LIVE Cheapest: GLM-4.7-Flash $0/Mtok in 154 models tracked Updated Jul 1, 2026
Jul 1, 2026
ModelPriceWatch$/Mtok
Pricing / Compare / Granite Embedding 278M Multilingual vs Granite 4.0 Micro

Granite Embedding 278M Multilingual vs Granite 4.0 Micro

Side-by-side comparison of API pricing, specs, benchmarks, and capabilities

🏆 Granite Embedding 278M Multilingual is 21.7% cheaper on blended cost ($0.053 vs $0.065/Mtok)
 
by IBM
by IBM
Overview
Status Current embedding Open weights Current budget Open weights
Released Jun 1, 2025 Oct 19, 2025
Pricing per million tokens
Input $0.106/Mtok $0.017/Mtok
Output $—/Mtok $0.112/Mtok
Blended avg $0.053/Mtok $0.065/Mtok
Specifications
Context window tokens 128K tokens
Parameters 278M Proprietary
Speed (TPS)
Modalities
Input
text
text
Providers
Available from
IBM — $0.106/$—/Mtok
IBM — $0.017/$0.112/Mtok

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

VolumeGranite Embedding 278M MultilingualGranite 4.0 MicroSavings
1M tokens $0.05 $0.06 $0.01 (15.5%)
10M tokens $0.53 $0.65 $0.12 (18.6%)
100M tokens $5.3 $6.45 $1.15 (17.8%)
1000M tokens $53 $64.5 $11.5 (17.8%)

Summary

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

Granite 4.0 Micro by IBM costs $0.017/Mtok input and $0.112/Mtok output, with a 128K-token context window. It supports text input.

On a blended cost basis, Granite Embedding 278M Multilingual is 21.7% cheaper than Granite 4.0 Micro.

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