Embedding
Compare cost for vector-index workloads where you send text and get back vector embeddings, priced per input token only.
What matters most
Embedding models charge per input token only — there is no output token cost. Low input price matters most, but context window also affects which model fits your documents.
Base example
This page starts with 500 input tokens per document and 100,000 documents indexed per month.
Low-cost embedding models in the base example
These rows are server-rendered, so search engines can read them before any script runs.
| Model | Context | Input | Monthly cost |
|---|---|---|---|
| pplx-embed-v1-0.6b | 32.8K | $0.0040 / 1M tokens | $0.20 |
| text-embedding-preview-0409 | 3.1K | $0.0063 / 1M tokens | $0.31 |
| nomic-embed-text-v1 | 8.2K | $0.0080 / 1M tokens | $0.40 |
| nomic-embed-text-v1.5 | 8.2K | $0.0080 / 1M tokens | $0.40 |
| gte-base | 512 | $0.0080 / 1M tokens | $0.40 |
| together-ai-embedding-up-to-150m | N/A | $0.0080 / 1M tokens | $0.40 |
| bge-base-en-v1.5 | N/A | $0.0080 / 1M tokens | $0.40 |
| bge-base-en-v1.5 | N/A | $0.0080 / 1M tokens | $0.40 |
Open the compare tool with the lowest-cost embedding candidates preselected.
Open calculator to estimate your own workload cost with different token counts and model choices.
Browse providers to compare models from OpenAI, Anthropic, Google, Mistral, and other providers.
Pricing data from catalog last generated Aug 10, 2026. Verify before production decisions. Data sources.