How much does Text Embedding Ada 002 cost per 1M tokens?

OpenAI lists $0.1 / — per 1M input / output tokens in the odnoga catalog. Through odnoga you pay that vendor price plus your plan margin, and every request is recorded with both numbers.

What is Text Embedding Ada 002 best for?

High-volume, latency-sensitive calls: classification, extraction, routing, short rewrites and summaries.

Can I switch to Text Embedding Ada 002 without changing my code?

Yes. odnoga exposes one OpenAI-compatible endpoint, so switching means sending "text-embedding-ada-002" as the model id — or changing it in the managed prompt version, with no application deploy.

Text Embedding Ada 002

Text Embedding Ada 002 by OpenAI: $0.1 input and — output per 1M tokens, 8K context. Call it through the odnoga LLM gateway.

Text Embedding Ada 002 is served by OpenAI and called through odnoga with the same OpenAI-compatible request shape as every other model in the catalog. Its 8K-token context window sets how much input you can send in one request.

Specification and price

Vendor	OpenAI
Model ID	text-embedding-ada-002
Context window	8K tokens
Max output	—
Capabilities	—

Your plan

Per 1M tokens	Vendor cost	Your price on Free+7%
Input	$0.1	$0.108
Output	—	—
Cached input	—	—

Vendor cost is the list price per million tokens as recorded in the odnoga catalog; your price applies your plan margin with the same formula that bills every request — see pricing. Pricing

Call it through odnoga

const res = await fetch("https://api.odnoga.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ODNOGA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "text-embedding-ada-002",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Same request shape for every vendor in the catalog — swap the model id and odnoga handles keys, routing, limits and cost accounting.

How to use Text Embedding Ada 002

Derived from the odnoga catalog record for this model.

Best for

High-volume, latency-sensitive calls: classification, extraction, routing, short rewrites and summaries.

Not the right pick when

Anything that needs to read an image — this model takes text only.
Agent loops that must call your functions — tool calling is not available here.
Pipelines that require guaranteed JSON — parse defensively or pick a model with enforced JSON.
Large documents in one request — the window is 8K tokens, so you will need chunking.
Anything where a wrong answer is costly without a human check — no model in the catalog removes that requirement.

Practical tips through odnoga

01Pin the model id in a managed prompt version, so a model swap is a version change you can compare and roll back, not an edit in application code.
02Compare it against 2–8 other models on the same frozen test cases in the evaluation laboratory before you make it the production default.
03For repeated identical deterministic calls, odnoga answer reuse returns the stored answer and bills no vendor tokens — turn it off for creative output.
04Set a fallback model on the route so a vendor incident degrades quality instead of returning an error, and a per-tenant budget so one caller cannot spend the month.