Quick setup
Open the kRouter dashboard at http://localhost:20128
Go to Providers → click Together AI
Paste your API key, click Save
Test the connection
Use in your IDE
Point any OpenAI-compatible client at kRouter using your local API key.
# Endpoint
http://localhost:20128/v1
# API key (from Dashboard → API Keys)
sk-krouter-XXXX
# Model
together/meta-llama/llama-4-405bHow Together AI billing works with kRouter
Together AI is pay-per-token. You bring your own API key and kRouter routes to it, so you keep your own rate limits and billing relationship. kRouter authenticates it via apikey. 6 models are routable as together/<model>.
Through kRouter, Together AI serves chat and code completion and embeddings, exposed on /v1/embeddings. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from Together AI is a one-line model change in your client rather than a rewrite.
Together AI models & pricing
Prices are USD per 1M tokens, cheapest first. kRouter bills nothing on top; this is the provider's own rate.
| Model | Route as | Input /1M | Output /1M |
|---|---|---|---|
| DeepSeek R1 | together/deepseek-ai/DeepSeek-R1 | $0.14 | $0.28 |
| Qwen3 235B | together/Qwen/Qwen3-235B-A22B | $0.50 | $2.00 |
| Llama 3.3 70B Turbo | together/meta-llama/Llama-3.3-70B-Instruct-Turbo | — | — |
| Llama 4 Maverick | together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | — | — |
| BGE Large EN v1.5 | together/BAAI/bge-large-en-v1.5 | — | — |
| M2 BERT 80M 8K | together/togethercomputer/m2-bert-80M-8k-retrieval | — | — |
Together AI links
Together AI FAQ
Is Together AI free through kRouter?
Together AI is pay-per-token: you bring your own API key and are billed by Together AI at their rates. kRouter adds nothing on top and is free and MIT-licensed.
How do I use Together AI with Claude Code or Cursor?
Connect Together AI in the kRouter dashboard, then point your tool at kRouter's local endpoint (http://localhost:20128/v1) with a kRouter API key. Any OpenAI-compatible client works, and models are addressed as together/<model>.
Which Together AI models can kRouter route to?
6 models, including Llama 3.3 70B Turbo, DeepSeek R1, Qwen3 235B. Every one is addressed as together/<model> from any client.
What happens when Together AI is rate limited?
kRouter detects the limit, parks that account until its real reset time, and fails over to your next connected account or provider — so the request still completes instead of erroring.