Gemini Embedding 2
sap-ai-core/gemini-embedding-2 · family gemini · in: text, image, audio, video, pdf → out: text · price provider-declared (via models.dev). Capabilities: text image audio video pdf.
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
- 8,192 tokens
- Max output
- 3,072 tokens
- Capabilities
- text image audio video pdf
Same model, other providers
“Gemini Embedding 2” is offered by 4 providers — cheapest-effective first. Tempr is the cheapest at $0.15 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Tempr | $0.2 | free | $0.15 | 8k |
| $0.2 | free | $0.15 | 8k | |
| SAP AI Core (this) | — | — | — | 8k |
| Vercel AI Gateway | — | — | — | 0 |
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-2","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):