LIVE
ANTHROPICOpus 4.7 benchmarks published2m ago
CLAUDEOK142ms
OPUS 4.7$15 / $75per Mtok
CHATGPTOK89ms
HACKERNEWSWhy has not AI improved design quality the way it improved dev speed?14m ago
MMLU-PROleader Opus 4.788.4
GEMINIDEGRADED312ms
MISTRALMistral Medium 3 released6m ago
GPT-4o$5 / $15per Mtok
ARXIVCompositional reasoning in LRMs22m ago
BEDROCKOK178ms
GEMINI 2.5$3.50 / $10.50per Mtok
THE VERGEFrontier Model Forum expansion announced38m ago
SWE-BENCHleader Claude Opus 4.772.1%
MISTRALOK104ms
ANTHROPICOpus 4.7 benchmarks published2m ago
CLAUDEOK142ms
OPUS 4.7$15 / $75per Mtok
CHATGPTOK89ms
HACKERNEWSWhy has not AI improved design quality the way it improved dev speed?14m ago
MMLU-PROleader Opus 4.788.4
GEMINIDEGRADED312ms
MISTRALMistral Medium 3 released6m ago
GPT-4o$5 / $15per Mtok
ARXIVCompositional reasoning in LRMs22m ago
BEDROCKOK178ms
GEMINI 2.5$3.50 / $10.50per Mtok
THE VERGEFrontier Model Forum expansion announced38m ago
SWE-BENCHleader Claude Opus 4.772.1%
MISTRALOK104ms
All endpoints

Embedding Models

Free
GET /api/embeddings

The /api/embeddings endpoint returns the curated catalog of production-ready embedding and reranker models. Each entry includes provider, dimensions (null for rerankers), max input tokens, $/1M tokens, MTEB average score, multilingual flag, license, and a one-line note. Filter with ?type=embedding or ?type=reranker.

When to use this endpoint

When your agent needs to pick or compare embeddings for a RAG pipeline. The /api/models endpoint covers chat/completion models; this is the missing peer for embeddings + rerankers.

Parameters

NameInTypeDescription
typequerystringFilter to "embedding" or "reranker" onlye.g. embedding

* required

Example response

{
  "ok": true,
  "lastUpdated": "2026-04-30",
  "count": 18,
  "models": [
    {
      "id": "voyage-3-large",
      "name": "voyage-3-large",
      "provider": "Voyage AI",
      "type": "embedding",
      "dimensions": 1024,
      "maxInputTokens": 32000,
      "pricePer1MTokens": 0.18,
      "openSource": false,
      "license": "Proprietary",
      "multilingual": true,
      "mtebAvg": 67.0
    }
  ]
}

Code samples

Python SDK

from tensorfeed import TensorFeed
tf = TensorFeed()
emb = tf.embeddings(type="embedding")
# Cheapest production embedding
ranked = sorted(
    [m for m in emb["models"] if m["pricePer1MTokens"] is not None],
    key=lambda m: m["pricePer1MTokens"]
)
print(ranked[0]["name"], ranked[0]["pricePer1MTokens"])

TypeScript SDK

const res = await fetch("https://tensorfeed.ai/api/embeddings?type=embedding");
const { models } = await res.json();
const cheapest = models
  .filter(m => m.pricePer1MTokens !== null)
  .sort((a, b) => a.pricePer1MTokens - b.pricePer1MTokens)[0];
console.log(cheapest.name);

FAQ

How current is the embedding catalog?

Editorial. Refreshed on redeploy when providers ship a new version or change pricing. Embedding-model pricing changes rarely (months, not days), so a daily cron does not match the data.

Why is rerank-v3.5 listed at $0?

Because Cohere prices rerank by search (each search = up to 100 documents reranked), not by token. The pricingNote field on each entry has the actual pricing model.

Related endpoints