Embedding model · Perplexity
Perplexity pplx-embed-v1-0.6b pricing
Per million tokens
$0.004
Per 100M tokens
$0.400
Cheapest of 18 among 18 embedding model prices in the index. Figures are USD list prices excluding tax.
Price history
Tracked since 7 September 2026. A chart appears once there are at least two weekly readings.
| Date | Figure | Reading | Change |
|---|---|---|---|
| 2026-09-07 | Price ($/Mtok) | $0.0040 | — |
Machine-readable: history.json · Every movement also appears in the change log.
What it costs in practice
Computed from the current figures above. Change the assumptions in the RAG cost calculator.
| Workload | Cost |
|---|---|
| One million tokens | $0.0040 |
| A 10,000-document corpus (~100M tokens) | $0.400 |
| 1,000 queries a day for a month (50 tokens each) | $0.0060 |
| Re-embedding that corpus after a model change | $0.400 |
Compared with the closest alternatives
| Model | $/Mtok | vs this |
|---|---|---|
| Perplexity pplx-embed-context-v1-0.6b | $0.0080 | +100% |
| OpenAI text-embedding-3-small | $0.020 | +400% |
| Voyage AI voyage-4-lite | $0.020 | +400% |
| Perplexity pplx-embed-v1-4b | $0.030 | +650% |
| Perplexity pplx-embed-context-v1-4b | $0.050 | +1150% |
| Voyage AI rerank-3 | $0.050 | +1150% |
| Voyage AI voyage-4 | $0.060 | +1400% |
| Mistral AI Mistral Embed | $0.100 | +2400% |
How to read this page
The figures are the list prices published on the vendor's own pricing page, re-read every week by an automated check that never invents a number: if the page cannot be read, the previous reading is kept and the item is flagged after three missed weeks. Negotiated rates, volume tiers, free credits and regional pricing are not modelled. The methodology describes the process and its limits; the price index shows every embedding model figure side by side.