LIVE Cheapest: GLM-4.7-Flash $0.000/Mtok in 153 models tracked Updated Jun 25, 2026
Jun 25, 2026
ModelPriceWatch$/Mtok
Pricing / Compare / Granite Embedding 278M Multilingual vs Granite 4 H Small

Granite Embedding 278M Multilingual vs Granite 4 H Small

Side-by-side API pricing comparison · IBM vs IBM

🏆 Granite Embedding 278M Multilingual is 46.2% cheaper on blended cost ($0.106 vs $0.155/Mtok)

Granite Embedding 278M Multilingual

by IBM

Current embedding Open weights
Input
$0.106/Mtok
Output
$0.106/Mtok
✓ Cheaper
Blended avg$0.106/Mtok
Context— tokens
Modalitytext
Parameters278M
ReleasedJun 1, 2025
Full details →

Granite 4 H Small

by IBM

Current budget Open weights
Input
$0.060/Mtok
Output
$0.250/Mtok
Blended avg$0.155/Mtok
Context128K tokens
Modalitytext
ParametersProprietary
ReleasedOct 19, 2025
Full details →

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

VolumeGranite Embedding 278M MultilingualGranite 4 H SmallSavings
1M tokens $0.11 $0.16 $0.05 (32.3%)
10M tokens $1.06 $1.55 $0.49 (31.6%)
100M tokens $10.6 $15.5 $4.9 (31.6%)
1000M tokens $106 $155 $49 (31.6%)

Summary

Granite Embedding 278M Multilingual by IBM costs $0.106/Mtok input and $0.106/Mtok output, with a —-token context window. It supports text input.

Granite 4 H Small by IBM costs $0.060/Mtok input and $0.250/Mtok output, with a 128K-token context window. It supports text input.

On a blended cost basis, Granite Embedding 278M Multilingual is 46.2% cheaper than Granite 4 H Small.

Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.