Rerank 2
rerank-2Pricing
List prices at VoyageAI by MongoDB, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.05 | $0.00 |
What it costs a month
At VoyageAI by MongoDB list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$15.00
- RAG over documents2,000 requests a day, 8K in / 0.6K out$24.00
- Coding agent1,000 requests a day, 40K in / 2K out$60.00
- Overnight batch20,000 requests a day, 4K in / 0.4K out$120
Where to run it
1 host serve Rerank 2. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
VoyageAI by MongoDBCloud rerank-2 | $0.05 / $0.00 | rerank-2 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than VoyageAI by MongoDB.
Smaller Cohere models
- 60% less
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
No cheaper open-weight match.
Model line
Newer and older versions, at each lab's own price.
- UndatedRerank V3.5LatestNot listed
- UndatedRerank V3Not listed
- UndatedRerank 3$0.05 / $0.00
- UndatedRerank 2.5$0.05 / $0.00
- UndatedRerank 2This page$0.05 / $0.00
- UndatedRerank 1$0.05 / $0.00
Call it
Using VoyageAI by MongoDB's API.
from litellm import completion
response = completion(
model="voyage/rerank-2",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Rerank 2 cost?
On VoyageAI by MongoDB, Rerank 2 costs $0.05 per million input tokens.
Which APIs offer Rerank 2?
Rerank 2 runs on 1 API: VoyageAI by MongoDB.
What is Rerank 2's context window?
16K tokens, with up to 16K tokens in one reply.
Is Rerank 2 being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Rerank 2?
Yes. Rerank V3.5 is the newest model in this line.
What are cheaper alternatives to Rerank 2?
Models that cost less and keep most of what it can do: Rerank V5.0 Fast on Cohere (60% less).
What is Rerank 2's API model id?
Use rerank-2 with VoyageAI by MongoDB.
Sources
Raw catalog entry for rerank-2 on VoyageAI by MongoDB
{
"input_cost_per_token": 5e-8,
"litellm_provider": "voyage",
"max_input_tokens": 16000,
"max_output_tokens": 16000,
"mode": "rerank",
"output_cost_per_token": 0
}