ModelPriceWatch.com
Last scan 2026-08-09 Models tracked 198 Providers 30 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

rerank-2.5 vs Granite Embedding 278M Multilingual

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

rerank-2.5 is 52.8% cheaper on blended cost ($0.050 vs $0.106/Mtok)
Specification
by IBM
Overview
StatusCurrent embedding Current embedding Open weights
Released Jun 1, 2025 Jun 1, 2025
Pricing per million tokens
Input $0.050/Mtok $0.106/Mtok
Output $—/Mtok $—/Mtok
Blended avg $0.050/Mtok $0.106/Mtok
Specifications
Context window tokens tokens
Parameters Proprietary 278M
Speed (TPS)
Modalities
Input
text
text
Providers
Available from
Voyage AI — $0.050/Mtok
IBM — $0.106/Mtok

Cost at scale

1M tokens · 50/50 input/output
Projected cost of rerank-2.5 vs Granite Embedding 278M Multilingual at increasing token volumes
Volumererank-2.5Granite Embedding 278M MultilingualSavings
1M tokens $0.05 $0.11 $0.06 (56.6%)
10M tokens $0.5 $1.06 $0.56 (52.8%)
100M tokens $5 $10.6 $5.6 (52.8%)
1000M tokens $50 $106 $56 (52.8%)

When to pick which

distilled from the pricing and spec data above
Pick rerank-2.5 if…
  • cost dominates: $0.050/Mtok blended vs $0.106 — 52.8% less on the same 50/50 token mix
Pick Granite Embedding 278M Multilingual if…
  • you want open weights — self-host it, fine-tune it, or exit the API entirely; rerank-2.5 is closed
Try rerank-2.5 on Voyage AI

The cheaper option here — rerank-2.5 costs $0.050/Mtok blended on Voyage AI.

Get API key →

Summary

rerank-2.5 by Voyage AI costs $0.050/Mtok input. It supports text input.

Granite Embedding 278M Multilingual by IBM costs $0.106/Mtok input. It supports text input.

On a blended cost basis, rerank-2.5 is 52.8% cheaper than Granite Embedding 278M Multilingual.

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

More comparisons

pairs sharing a model with this page