LIVE Cheapest: GLM-4.7-Flash $0.000/Mtok in 153 models tracked Updated Jun 25, 2026
Jun 25, 2026
ModelPriceWatch$/Mtok
Pricing / Compare / text-embedding-004 vs rerank-2.5

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 embedding
Input
$0.025/Mtok
Output
$0.025/Mtok
✓ Cheaper
Blended avg$0.025/Mtok
Context2K tokens
Modalitytext
ParametersProprietary
ReleasedOct 1, 2024
Full details →

rerank-2.5

by Voyage AI

Current embedding
Input
$0.050/Mtok
Output
$0.050/Mtok
Blended avg$0.050/Mtok
Context— tokens
Modalitytext
ParametersProprietary
ReleasedJun 1, 2025
Full details →

Cost at scale — 1M tokens (50/50 input/output)

Volumetext-embedding-004rerank-2.5Savings
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.