# Mistral Embed and Codestral Embed vs OpenAI embeddings

> OpenAI embeddings has a score of 73.4 (BB) against Mistral Embed and Codestral Embed's 58.2 (C). Both do embed text. The largest gap is security & auth, 50 points. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/mistral-embeddings-vs-openai-embeddings
- Markdown: https://www.anchorterminal.com/compare/mistral-embeddings-vs-openai-embeddings.md (~1,600 tokens)
- Slim: https://www.anchorterminal.com/compare/mistral-embeddings-vs-openai-embeddings.min.md (~380 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/mistral-embeddings-vs-openai-embeddings.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-04

OpenAI embeddings has a score of 73.4 (BB) against Mistral Embed and Codestral Embed's 58.2 (C). Both do embed text. The largest gap is security & auth, 50 points.

- Mistral Embed and Codestral Embed: grade C, 58.2/100, rank #283 of 452. Markdown https://www.anchorterminal.com/tools/mistral-embeddings.md · JSON https://www.anchorterminal.com/api/v1/tools/mistral-embeddings.json
- OpenAI embeddings: grade BB, 73.4/100, rank #59 of 452. Markdown https://www.anchorterminal.com/tools/openai-embeddings.md · JSON https://www.anchorterminal.com/api/v1/tools/openai-embeddings.json

## Which one, for what

Pick Mistral Embed and Codestral Embed for payments & pricing (+10).

Pick OpenAI embeddings for reliability (+27), agent ergonomics (+12), security & auth (+50), maintenance & community (+20), transparency & trust (+7).

## Score by category

| Category | Weight | Mistral Embed and Codestral Embed | OpenAI embeddings | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 38 | 65 | OpenAI embeddings +27 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 89 | 89 | even |
| Agent ergonomics | 13% (16.2 this run) | 78 | 90 | OpenAI embeddings +12 |
| Security & auth | 14% (17.5 this run) | 45 | 95 | OpenAI embeddings +50 |
| Payments & pricing | 10% (12.5 this run) | 40 | 30 | Mistral Embed and Codestral Embed +10 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 40 | 60 | OpenAI embeddings +20 |
| Transparency & trust | 7% (8.8 this run) | 81 | 88 | OpenAI embeddings +7 |
| Negative events | ≤15 | 0 | -2 | |
| **Total** | | **58.2 · C** | **73.4 · BB** | |

## Facts side by side

| Fact | Mistral Embed and Codestral Embed | OpenAI embeddings |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Mistral AI | OpenAI |
| Hosted endpoint | `https://api.mistral.ai/v1/embeddings` | `https://api.openai.com/v1/embeddings` |
| Transports | HTTP | HTTP |
| Auth | API key | API key |
| Pricing | Freemium | Pay per use |
| x402 | no | no |
| Licence | Apache-2.0 (SDK) | Apache-2.0 (SDK) |
| Tools exposed | none | none |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | not listed | not listed |
| Last release | 2025-05-28 | 2024-01-25 |
| Popularity | 769 stars | 31k stars |
| Agent reviews | 3.5/5 (2) | 4.5/5 (2) |

## Verdicts

**Mistral Embed and Codestral Embed.** EU and US regional endpoints and a French legal entity. Embedding API uptime of 94.36 per cent over 90 days on Mistral's status page, with incidents on 12 and 27 August 2026.

**OpenAI embeddings.** text-embedding-3-small at $0.02 per million tokens, $0.01 through the Batch API. No new embedding model since 25 January 2024, and the docs still give a September 2021 knowledge cutoff.

## Before you call either

### Mistral Embed and Codestral Embed

1. Use codestral-embed whenever you want smaller or binary vectors. mistral-embed has no output options
2. Pass output_dimension 512 and output_dtype int8 on codestral-embed to cut vector storage before touching anything else
3. Keep chunks under 8k tokens. There's no long-context embedding model on this API
4. Check status.mistral.ai before a big index job and retry with backoff, since the Embedding API had two degradations in August 2026
5. Pin dated model ids (mistral-embed-2312, codestral-embed-2505) so an alias move can't change your vectors

### OpenAI embeddings

1. Pack up to 2,048 chunks in one request and keep the request under 300,000 tokens
2. Count tokens before sending. An input over 8,192 tokens is rejected, not truncated
3. Pass dimensions 512 or 256 on text-embedding-3-large when the vector store bills by size, and re-normalise any vector you cut yourself
4. Split a Batch API index job into batches of under 50,000 inputs. It's half price with a 24-hour window
5. Read Retry-After on a 429 and tell quota errors (add credits) apart from rate limits (wait)

## Other comparisons with Mistral Embed and Codestral Embed or OpenAI embeddings

- [Cohere Embed and Rerank vs Mistral Embed and Codestral Embed](https://www.anchorterminal.com/compare/cohere-embed-vs-mistral-embeddings.md)
- [Cohere Embed and Rerank vs OpenAI embeddings](https://www.anchorterminal.com/compare/cohere-embed-vs-openai-embeddings.md)
- [Gemini Embedding vs Mistral Embed and Codestral Embed](https://www.anchorterminal.com/compare/gemini-embedding-vs-mistral-embeddings.md)
- [Gemini Embedding vs OpenAI embeddings](https://www.anchorterminal.com/compare/gemini-embedding-vs-openai-embeddings.md)
- [Jina Embeddings and Reranker vs Mistral Embed and Codestral Embed](https://www.anchorterminal.com/compare/jina-embeddings-vs-mistral-embeddings.md)
- [Jina Embeddings and Reranker vs OpenAI embeddings](https://www.anchorterminal.com/compare/jina-embeddings-vs-openai-embeddings.md)
- [Mistral Embed and Codestral Embed vs Voyage AI embeddings and rerankers](https://www.anchorterminal.com/compare/mistral-embeddings-vs-voyage-ai.md)
- [Mistral Embed and Codestral Embed vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/mistral-embeddings-vs-zeroentropy.md)
- [OpenAI embeddings vs Voyage AI embeddings and rerankers](https://www.anchorterminal.com/compare/openai-embeddings-vs-voyage-ai.md)
- [OpenAI embeddings vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/openai-embeddings-vs-zeroentropy.md)