rerank-2.5-lite vs Granite Embedding 278M Multilingual
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
rerank-2.5-lite is 81.1% cheaper on blended cost ($0.020 vs $0.106/Mtok)
| Specification |
by Voyage AI
|
by IBM
|
|---|---|---|
| Overview | ||
| Status | Current embedding | Current embedding Open weights |
| Released | Jun 1, 2025 | Jun 1, 2025 |
| Pricing per million tokens | ||
| Input | $0.020/Mtok | $0.106/Mtok |
| Output | $—/Mtok | $—/Mtok |
| Blended avg | $0.020/Mtok | $0.106/Mtok |
| Specifications | ||
| Context window | — tokens | — tokens |
| Parameters | Proprietary | 278M |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Providers | ||
| Available from |
Voyage AI — $0.020/Mtok
|
IBM — $0.106/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | rerank-2.5-lite | Granite Embedding 278M Multilingual | Savings |
|---|---|---|---|
| 1M tokens | $0.02 | $0.11 | $0.09 (84.9%) |
| 10M tokens | $0.2 | $1.06 | $0.86 (81.1%) |
| 100M tokens | $2 | $10.6 | $8.6 (81.1%) |
| 1000M tokens | $20 | $106 | $86 (81.1%) |
When to pick which
distilled from the pricing and spec data above
Pick rerank-2.5-lite if…
- cost dominates: $0.020/Mtok blended vs $0.106 — 81.1% 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-lite is closed
Try rerank-2.5-lite on Voyage AI
The cheaper option here — rerank-2.5-lite costs $0.020/Mtok blended on Voyage AI.
Summary
rerank-2.5-lite by Voyage AI costs $0.020/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-lite is 81.1% 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
Rerank 3.5 vs Granite Embedding 278M Multilingual
81% price gap
text-embedding-3-small vs Granite Embedding 278M Multilingual
81% price gap
voyage-4-lite vs Granite Embedding 278M Multilingual
81% price gap
rerank-2.5 vs Granite Embedding 278M Multilingual
53% price gap
voyage-4 vs Granite Embedding 278M Multilingual
43% price gap
Rerank 3.5 vs rerank-2.5-lite
text-embedding-3-small vs rerank-2.5-lite
Claude Fable 5 vs DeepSeek V4 Pro
97% price gap