OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
M2-BERT-Retrieval-8k This page | ||||
| Semantic search + RAG | ||||
| Semantic search + RAG | ||||
| Semantic search + RAG | ||||
| Semantic search + RAG |
M2-BERT-Retrieval-8k is priced at input $0.011 / 1M.
Yes, M2-BERT-Retrieval-8k can stream responses as they are generated.
Yes, M2-BERT-Retrieval-8k supports both function calling and structured outputs.
M2-BERT-Retrieval-8k was built by Together.
It uses the v1 endpoint.