Gemini Embedding 001
sap-ai-core/gemini-embedding · family gemini · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.
This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See SAP AI Core’s docs for per-unit rates.
- Provider
- SAP AI Core (
sap-ai-core) - Kind
- text (outputs text)
- Context
- 2,048 tokens
- Max output
- 1 tokens
- Capabilities
- text
Same model, other providers
“Gemini Embedding 001” is offered by 6 providers — cheapest-effective first. Google is the cheapest at $0.11 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| $0.15 | free | $0.11 | 2k | |
| Merge Gateway | $0.15 | free | $0.11 | 2k |
| Tempr | $0.15 | free | $0.11 | 2k |
| Vertex | $0.15 | free | $0.11 | 2k |
| SAP AI Core (this) | — | — | — | 2k |
| Vercel AI Gateway | — | — | — | 8k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at SAP AI Core and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"gemini-embedding","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):