text-embedding-004 vs rerank-2.5
Side-by-side API pricing comparison · Google vs Voyage AI
🏆
text-embedding-004 is 100% cheaper on blended cost ($0.025 vs $0.050/Mtok)
text-embedding-004
by Google
Current embeddingInput
$0.025/Mtok
Output
$0.025/Mtok
✓ Cheaper
| Blended avg | $0.025/Mtok |
|---|---|
| Context | 2K tokens |
| Modality | text |
| Parameters | Proprietary |
| Released | Oct 1, 2024 |
rerank-2.5
by Voyage AI
Current embeddingInput
$0.050/Mtok
Output
$0.050/Mtok
| Blended avg | $0.050/Mtok |
|---|---|
| Context | — tokens |
| Modality | text |
| Parameters | Proprietary |
| Released | Jun 1, 2025 |
Cost at scale — 1M tokens (50/50 input/output)
| Volume | text-embedding-004 | rerank-2.5 | Savings |
|---|---|---|---|
| 1M tokens | $0.03 | $0.05 | $0.03 (60%) |
| 10M tokens | $0.25 | $0.5 | $0.25 (50%) |
| 100M tokens | $2.5 | $5 | $2.5 (50%) |
| 1000M tokens | $25 | $50 | $25 (50%) |
Summary
text-embedding-004 by Google costs $0.025/Mtok input and $0.025/Mtok output, with a 2K-token context window. It supports text input.
rerank-2.5 by Voyage AI costs $0.050/Mtok input and $0.050/Mtok output, with a —-token context window. It supports text input.
On a blended cost basis, text-embedding-004 is 100% cheaper than rerank-2.5. It also has a larger context window.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.