Relace Search
Relace · released Dec 8, 2025
- Type
- Proprietary
- Input
- $1.00
- Output
- $3.00
- Cached
- Not published
List price · per 1M tokens · Relace at 256K context · source ↗
Our take
Written Aug 3, 2026Relace Search is a hosted-only text model built for long-document retrieval and analysis, with a 256,000-token request limit that lets you send entire documents without splitting them. It is a cost-predictable option with identical rates across both providers, though no independent quality scores are available yet.
Choose this when you need to search or analyse very long documents in one pass, and want predictable costs regardless of which provider you pick. Use it if you value knowing the exact throughput on Relace's own endpoint. Skip it if you need measured quality benchmarks, faster generation speed, or any choice of price or provider.
The case for it
- 256,000-token request limit, large enough for most long documents without chunking.
- Identical pricing across both tracked providers, so costs do not shift when you switch host.
- Known throughput of 6.5 tokens per second on Relace's direct endpoint.
The case against it
- No benchmark scores in our data — chat, reasoning and retrieval accuracy are all unverified.
- Only 6.5 tokens per second on direct hosting, the only throughput figure we hold, and it is low.
- Just two offers with identical pricing, so there is no price competition or faster alternative in our data.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Relace Search — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
Why this differs from the header. The strip above quotes Relace's own list price. This is the cheapest live offer at the widest standard context we hold, 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $1.00 / $3.00 | 256K | not measured | Unknown | Unknown | Unknown |
| Relacebf16 | $1.00 / $3.00 | 256K | 4 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✗ |
| Relacebf16 | ✓ | ✓ | ✗ |
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
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, 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 do not say whether they train on prompts.
- We hold no cached-input 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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text->text
- Catalogue slug
- relace-relace-search