Text price
Embeddings API price for text; index storage is not included.
Models for semantic search, RAG and code retrieval. Pick two to four options to explore how they differ.
Snapshot: 2026-09-08 · Public sources · Not a real-time feedEditorial edition · Reviewed on 2026-09-08 · Not a real-time feed
| Metric | Cohere Embed 4 | Codestral Embed |
|---|---|---|
| Text priceUSD / M tokens · lower is better | No dataNot included | $0.15Vendor ↗ |
| Reference dimensionsdimensions · higher is better | 1,536Vendor ↗ | 3,072Vendor ↗ |
| Input per documenttokens · higher is better | 128KVendor ↗ | 8KVendor ↗ |
Text pricing per million tokens, excluding starter credits and batch. Dimensions and context don't measure retrieval quality. Don't mix vector spaces from different models.
Embeddings API price for text; index storage is not included.
A relationship between two dimensions, not an automatic recommendation.
| Feature | Cohere Embed 4 | Codestral Embed |
|---|---|---|
| Dimensiones de referencia | 1536 (por defecto) | 3072 (máximo configurable) |
| Dimensiones admitidas | 256, 512, 1024, 1536 | No data |
| Identificador API | embed-v4.0 | codestral-embed |
| Entrada | Texto, imagen y documentos mixtos | Código y texto |
What to validate before you make a decision.
No se incorpora una tarifa comparable por token: el precio depende de modalidad y despliegue. La oferta dedicada por instancia no se convierte artificialmente a tokens.
Checked on 2026-09-08 · Editorial update3072 es el máximo configurable, no una puntuación de calidad. Una dimensión menor requiere regenerar y versionar el índice. Contexto publicado como 8k.
Checked on 2026-09-08 · Editorial updateShare your requirements and the options you're weighing. No sign-up, no automatic subscriptions.