Together AI
Access 24 Together AI models through Mastra's model router. Authentication is handled automatically using the TOGETHER_API_KEY environment variable.
Learn more in the Together AI documentation.
.env
TOGETHER_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: "togetherai/LiquidAI/LFM2-24B-A2B"
});
// 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);
}
ModelsDirect link to Models
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|---|---|
togetherai/deepcogito/cogito-v2-1-671b | 164K | $1 | $1 | |||||
togetherai/deepseek-ai/DeepSeek-V4-Pro | 512K | $2 | $3 | |||||
togetherai/essentialai/Rnj-1-Instruct | 33K | $0.15 | $0.15 | |||||
togetherai/google/gemma-3n-E4B-it | 33K | $0.06 | $0.12 | |||||
togetherai/google/gemma-4-31B-it | 262K | $0.39 | $0.97 | |||||
togetherai/LiquidAI/LFM2-24B-A2B | 33K | $0.03 | $0.12 | |||||
togetherai/meta-llama/Llama-3.3-70B-Instruct-Turbo | 131K | $0.88 | $0.88 | |||||
togetherai/meta-llama/Meta-Llama-3-8B-Instruct-Lite | 8K | $0.14 | $0.14 | |||||
togetherai/MiniMaxAI/MiniMax-M2.7 | 203K | $0.30 | $1 | |||||
togetherai/MiniMaxAI/MiniMax-M3 | 524K | $0.30 | $1 | |||||
togetherai/moonshotai/Kimi-K2.6 | 262K | $1 | $5 | |||||
togetherai/moonshotai/Kimi-K2.7-Code | 262K | $0.95 | $4 | |||||
togetherai/nvidia/nemotron-3-ultra-550b-a55b | 512K | $0.60 | $4 | |||||
togetherai/openai/gpt-oss-120b | 131K | $0.15 | $0.60 | |||||
togetherai/openai/gpt-oss-20b | 131K | $0.05 | $0.20 | |||||
togetherai/pearl-ai/gemma-4-31b-it | 32K | $0.28 | $0.86 | |||||
togetherai/Qwen/Qwen2.5-7B-Instruct-Turbo | 33K | $0.30 | $0.30 | |||||
togetherai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput | 262K | $0.20 | $0.60 | |||||
togetherai/Qwen/Qwen3.5-397B-A17B | 262K | $0.60 | $4 | |||||
togetherai/Qwen/Qwen3.5-9B | 262K | $0.17 | $0.25 | |||||
togetherai/Qwen/Qwen3.6-Plus | 1.0M | $0.50 | $3 | |||||
togetherai/Qwen/Qwen3.7-Max | 1.0M | $1 | $4 | |||||
togetherai/zai-org/GLM-5 | 203K | $1 | $3 | |||||
togetherai/zai-org/GLM-5.1 | 203K | $1 | $4 |
Advanced configurationDirect link to Advanced configuration
Custom headersDirect link to Custom headers
src/mastra/agents/my-agent.ts
const agent = new Agent({
id: "custom-agent",
name: "custom-agent",
model: {
id: "togetherai/LiquidAI/LFM2-24B-A2B",
apiKey: process.env.TOGETHER_API_KEY,
headers: {
"X-Custom-Header": "value"
}
}
});
Dynamic model selectionDirect link to 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
? "togetherai/zai-org/GLM-5.1"
: "togetherai/LiquidAI/LFM2-24B-A2B";
}
});
Direct provider installationDirect link to Direct provider installation
This provider can also be installed directly as a standalone package, which can be used instead of the Mastra model router string. View the package documentation for more details.
- npm
- pnpm
- Yarn
- Bun
npm install @ai-sdk/togetherai
pnpm add @ai-sdk/togetherai
yarn add @ai-sdk/togetherai
bun add @ai-sdk/togetherai
For detailed provider-specific documentation, see the AI SDK Together AI provider docs.