Batchrouter
Back to models
Model · text-embedding-3-small

Text Embedding 3 Small

BatchRouter's default embedding catalog entry for large-volume asynchronous vector generation jobs.

standard
confidential
embeddings
8k ctx
1 provider
Estimate a batchQuickstart

Lane pricing

Provider rates, live status, and capability fit for this model.

$0.0959 discounted customer input rate per 1M tokens from currently available batch provider quotes.

Capabilities

Catalog model

Runtime

No advanced runtime capability has been declared.

Hosted tools

Retrieval
  • Retrieval: Retrieval-augmented context is declared for knowledge-base backed runs.
Why use this model

Batch-ready workload fit

Use it for embeddings jobs where cost, routing auditability, and async delivery matter more than single-request latency.

Declared hosted tools

Retrieval support is modeled from provider offerings instead of marketing copy.

Known context envelope

The catalog declares a 8k context window, which helps reject lanes that cannot fit large batch items before dispatch.

Privacy tier awareness

Available privacy tiers include standard, confidential, so routing can enforce buyer constraints.

Providers
1
Best p50
—
Context
8k

Providers serving this model

View rankings →
  • op
    openai
    openai
    Active
    No refresh
    No heartbeat

Route a batch to Text Embedding 3 Small

Cost estimate in <200ms. Final charge follows delivered token usage.

Start free