Model catalogue
Your model.
The same endpoint.
Call GET /v1/models for the current configured list. Provider adapters share one response format; their dimensions and input-purpose settings remain explicit.
中文語料，直接送出。
| Model | Direct provider | Default dimensions | Service rate | Status |
|---|---|---|---|---|
bge-m3 | cloudflare | 1,024 | $0.10 | Live |
text-embedding-3-small | openai | 1,536 configurable | $0.40 | Needs credentials |
text-embedding-3-large | openai | 3,072 configurable | $0.80 | Needs credentials |
voyage-3.5 | voyage | 1,024 configurable | $0.60 | Needs credentials |
embed-v4.0 | cohere | 1,536 configurable | $0.80 | Needs credentials |
jina-embeddings-v3 | jina | 1,024 configurable | $0.60 | Needs credentials |
gemini-embedding-001 | 3,072 configurable | $0.80 | Needs credentials | |
qwen3-embedding-0-6b | databricks | 1,024 configurable | $0.40 | Needs credentials |
gte-large-en | databricks | 1,024 | $0.80 | Needs credentials |
Choose a vector space before indexing.
BGE-M3: 1,024 dimensions, multilingual text, fixed vector size. Used by managed document search.
OpenAI, Jina, Gemini and Qwen: specify dimensions for shorter vectors up to the default size. Voyage accepts 256, 512, 1,024 or 2,048; Cohere accepts 256, 512, 1,024 or 1,536.
GTE: fixed at 1,024 dimensions. Use cosine distance; an existing corpus must keep the same model.
Use input_type: "query" for a search query and "document" for indexed text. Different purposes are cached separately.
Image embeddings, model evaluation and database branching are outside this release.