helpful assistant",
model: "stepping-stone/BAAI/bge-m3"
});
// 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);
}
note
Mastra uses the OpenAI-compatible /chat/completions endpoint. Some provider-specific features may not be available. Check the stepping stone AG documentation for details.
ModelsDirect link to Models
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|---|---|
stepping-stone/allenai/olmOCR-2-7B | 8K | $0.07 | $0.35 | |||||
stepping-stone/apertus-ai/Apertus-v1.5-8B | 131K | $0.02 | $0.12 | |||||
stepping-stone/BAAI/bge-m3 | 8K | $0.12 | — | |||||
stepping-stone/BAAI/bge-reranker-v2-m3 | 8K | $0.12 | — | |||||
stepping-stone/deepseek-ai/DeepSeek-V4-Flash-0731 | 524K | $0.54 | $2 | |||||
stepping-stone/google/gemma-4-31B-it | 164K | $0.30 | $1 | |||||
stepping-stone/lightonai/LightOnOCR-2-1B | 16K | $0.02 | $0.07 | |||||
stepping-stone/MiniMaxAI/MiniMax-M2.5 | 197K | $2 | $12 | |||||
stepping-stone/NVIDIA/NVIDIA-Nemotron-3-Super-120B-A12B | 131K | $2 | $6 | |||||
stepping-stone/openai/gpt-oss-120b | 131K | $0.48 | $2 | |||||
stepping-stone/opendatalab/MinerU2.5-2509-1.2B | 16K | $0.02 | $0.07 | |||||
stepping-stone/Qwen/Qwen3-Coder-Next | 262K | $0.40 | $2 | |||||
stepping-stone/Qwen/Qwen3.5-35B-A3B-FP8 | 131K | $0.20 | $1 | |||||
stepping-stone/Qwen/Qwen3.8-27B | 262K | $0.30 | $2 | |||||
stepping-stone/zai-org/GLM-5.3-Flash | 262K | $0.36 | $2 |
Model availability, capabilities, context windows, and pricing are sourced from models.dev and may change.
Advanced configurationDirect link to Advanced configuration
Custom headersDirect link to Custom headers
src/mastra/agents/my-agent.ts
import { Agent } from "@mastra/core/agent";
const agent = new Agent({
id: "custom-agent",
name: "custom-agent",
model: {
url: "https://llm.stoney-cloud.com/v1",
id: "stepping-stone/BAAI/bge-m3",
apiKey: process.env.STONEY_API_KEY,
headers: {
"X-Custom-Header": "value"
}
}
});
Dynamic model selectionDirect link to Dynamic model selection
src/mastra/agents/my-agent.ts
import { Agent } from "@mastra/core/agent";
const agent = new Agent({
id: "dynamic-agent",
name: "Dynamic Agent",
model: ({ requestContext }) => {
const useAdvanced = requestContext.task === "complex";
return useAdvanced
? "stepping-stone/zai-org/GLM-5.3-Flash"
: "stepping-stone/BAAI/bge-m3";
}
});