openai

OpenAI: Text Embedding Ada 002 (batch)

openai/text-embedding-ada-002:batch

Our take

AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.

The OpenRouter catalog identifies openai/text-embedding-ada-002:batch as an OpenAI model that transforms text into embeddings and describes the canonical model as OpenAI's legacy text embedding model. It reports text input, embedding output, and an 8,192-token context window, but no benchmark results or reasoning capability. Because this source pack contains only catalog data and no independent model card, performance should not be inferred; teams should validate embedding quality, latency, and fit on their own workloads.[1]

Strengths

Maps text input directly to embedding output.[1]
OpenRouter reports an 8,192-token context window.[1]

Limitations

Evidence is catalog-only; no independent model card was available in this source pack.[1]
No measured benchmark results, supported parameters, or reasoning capability are reported.[1]
The source calls the canonical model legacy, so current support expectations should be verified.[1]

Where to use it

Consider for existing embedding integrations where OpenAI compatibility matters, subject to workload validation.[1]
Evaluate for semantic search, similarity matching, or retrieval workflows that consume embeddings rather than generated text.[1]

Sources

[1] OpenRouter catalog · OpenAI: Text Embedding Ada 002 (batch)Sources checked: Nov 13, 2026

About this model

Description below is the original text supplied by OpenRouter, shown in the source language.

text-embedding-ada-002 is OpenAI's legacy text embedding model.

Specifications

Model ID: openai/text-embedding-ada-002:batch
Canonical ID: openai/text-embedding-ada-002
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 $0.050 / 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)
OpenAI	8,192	$0.050	$0	—	—	—

Provider data retrieved: 13.11.2026

No published articles identify this model yet.