Providers
together
Together AI — hosts 200+ open models behind one OpenAI-compatible API.
import { together } from '@agentskit/adapters'
const adapter = together({
apiKey: process.env.TOGETHER_API_KEY!,
model: 'meta-llama/Llama-3.3-70B-Instruct-Turbo',
})#Options
| Option | Type | Default |
|---|---|---|
apiKey | string | required |
model | string | required |
baseUrl | string | https://api.together.xyz/v1 |
fetch | typeof fetch | global |
#Why together
- Cheapest hosted path to Llama / Qwen / DeepSeek / Mixtral.
- OpenAI-compatible — swap from openai in one line.
- Good for price-sensitive batch workloads.
#Env
| Var | Purpose |
|---|---|
TOGETHER_API_KEY | API key |
#Related
Explore nearby
- PeerProviders
25 native chat and embedder adapters, plus higher-order adapters that compose candidates. Separate from the 140-provider models catalog.
- PeerChoosing an adapter
Capability decision table and rules of thumb for picking a chat adapter.
- PeerHosted chat adapters
17 managed-LLM adapters. Same contract; swap by changing one import.