Gemini Embedding 2 vs Codestral Embed
Gemini Embedding 2 from Google and Codestral Embed from Mistral AI, side by side. Every figure comes from the model registry. No markup on model usage: you pay the provider's list price.
| Attribute |  Gemini Embedding 2 |  Codestral Embed |
|---|---|---|
| Provider | Mistral AI | |
| Model id | google/gemini-embedding-2 | mistral/codestral-embed-2505 |
| Status | Available via Safeguard | Available via Safeguard |
| Input / 1M tokens | $0.20 | $0.15 |
| Output / 1M tokens | Price on request | Price on request |
| Price notes | Text input $0.20/1M. Image $0.45/1M ($0.00012 per image), audio $6.50/1M, video $12.00/1M. Output not billed. | Embeddings: input tokens only. Cached input $0.015. |
| Context | 8K | 8K |
| Parameters | Not published | Not published |
| Max output | Not published | Not published |
| Modality | Embeddings | Embeddings |
| Weights | Closed | Closed |
| Zero data retention | Not offered | Available |
| Prompts go to | Google (Gemini Developer API) | Mistral AI (global endpoint by default) |
| Retention | Paid tier: prompts and responses not used to improve Google products, but logged for a limited period for abuse monitoring, free tier content may be used to improve products | Commercial terms: no training on customer data unless opted in, with exceptions, Studio Free mode may train on inputs and outputs (opt-out available), pay-as-you-go can opt out, ZDR available on pay-as-you-go for stateless endpoints |
| Region | No region guarantee, data may be stored transiently or cached in any country where Google operates. Google points ZDR and enterprise processing needs to Vertex AI (Gemini Enterprise Agent Platform) | Global by default, optional EU or US regional inference endpoints at 1.1x pricing |
| Price checked | 2026-10-08 | 2026-10-08 |
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.