Rerank 3.5 vs rerank-2.5
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
Rerank 3.5 is 60% cheaper on blended cost ($0.020 vs $0.050/Mtok)
| Specification |
by Cohere
|
by Voyage AI
|
|---|---|---|
| Overview | ||
| Status | Current embedding | Current embedding |
| Released | Mar 1, 2025 | Jun 1, 2025 |
| Pricing per million tokens | ||
| Input | $0.020/Mtok | $0.050/Mtok |
| Output | $—/Mtok | $—/Mtok |
| Blended avg | $0.020/Mtok | $0.050/Mtok |
| Specifications | ||
| Context window | — tokens | — tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Providers | ||
| Available from |
Cohere — $0.020/Mtok
|
Voyage AI — $0.050/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Rerank 3.5 | rerank-2.5 | Savings |
|---|---|---|---|
| 1M tokens | $0.02 | $0.05 | $0.03 (60%) |
| 10M tokens | $0.2 | $0.5 | $0.3 (60%) |
| 100M tokens | $2 | $5 | $3 (60%) |
| 1000M tokens | $20 | $50 | $30 (60%) |
When to pick which
distilled from the pricing and spec data above
Pick Rerank 3.5 if…
- cost dominates: $0.020/Mtok blended vs $0.050 — 60% less on the same 50/50 token mix
Pick rerank-2.5 if…
- this pairing gives rerank-2.5 no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)
Try Rerank 3.5 on Cohere
The cheaper option here — Rerank 3.5 costs $0.020/Mtok blended on Cohere.
Summary
Rerank 3.5 by Cohere costs $0.020/Mtok input. It supports text input.
rerank-2.5 by Voyage AI costs $0.050/Mtok input. It supports text input.
On a blended cost basis, Rerank 3.5 is 60% cheaper than rerank-2.5.
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
Rerank 3.5 vs voyage-4
67% price gap
text-embedding-3-small vs rerank-2.5
60% price gap
rerank-2.5 vs Granite Embedding 278M Multilingual
53% price gap
Rerank 3.5 vs text-embedding-3-small
Rerank 3.5 vs rerank-2.5-lite
Rerank 3.5 vs voyage-4-lite
Claude Fable 5 vs DeepSeek V4 Pro
97% price gap