E5-Mistral embeddings

E5-Mistral embeddings is a efficient-tier language model from Infercom. E5-Mistral embeddings is an open-weights model, meaning the weights are publicly available for self-hosting, fine-tuning, and deployment on your own infrastructure — not just through Infercom's API. The E5-Mistral family is Infercom's model series for this capability tier.

E5-Mistral embeddings is priced at $0.13/1M input tokens. Output token pricing does not apply to this model — it returns a vector or score rather than generated text. At 1,000 tokens per call, E5-Mistral embeddings costs approximately $0.13 per 1,000 API calls.

Its 33K-token context window is sufficient for most production use cases, handling documents up to ~25,000 words or multi-turn conversations spanning dozens of exchanges.

E5-Mistral embeddings is best suited to embeddings, EU. It is a text-only model without vision or function calling support. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how E5-Mistral embeddings compares to similar models across these dimensions.

E5-Mistral embeddings sits in the efficient tier — optimized for speed and cost while maintaining solid quality, ideal for high-volume or latency-sensitive workloads. As an open-weights model, E5-Mistral embeddings can be self-hosted on GPU compute (see the GPU rental comparison on this site) to eliminate per-token API costs entirely — the break-even point versus API pricing depends on your volume and the GPU hourly rate. When comparing E5-Mistral embeddings to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (N/A/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.