Weights & Biases
透過 Mastra 的模型路由器存取 27 個 Weights & Biases 模型。系統會自動使用 WANDB_API_KEY 環境變數完成身分驗證。
如需進一步了解,請參閱Weights & Biases 文件。
.env
WANDB_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: 'wandb/JetBrains/Mellum2-12B-A2.5B-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)
}
資訊
Mastra 使用與 OpenAI 相容的 /chat/completions endpoint。部分 Provider 特有功能可能無法使用,詳情請參閱Weights & Biases 文件。
模型「模型」的直接連結
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|---|---|
wandb/deepseek-ai/DeepSeek-V3.1 | 161K | $0.55 | $2 | |||||
wandb/deepseek-ai/DeepSeek-V4-Flash | 1.0M | $0.14 | $0.28 | |||||
wandb/deepseek-ai/DeepSeek-V4-Flash-0731 | 262K | $0.13 | $0.28 | |||||
wandb/deepseek-ai/DeepSeek-V4-Pro | 1.0M | $1 | $3 | |||||
wandb/google/gemma-4-31B-it | 262K | $0.10 | $0.34 | |||||
wandb/ibm-granite/granite-4.1-8b | 131K | $0.05 | $0.10 | |||||
wandb/JetBrains/Mellum2-12B-A2.5B-Instruct | 131K | $0.05 | $0.10 | |||||
wandb/meta-llama/Llama-3.1-70B-Instruct | 128K | $0.80 | $0.80 | |||||
wandb/meta-llama/Llama-3.1-8B-Instruct | 128K | $0.22 | $0.22 | |||||
wandb/meta-llama/Llama-3.3-70B-Instruct | 128K | $0.71 | $0.71 | |||||
wandb/MiniMaxAI/MiniMax-M2.5 | 197K | $0.30 | $1 | |||||
wandb/MiniMaxAI/MiniMax-M3 | 262K | $0.23 | $0.96 | |||||
wandb/moonshotai/Kimi-K2.6 | 262K | $0.65 | $3 | |||||
wandb/moonshotai/Kimi-K2.7-Code | 262K | $0.71 | $4 | |||||
wandb/moonshotai/Kimi-K3 | 1.0M | $3 | $15 | |||||
wandb/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | 262K | $0.20 | $0.80 | |||||
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | 262K | $0.75 | $3 | |||||
wandb/openai/gpt-oss-120b | 131K | $0.03 | $0.17 | |||||
wandb/openai/gpt-oss-20b | 131K | $0.03 | $0.13 | |||||
wandb/OpenPipe/Qwen3-14B-Instruct | 33K | $0.05 | $0.22 | |||||
wandb/Qwen/Qwen3-30B-A3B-Instruct-2507 | 262K | $0.10 | $0.30 | |||||
wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct | 262K | $1 | $2 | |||||
wandb/Qwen/Qwen3.5-35B-A3B | 262K | $0.25 | $1 | |||||
wandb/Qwen/Qwen3.6-27B | 262K | $0.60 | $4 | |||||
wandb/Qwen/Qwen3.6-35B-A3B | 262K | $0.25 | $1 | |||||
wandb/zai-org/GLM-5.1 | 203K | $1 | $4 | |||||
wandb/zai-org/GLM-5.2 | 262K | $0.76 | $2 |
進階設定「進階設定」的直接連結
自訂標頭「自訂標頭」的直接連結
src/mastra/agents/my-agent.ts
const agent = new Agent({
id: 'custom-agent',
name: 'custom-agent',
model: {
url: 'https://api.inference.wandb.ai/v1',
id: 'wandb/JetBrains/Mellum2-12B-A2.5B-Instruct',
apiKey: process.env.WANDB_API_KEY,
headers: {
'X-Custom-Header': 'value',
},
},
})
動態選擇模型「動態選擇模型」的直接連結
src/mastra/agents/my-agent.ts
const agent = new Agent({
id: 'dynamic-agent',
name: 'Dynamic Agent',
model: ({ requestContext }) => {
const useAdvanced = requestContext.task === 'complex'
return useAdvanced ? 'wandb/zai-org/GLM-5.2' : 'wandb/JetBrains/Mellum2-12B-A2.5B-Instruct'
},
})