Text price
USD / M tokens · lower rate
Source: vendor documentation · 2026-09-08Models for semantic search, RAG and code retrieval.
Editorial edition · Reviewed on 2026-09-08 · Not a real-time feed
Models for semantic search, RAG and code retrieval.
| Select | Product / provider | Type | |||
|---|---|---|---|---|---|
VoVoyage 4 LiteVoyage AI | $0.02 | 1,024 | 32K | Texto multilingüe | |
MiMistral EmbedMistral AI | $0.10 | 1,024 | 8K | Texto | |
MiCodestral EmbedMistral AI | $0.15 | 3,072 | 8K | Código | |
CoCohere Embed 4Cohere | No data | 1,536 | 128K | Multimodal |
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. Sources and methodology ↗
Every scale starts at zero. Each chart keeps its own unit.
USD / M tokens · lower rate
Source: vendor documentation · 2026-09-08dimensions · a spec, not a score
Source: vendor documentation · 2026-09-08tokens · a spec, not a score
Source: vendor documentation · 2026-09-08Compare published indexes, API pricing and context limits.
Compare 2 options Cloud optionsInstances and platforms to deploy applications. Compare the plan, not just the vendor.
Compare 2 options DatabasesManaged database plans: entry price, storage and operating conditions.
Compare 2 options EmbeddingsModels for semantic search, RAG and code retrieval.
Compare 2 options Object storageBuckets for files, assets and backups: rates, operations and conditions.
Compare 2 options Message queuesAsynchronous delivery for workers, webhooks and background jobs.
Compare 2 optionsA lower price is not a lower total cost. A higher index doesn't guarantee the best result in your application.
How to read the data