Charm Hyper

Accédez à 24 modèles Charm Hyper via le routeur de modèles de Mastra. L’authentification est gérée automatiquement à l’aide de la variable d’environnement HYPER_API_KEY.

Pour en savoir plus, consultez la documentation Charm Hyper.

.env

HYPER_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: "hyper/deepseek-v4-flash"
});

// 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 utilise le point de terminaison /chat/completions compatible avec OpenAI. Certaines fonctionnalités propres au Provider peuvent ne pas être disponibles. Consultez la documentation Charm Hyper pour plus de détails.

Modèles

24 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
hyper/deepseek-v4-flash	1.0M						$0.20	$0.40
hyper/deepseek-v4-flash-0731	1.0M						$0.15	$0.30
hyper/deepseek-v4-pro	1.0M						$2	$5
hyper/gemma-4-26b-a4b-it	256K						$0.12	$0.42
hyper/glm-5.1	203K						$2	$5
hyper/glm-5.2	1.0M						$1	$4
hyper/gpt-oss-120b	131K						$0.18	$0.71
hyper/kimi-k2.5	262K						$0.55	$3
hyper/kimi-k2.6	262K						$0.95	$4
hyper/kimi-k2.7-code	256K						$0.95	$4
hyper/kimi-k3	1.0M						$3	$16
hyper/llama-3.3-70b-instruct	128K						$0.61	$1
hyper/llama-4-maverick-17b-128e-instruct-fp8	430K						$0.27	$0.90
hyper/minimax-m2.7	262K						$0.44	$2
hyper/minimax-m3	512K						$0.33	$1
hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar	106K						$0.57	$2
hyper/qwen3-next-80b-a3b-instruct	262K						$0.12	$1
hyper/qwen3.6-flash	1.0M						$1	$4
hyper/qwen3.6-max	256K						$2	$12
hyper/qwen3.6-plus	1.0M						$2	$6
hyper/qwen3.7-flash	1.0M						$0.20	$0.80
hyper/qwen3.7-max	1.0M						$3	$8
hyper/qwen3.7-plus	1.0M						$1	$5
hyper/qwen3.8-max	1.0M						$2	$6

Configuration avancée

En-têtes personnalisés

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://hyper.charm.land/v1",
    id: "hyper/deepseek-v4-flash",
    apiKey: process.env.HYPER_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Sélection dynamique du modèle

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
      ? "hyper/qwen3.8-max"
      : "hyper/deepseek-v4-flash";
  }
});