Price directory
Reranker API pricing, per search or per 1M tokens.
8 rerankers — priced per search or per 1M tokens; every price dated and sourced.
Latest events
Mercury 2.5 launches at $0.04/$0.15
Sep 8, 2026
At $0.04/$0.15 per MTok, Mercury 2.5 prices roughly 6x below Mercury 2's Output cost ($0.75/1M) dramatically undercuts Claude Haiku ($4.00) and Gemini Flash ($2.50) baseline, while still matching quality on cost-optimized frontier models like GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5.
GPT-6 Astra launches at $50/MTok
Sep 3, 2026
Muse Spark 1.3: 90% training discount
Sep 2, 2026
Claude Fable/Mythos 5.1: 75% cache cut
Sep 1, 2026
Meta Muse Image: $0.01 per image
Aug 27, 2026
Price table
| Model | Provider | Pricing | Released | ||
|---|---|---|---|---|---|
|
Z
ZeroEntropy's reranker, billed per token; weights on Hugging Face.
—/—I/O
|
ZeroEntropy | $0.025 / 1M tokens Token-based as of Jul 2026 | — | ||
|
J
Jina AI's flagship reranker (131K context, up to 64 documents).
—/—I/O
|
Jina AI | Pricing not published | — | ||
|
V
Voyage AI's lighter, cheaper reranker.
—/—I/O
|
Voyage AI | $0.02 / 1M tokens Token-based as of Jul 2026 | — | ||
|
V
Voyage AI's general reranker, billed per token of query and documents.
—/—I/O
|
Voyage AI | $0.05 / 1M tokens Token-based as of Jul 2026 | — | ||
| Cohere | $2.00 / 1K searches Per search as of Jul 2026 | — | |||
|
P
Pinecone's hosted reranker, via Pinecone Inference.
—/—I/O
|
Pinecone | $2.00 / 1K requests Per search as of Jul 2026 | — | ||
|
M
Mixedbread's open-weight (Apache-2.0) cross-encoder reranker.
—/—I/O
|
Mixedbread | $0.10 / 1K queries Per search as of Jul 2026 | — | ||
|
B
BAAI's open-weight (Apache-2.0) cross-encoder reranker, the canonical open baseline.
—/—I/O
|
BAAI | Pricing not published | — |
Select a model
Select a model