Prime Inference

Access 64 Prime Inference models through Mastra's model router. Authentication is handled automatically using the PRIME_API_KEY environment variable.

Learn more in the Prime Inference documentation.

.env

PRIME_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: "prime/anthropic/claude-fable-5"
});

// 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 Prime Inference documentation for details.

Models

64 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
prime/anthropic/claude-fable-5	1.0M						$10	$50
prime/anthropic/claude-fable-5.1	1.0M						$10	$50
prime/anthropic/claude-opus-4.6	1.0M						$5	$25
prime/anthropic/claude-opus-4.7	1.0M						$5	$25
prime/anthropic/claude-opus-4.8	1.0M						$5	$25
prime/anthropic/claude-opus-5	1.0M						$5	$25
prime/anthropic/claude-opus-5.5	1.0M						$4	$20
prime/anthropic/claude-sonnet-4.6	1.0M						$3	$15
prime/anthropic/claude-sonnet-5	1.0M						$2	$10
prime/deepseek/deepseek-v4-flash	1.0M						$0.44	$1
prime/deepseek/deepseek-v4-flash-0731	1.0M						$0.44	$1
prime/deepseek/deepseek-v4-pro	1.0M						$2	$4
prime/deepseek/deepseek-v4.1-flash	1.0M						$0.30	$1
prime/google/gemini-3-flash-preview	1.0M						$0.50	$3
prime/google/gemini-3.1-pro-preview	1.0M						$2	$12
prime/google/gemini-3.5-flash	1.0M						$2	$9
prime/google/gemini-3.6-flash	1.0M						$2	$8
prime/google/gemini-3.7-flash	1.0M						$1	$7
prime/google/gemini-3.8-flash	1.0M						$0.75	$4
prime/google/gemma-3-27b-it	131K						$0.12	$0.30
prime/meta-llama/llama-3.3-70b-instruct	131K						$1	$2
prime/mistralai/mistral-large-2512	262K						$0.50	$2
prime/mistralai/mistral-nemo	131K						$0.17	$0.17
prime/mistralai/mistral-small-2603	262K						$0.17	$0.66
prime/mistralai/mixtral-8x22b-instruct	66K						$2	$7
prime/moonshotai/kimi-k2-0905	262K						$0.60	$3
prime/moonshotai/kimi-k3	1.0M						$3	$17
prime/openai/gpt-4.1	1.0M						$2	$8
prime/openai/gpt-4.1-mini	1.0M						$0.40	$2
prime/openai/gpt-4.1-nano	1.0M						$0.10	$0.40
prime/openai/gpt-4o	128K						$3	$10
prime/openai/gpt-4o-mini	128K						$0.15	$0.60
prime/openai/gpt-5	400K						$1	$10
prime/openai/gpt-5-mini	400K						$0.25	$2
prime/openai/gpt-5-nano	400K						$0.05	$0.40
prime/openai/gpt-5.1	400K						$1	$10
prime/openai/gpt-5.2	400K						$2	$14
prime/openai/gpt-5.2-pro	400K						$21	$168
prime/openai/gpt-5.3-codex	400K						$2	$14
prime/openai/gpt-5.4	1.1M						$3	$15
prime/openai/gpt-5.4-mini	400K						$0.75	$5
prime/openai/gpt-5.4-nano	400K						$0.20	$1
prime/openai/gpt-5.4-pro	1.1M						$30	$180
prime/openai/gpt-5.5	1.1M						$5	$30
prime/openai/gpt-5.6-luna	1.1M						$0.20	$1
prime/openai/gpt-5.6-luna-pro	1.1M						$1	$6
prime/openai/gpt-5.6-sol	1.1M						$5	$30
prime/openai/gpt-5.6-sol-pro	1.1M						$5	$30
prime/openai/gpt-5.6-terra	1.1M						$3	$15
prime/openai/gpt-5.6-terra-pro	1.1M						$3	$15
prime/openai/gpt-6-astra	1.1M						$10	$50
prime/openai/gpt-6-luna	1.1M						$0.10	$0.50
prime/openai/gpt-6-sol	1.1M						$2	$10
prime/openai/gpt-6.1-sol	1.1M						$2	$10
prime/openai/gpt-oss-120b	131K						$0.35	$0.75
prime/openai/gpt-oss-20b	131K						$0.07	$0.30
prime/qwen/qwen3-coder-next	262K						$0.30	$2
prime/qwen/qwen3-vl-235b-a22b-instruct	262K						$0.30	$2
prime/qwen/qwen3-vl-30b-a3b-instruct	262K						$0.20	$0.70
prime/x-ai/grok-4.6	500K						$2	$6
prime/x-ai/grok-4.7	500K						$2	$5
prime/z-ai/glm-5.2	1.0M						$2	$5
prime/z-ai/glm-5.3	1.0M						$1	$4
prime/z-ai/glm-5.3-flash	1.0M						$0.15	$0.50

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://api.pinference.ai/api/v1",
    id: "prime/anthropic/claude-fable-5",
    apiKey: process.env.PRIME_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
      ? "prime/z-ai/glm-5.3-flash"
      : "prime/anthropic/claude-fable-5";
  }
});