Relace Search
Relace · released Dec 8, 2025
- Type
- Closed
- Input
- $1.00
- Output
- $3.00
- Cached
- None held
List price · per 1M tokens · Relace at 256K context · source ↗
Our take
Written Sep 2, 2026Relace Search is a hosted-only text model built for searching and retrieving information across very long documents. It handles up to 256,000 tokens in a single request and is available at the same rate across both tracked hosts.
Pick this for long-document search and retrieval where a quarter-million-token context removes the need to split documents into pieces. Use it when predictable, uniform pricing across hosts matters. Skip it if you need measured quality scores, fast throughput, or the option to run the model yourself.
The case for it
- 256,000-token request limit avoids chunking for most books and document collections.
- Identical pricing on both tracked hosts, with no premium for direct hosting.
The case against it
- Direct-host throughput is modest at 8.5 tokens per second.
- No benchmark scores in our data: chat, reasoning, coding and retrieval accuracy are all unverified.
- Proprietary weights with no disclosed licence for redistribution or local use.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Where to rent it
Prices checked 2 hours ago — each listing carries its own date.
Why this differs from the header. The strip above quotes Relace's own list price; this is the cheapest live offer, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $1.00 in / $3.00 out
- Context served
- 256K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $1.00 / $3.00checked 2 hours ago | 256K | not measured | Unknown | Unknown | Unknown |
| Relacebf16Through OpenRouter | $1.00 / $3.00checked 2 hours ago | 256K128K max reply | 9 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✗ |
| Relacebf16Through OpenRouter | ✓ | ✓ | ✗ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 0 of 2 listings say yes, 2 say no.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text in, text out
- Catalogue slug
- relace-relace-search