Together AI
Use Together AI for fast open-source model inference and embeddings with Nexus.
Together AI hosts popular open-source models with fast inference and embedding support. Uses an OpenAI-compatible API.
import "github.com/xraph/nexus/providers/together"
provider := together.New(os.Getenv("TOGETHER_API_KEY"))
gw := nexus.New(
nexus.WithProvider(provider),
)
| Option | Description |
|---|
together.WithBaseURL(url) | Override the API base URL (default: https://api.together.xyz/v1) |
| Capability | Supported |
|---|
| Chat | Yes |
| Streaming | Yes |
| Embeddings | Yes |
| Vision | No |
| Tools | Yes |
| Thinking | No |
| Model | Context | Max Output | Input Price | Output Price |
|---|
meta-llama/Llama-3.3-70B-Instruct-Turbo | 131K | 4,096 | $0.88/M | $0.88/M |
meta-llama/Llama-3.1-405B-Instruct-Turbo | 131K | 4,096 | $3.50/M | $3.50/M |
meta-llama/Llama-3.1-8B-Instruct-Turbo | 131K | 4,096 | $0.18/M | $0.18/M |
togethercomputer/m2-bert-80M-8k-retrieval | 8,192 | — | $0.008/M | — |