OCI Generative AI

Access 9 OCI Generative AI models through Mastra's model router. Authentication is handled automatically using the OCI_GENAI_API_KEY environment variable.

Learn more in the OCI Generative AI documentation.

.env

OCI_GENAI_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: "oci/meta.llama-3.3-70b-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);
}

note

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

Models

9 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
oci/meta.llama-3.3-70b-instruct	128K						$0.72	$0.72
oci/meta.llama-4-maverick-17b-128e-instruct-fp8	512K						$0.72	$0.72
oci/meta.llama-4-scout-17b-16e-instruct	192K						$0.72	$0.72
oci/openai.gpt-oss-120b	128K						$0.15	$0.60
oci/openai.gpt-oss-20b	128K						$0.07	$0.30
oci/xai.grok-4.20-non-reasoning	1.0M						$1	$3
oci/xai.grok-4.20-reasoning	1.0M						$1	$3
oci/xai.grok-4.3	1.0M						$1	$3
oci/xai.grok-4.6	500K						$2	$6

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

Advanced configuration

Custom headers

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/openai/v1",
    id: "oci/meta.llama-3.3-70b-instruct",
    apiKey: process.env.OCI_GENAI_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic model selection

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
      ? "oci/xai.grok-4.6"
      : "oci/meta.llama-3.3-70b-instruct";
  }
});