跳到主要内容
非官方简体中文翻译，内容版权归 Mastra 所有，遵循 Apache-2.0 许可。

DigitalOcean logoDigitalOcean

Access 103 DigitalOcean models through Mastra's model router. Authentication is handled automatically using the DIGITALOCEAN_ACCESS_TOKEN environment variable.

Learn more in the DigitalOcean documentation.

.env
DIGITALOCEAN_ACCESS_TOKEN=your-api-token
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: "digitalocean/alibaba-qwen3-32b"
});

// 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);
}
备注

Mastra uses the OpenAI-compatible /chat/completions endpoint. Some provider-specific features may not be available. Check the DigitalOcean documentation for details.

Models
Models的直接链接

ModelContextToolsReasoningImageAudioVideoInput $/1MOutput $/1M
digitalocean/alibaba-qwen3-32b33K$0.25$0.55
digitalocean/all-mini-lm-l6-v2256$0.01—
digitalocean/anthropic-claude-4.1-opus200K$15$75
digitalocean/anthropic-claude-4.5-sonnet200K$3$15
digitalocean/anthropic-claude-4.6-sonnet200K$3$15
digitalocean/anthropic-claude-5-sonnet1.0M$2$10
digitalocean/anthropic-claude-5.5-haiku1.0M$0.10$0.50
digitalocean/anthropic-claude-fable-51.0M$10$50
digitalocean/anthropic-claude-fable-5.11.0M$10$50
digitalocean/anthropic-claude-haiku-4.5200K$1$5
digitalocean/anthropic-claude-opus-4200K$15$75
digitalocean/anthropic-claude-opus-4.5200K$5$25
digitalocean/anthropic-claude-opus-4.6200K$5$25
digitalocean/anthropic-claude-opus-4.7200K$5$25
digitalocean/anthropic-claude-opus-4.81.0M$5$25
digitalocean/anthropic-claude-opus-51.0M$5$25
digitalocean/anthropic-claude-opus-5.51.0M$4$20
digitalocean/anthropic-claude-sonnet-41.0M$3$15
digitalocean/anthropic-claude-sonnet-5.51.0M$2$10
digitalocean/arcee-trinity-large-thinking128K$0.25$0.90
digitalocean/bge-m38K$0.02—
digitalocean/bge-reranker-v2-m38K$0.01—
digitalocean/deepseek-3.2164K$0.50$2
digitalocean/deepseek-4-flash1.0M$0.14$0.28
digitalocean/deepseek-r1-distill-llama-70b33K$0.99$0.99
digitalocean/deepseek-v3164K——
digitalocean/deepseek-v4-flash-07311.0M$0.14$0.28
digitalocean/deepseek-v4-pro1.0M$2$3
digitalocean/deepseek-v4-pro-08131.0M$1$4
digitalocean/deepseek-v4.1-flash1.0M$0.30$1
digitalocean/e5-large-v2512$0.02—
digitalocean/fal-ai/elevenlabs/tts/multilingual-v2———
digitalocean/fal-ai/fast-sdxl———
digitalocean/fal-ai/flux/schnell———
digitalocean/fal-ai/stable-audio-25/text-to-audio———
digitalocean/gemma-4-31B-it256K$0.18$0.50
digitalocean/glm-564K$1$3
digitalocean/glm-5.1164K$1$4
digitalocean/glm-5.2262K$1$4
digitalocean/glm-5.31.0M$1$4
digitalocean/glm-5.3-flash1.0M$0.15$0.50
digitalocean/gte-large-en-v1.58K$0.09—
digitalocean/kimi-k2.5262K$0.50$3
digitalocean/kimi-k2.6262K$0.95$4
digitalocean/kimi-k31.0M$3$15
digitalocean/llama-4-maverick128K$0.25$0.87
digitalocean/llama3-8b-instruct131K$0.20$0.20
digitalocean/llama3.3-70b-instruct128K$0.65$0.65
