perplexity
pplx-embed-v1-0.6b
In this workload, the estimated monthly API cost is $0.20. The route's listed context window is 32.8K.
Open model detailsData-led article
Cheapest LLM API embedding models for a 500-token vector-search workload
Embedding models turn text into vector representations for semantic search, clustering, and retrieval-augmented generation. This screen prices one narrow workload: 500 tokens per document, 100,000 documents indexed per month.
Scenario
The vector-index workload being priced
The numbers are generated from the site's current pricing data. Provider bills can differ because of cache behavior, discounts, regions, tiers, or provider-specific billing rules.
Input tokens / document
500 tokens A typical chunk size for text retrieval or semantic search.
Documents indexed / month
100,000 50,000,000 total input tokens.
Cost screen
Lowest-cost priced embedding routes in this workload
Rows are sorted by estimated monthly API cost. Embedding models typically charge per input token only. Open each model page before treating any route as production-ready.
| Model | Context | Input / 1M tokens | Monthly cost |
|---|---|---|---|
| pplx-embed-v1-0.6b perplexity | 32.8K | $0.0040 / 1M tokens | $0.20 |
| text-embedding-preview-0409 vertex_ai-embedding-models | 3.1K | $0.0063 / 1M tokens | $0.31 |
| nomic-embed-text-v1 fireworks_ai-embedding-models | 8.2K | $0.0080 / 1M tokens | $0.40 |
| nomic-embed-text-v1.5 fireworks_ai-embedding-models | 8.2K | $0.0080 / 1M tokens | $0.40 |
| gte-base fireworks_ai-embedding-models | 512 | $0.0080 / 1M tokens | $0.40 |
| together-ai-embedding-up-to-150m Together AI | N/A | $0.0080 / 1M tokens | $0.40 |
| bge-base-en-v1.5 Together AI | N/A | $0.0080 / 1M tokens | $0.40 |
| bge-base-en-v1.5 Together AI | N/A | $0.0080 / 1M tokens | $0.40 |
vertex_ai-embedding-models
text-embedding-preview-0409
In this workload, the estimated monthly API cost is $0.31. The route's listed context window is 3.1K.
Open model detailsfireworks_ai-embedding-models
nomic-embed-text-v1
In this workload, the estimated monthly API cost is $0.40. The route's listed context window is 8.2K.
Open model detailsChange the workload before choosing a route
If your documents are longer, shorter, or you index a different volume, rerun the calculator with your own token counts and model selection.
Caveats
What this comparison does not prove
This page does not rank embedding quality, output dimensions, retrieval accuracy, multilingual coverage, or latency. Some low-cost embedding routes may have smaller dimensions, shorter context limits, or lower accuracy for the specific domain you are indexing. Use this as a pricing shortlist, then test the exact model route and verify final pricing with the provider.