← Back to all comparisons
Side-by-side
Text embedding 3 large vs Codestral
OpenAI vs Mistral — head-to-head specs and pricing.
OpenAI
Text embedding 3 large
High-quality OpenAI embeddings.
3072-dim embeddings for retrieval, clustering, classification. Best-in-class semantic quality.
Mistral
Codestral
Low-latency code completion from Mistral.
Codestral — purpose-built for code completion and instruction in 80+ programming languages.
| Spec | Text embedding 3 large | Codestral |
|---|---|---|
| Provider | OpenAI | Mistral |
| Input cost / 1M tokens | — | $0.24 |
| Output cost / 1M tokens | — | $0.72 |
| Context window | — | 32,000 tokens |
| Max output tokens | — | — |
| Streaming support | — | ✓ |
| Tool calling | — | — |
| Vision input | — | — |
| JSON mode | — | — |
| Status | ACTIVE | ACTIVE |
Use both via OneAPIKey — one key, one bill
OneAPIKey aggregates OpenAI, Mistral, and 10 more providers behind a single API. Smart Routing automatically picks the best model per request — or you choose explicitly.