digitalocean/mimo-v2.5-pro262K$0.80$3
digitalocean/minimax-m2.566K$0.30$1
digitalocean/ministral-3-8b-instruct-2512262K——
digitalocean/mistral-3-14B262K$0.20$0.20
digitalocean/mistral-7b-instruct-v0.333K——
digitalocean/multi-qa-mpnet-base-dot-v1512$0.01—
digitalocean/nemotron-3-nano-30b262K——
digitalocean/nemotron-3-nano-omni66K$0.50$0.90
digitalocean/nemotron-3-ultra-550b131K$0.90$2
digitalocean/nemotron-3.5-super-vl1.0M$0.30$0.65
digitalocean/nemotron-nano-12b-v2-vl128K$0.20$0.60
digitalocean/nvidia-nemotron-3-super-120b1.0M$0.30$0.65
digitalocean/openai-gpt-4.11.0M$2$8
digitalocean/openai-gpt-4o128K$3$10
digitalocean/openai-gpt-4o-mini128K$0.15$0.60
digitalocean/openai-gpt-5400K$1$10
digitalocean/openai-gpt-5-mini400K$0.25$2
digitalocean/openai-gpt-5-nano400K$0.05$0.40
digitalocean/openai-gpt-5.1-codex-max400K$1$10
digitalocean/openai-gpt-5.2400K$2$14
digitalocean/openai-gpt-5.2-pro400K$21$168
digitalocean/openai-gpt-5.3-codex400K$2$14
digitalocean/openai-gpt-5.4400K$3$15
digitalocean/openai-gpt-5.4-mini400K$0.75$5
digitalocean/openai-gpt-5.4-nano400K$0.20$1
digitalocean/openai-gpt-5.4-pro1.1M$30$180
digitalocean/openai-gpt-5.51.0M$5$30
digitalocean/openai-gpt-5.6-luna1.1M$0.20$1
digitalocean/openai-gpt-5.6-sol1.1M$4$20
digitalocean/openai-gpt-5.6-terra1.1M$2$12
digitalocean/openai-gpt-6-1-sol1.1M$2$10
digitalocean/openai-gpt-6-astra1.1M$10$50
digitalocean/openai-gpt-6-luna1.1M$0.10$0.50
digitalocean/openai-gpt-6-sol1.1M$2$10
digitalocean/openai-gpt-image-1—$5$40
digitalocean/openai-gpt-image-1.5—$5$10
digitalocean/openai-gpt-image-2—$8$30
digitalocean/openai-gpt-oss-120b128K$0.10$0.70
digitalocean/openai-gpt-oss-20b128K$0.05$0.45
digitalocean/openai-o1200K$15$60
digitalocean/openai-o3200K$2$8
digitalocean/openai-o3-mini200K$1$4
digitalocean/qwen-2.5-14b-instruct131K——
digitalocean/qwen3-coder-flash262K$0.45$2
digitalocean/qwen3-embedding-0.6b8K$0.04—
digitalocean/qwen3-tts-voicedesign33K——
digitalocean/qwen3.5-397b-a17b131K$0.55$4
digitalocean/qwen3.8-max1.0M$2$6
digitalocean/stable-diffusion-3.5-large256$0.08—
digitalocean/wan2-2-t2v-a14b100$0.60—
98 available models

Model availability, capabilities, context windows, and pricing are sourced from models.dev and may change.

Advanced configuration
Advanced configuration的直接链接

Custom headers
Custom headers的直接链接

src/mastra/agents/my-agent.ts
const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://inference.do-ai.run/v1",
    id: "digitalocean/alibaba-qwen3-32b",
    apiKey: process.env.DIGITALOCEAN_ACCESS_TOKEN,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic model selection
Dynamic model selection的直接链接

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
      ? "digitalocean/wan2-2-t2v-a14b"
      : "digitalocean/alibaba-qwen3-32b";
  }
});
On this page