Skip to main content

Helicone logoHelicone

Access 91 Helicone models through Mastra's model router. Authentication is handled automatically using the HELICONE_API_KEY environment variable.

Learn more in the Helicone documentation.

HELICONE_API_KEY=your-api-key
import { Agent } from "@mastra/core/agent";

const agent = new Agent({
  id: "my-agent",
  name: "My Agent",
  instructions: "You are a helpful assistant",
  model: "helicone/chatgpt-4o-latest"
});

// 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);
}
info

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

Models
Direct link to Models

ModelContextToolsReasoningImageAudioVideoInput $/1MOutput $/1M
helicone/chatgpt-4o-latest128K$5$20
helicone/claude-3-haiku-20240307200K$0.25$1
helicone/claude-3.5-haiku200K$0.80$4
helicone/claude-3.5-sonnet-v2200K$3$15
helicone/claude-3.7-sonnet200K$3$15
helicone/claude-4.5-haiku200K$1$5
helicone/claude-4.5-opus200K$5$25
helicone/claude-4.5-sonnet200K$3$15
helicone/claude-haiku-4-5-20251001200K$1$5
helicone/claude-opus-4200K$15$75
helicone/claude-opus-4-1200K$15$75
helicone/claude-opus-4-1-20250805200K$15$75
helicone/claude-sonnet-4200K$3$15
helicone/claude-sonnet-4-5-20250929200K$3$15
helicone/codex-mini-latest200K$2$6
helicone/deepseek-r1-distill-llama-70b128K$0.03$0.13
helicone/deepseek-reasoner128K$0.56$2
helicone/deepseek-tng-r1t2-chimera130K$0.30$1
helicone/deepseek-v3128K$0.56$2
helicone/deepseek-v3.1-terminus128K$0.27$1
helicone/deepseek-v3.2164K$0.27$0.41
helicone/ernie-4.5-21b-a3b-thinking128K$0.07$0.28
helicone/gemini-2.5-flash1.0M$0.30$3
helicone/gemini-2.5-flash-lite1.0M$0.10$0.40
helicone/gemini-2.5-pro1.0M$1$10
helicone/gemini-3-pro-preview1.0M$2$12
helicone/gemma-3-12b-it131K$0.05$0.10
helicone/gemma2-9b-it8K$0.01$0.03
helicone/glm-4.6205K$0.45$2
helicone/gpt-4.11.0M$2$8
helicone/gpt-4.1-mini1.0M$0.40$2
helicone/gpt-4.1-mini-2025-04-141.0M$0.40$2
helicone/gpt-4.1-nano1.0M$0.10$0.40
helicone/gpt-4o128K$3$10
helicone/gpt-4o-mini128K$0.15$0.60
helicone/gpt-5400K$1$10
helicone/gpt-5-chat-latest128K$1$10
helicone/gpt-5-codex400K$1$10
helicone/gpt-5-mini400K$0.25$2
helicone/gpt-5-nano400K$0.05$0.40
helicone/gpt-5-pro128K$15$120
helicone/gpt-5.1400K$1$10
helicone/gpt-5.1-chat-latest128K$1$10
helicone/gpt-5.1-codex400K$1$10
helicone/gpt-5.1-codex-mini400K$0.25$2
helicone/gpt-oss-120b131K$0.04$0.16
helicone/gpt-oss-20b131K$0.05$0.20
helicone/grok-3131K$3$15
helicone/grok-3-mini131K$0.30$0.50
helicone/grok-4256K$3$15
helicone/grok-4-1-fast-non-reasoning2.0M$0.20$0.50
helicone/grok-4-1-fast-reasoning2.0M$0.20$0.50
helicone/grok-4-fast-non-reasoning2.0M$0.20$0.50
helicone/grok-4-fast-reasoning2.0M$0.20$0.50
helicone/grok-code-fast-1256K$0.20$2
helicone/hermes-2-pro-llama-3-8b131K$0.14$0.14
helicone/kimi-k2-0711131K$0.57$2
helicone/kimi-k2-0905262K$0.50$2
helicone/kimi-k2-thinking256K$0.48$2
helicone/llama-3.1-8b-instant131K$0.05$0.08
helicone/llama-3.1-8b-instruct16K$0.02$0.05
helicone/llama-3.1-8b-instruct-turbo128K$0.02$0.03
helicone/llama-3.3-70b-instruct128K$0.13$0.39
helicone/llama-3.3-70b-versatile131K$0.59$0.79
helicone/llama-4-maverick131K$0.15$0.60
helicone/llama-4-scout131K$0.08$0.30
helicone/llama-guard-4131K$0.21$0.21
helicone/llama-prompt-guard-2-22m512$0.01$0.01
helicone/llama-prompt-guard-2-86m512$0.01$0.01
helicone/mistral-large-2411128K$2$6
helicone/mistral-nemo128K$20$40
helicone/mistral-small128K$75$200
helicone/o1200K$15$60
helicone/o1-mini128K$1$4
helicone/o3200K$2$8
helicone/o3-mini200K$1$4
helicone/o3-pro200K$20$80
helicone/o4-mini200K$1$4
helicone/qwen2.5-coder-7b-fast32K$0.03$0.09
helicone/qwen3-235b-a22b-thinking262K$0.30$3
helicone/qwen3-30b-a3b41K$0.08$0.29
helicone/qwen3-32b131K$0.29$0.59
helicone/qwen3-coder262K$0.22$0.95
helicone/qwen3-coder-30b-a3b-instruct262K$0.10$0.30
helicone/qwen3-next-80b-a3b-instruct262K$0.14$1
helicone/qwen3-vl-235b-a22b-instruct256K$0.30$2
helicone/sonar127K$1$1
helicone/sonar-deep-research127K$2$8
helicone/sonar-pro200K$3$15
helicone/sonar-reasoning127K$1$5
helicone/sonar-reasoning-pro127K$2$8
91 available models

Advanced Configuration
Direct link to Advanced Configuration

Custom Headers
Direct link to Custom Headers

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://ai-gateway.helicone.ai/v1",
    id: "helicone/chatgpt-4o-latest",
    apiKey: process.env.HELICONE_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic Model Selection
Direct link to Dynamic Model Selection

const agent = new Agent({
  id: "dynamic-agent",
  name: "Dynamic Agent",
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === "complex";
    return useAdvanced
      ? "helicone/sonar-reasoning-pro"
      : "helicone/chatgpt-4o-latest";
  }
});

On this page