openai
OpenAI: Text Embedding 3 Large
openai/text-embedding-3-large
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
openai/text-embedding-3-large is an OpenAI embedding model listed in the OpenRouter catalog, converting text input into embedding vectors rather than generating text. The catalog describes it, quoting OpenAI's own positioning, as the provider's most capable embedding model for English and non-English tasks, and records a context length of 8192 tokens. Because the only evidence here is a marketplace catalog entry without an independent model card or benchmark results, all capability claims remain source-reported and should be validated on your own workloads before adoption.[1]
Strengths
- Produces embedding vectors from text, which the catalog describes as numerical representations usable for measuring relatedness between pieces of text.[1]
- Catalog-reported context length of 8192 tokens supports embedding longer passages in a single request.[1]
- Positioned by the vendor, per the catalog description, as OpenAI's most capable embedding model for English and non-English tasks, suggesting multilingual coverage.[1]
Limitations
- Evidence is catalog-only: no independent model card was available in this source pack, so all capability claims come from the vendor via OpenRouter and are unverified.[1]
- The catalog shows no benchmark results and null reasoning metadata, so real-world retrieval or clustering quality is unmeasured here and requires workload validation.[1]
- Output is limited to embeddings with no text generation; license terms, embedding dimensions, and hardware requirements are not stated in the source.[1]
Where to use it
- May suit semantic search and retrieval pipelines where measuring text relatedness via vectors is needed, pending validation on your corpus.[1]
- Could fit multilingual or non-English embedding tasks, given the vendor's reported cross-language capability claim in the catalog.[1]
- Potentially useful for clustering or classification over documents up to the reported 8192-token context, subject to your own evaluation.[1]
Sources
- [1] OpenRouter catalog · OpenAI: Text Embedding 3 LargeSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two...
Specifications
- Model ID
- openai/text-embedding-3-large
- Creator
- openai
- Added to OpenRouter
- 30.10.2025
- Context length
- 8,192
- Modality
- text->embeddings
- Input modalities
- text
- Output modalities
- embeddings
- Token pricing
- USD per 1M tokens: in $0.130 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | output: embeddings |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Azure | 8,192 | $0.130 | $0 | — | — | 100% |
| OpenAI | 8,192 | $0.130 | $0 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.