Relace · language model
Relace Search: pricing, context and benchmarks
Relace Search is Relace's model released on December 8, 2025. It costs $1 per million input tokens and $3 per million output tokens, with a 256K-token context window. No independent score has been published for it so far.
| Price | 10/30 | |
|---|---|---|
| Context | 6/15 | |
| Features | 8/15 |
What you need to know about Relace Search
Relace, based in United States, put Relace Search online on December 8, 2025. It accepts text as input and produces text. Its context window reaches 256,000 tokens, larger than 41 % of the models in the registry, and it can write up to 128,000 tokens in one go.
It has been available for about 11 months, long enough for its prices and scores to have settled.
Relace Search pricing
On OpenRouter, Relace Search costs $1 per million input tokens and $3 per million output tokens. Counting three tokens read for every token written, its average price is $1.5 per million, more expensive than 66 % of paid models (2 times the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0035. At 1,000 tasks a day, budget $105 a month. The price calculator redoes this with your own volumes.
Performance and benchmarks
Epoch AI does not yet publish a capabilities index for Relace Search. We therefore show no made-up performance rating: only price, context and features count towards its score.
Features, privacy and local use
- It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
- It can answer in an enforced JSON format (structured outputs).
Its weights are not published: it can only be used through the Relace API or a broker such as OpenRouter, which means sending your data off your machines.
Other Relace models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| Relace Apply 3 | Sep 26, 2025 | $0.95 | — |
Verdict
Computed score: 40/100, from public data (performance, price, context, features).
Strengths
- Agent-ready: tool calling and structured JSON output.
Limitations
- No independent score published: performance cannot be verified.
- Text only: reads neither images nor files.
Avoid if…
- your data must not leave your servers.
Alternatives
- GLM 5$1.55
- Grok Build 0.1$1.25
- GLM 5V Turbo$1.9
- GLM 5 Turbo$1.9
- Hermes 4 405B$1.5
- o4 Mini$1.93
Comparisons and tools
Learn more
Frequently asked questions
How much does Relace Search cost?
$1 per million input tokens and $3 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.0035.
How big is Relace Search's context window?
256,000 tokens, roughly 192,000 words, with a maximum of 128,000 output tokens.
Can Relace Search run locally?
No, Relace does not publish its weights: it is API-only.
Is Relace Search suitable for an AI agent?
Technically yes: it supports tool calling and structured outputs. Then check its cost for your volume.
What are the alternatives to Relace Search?
The closest models on price and performance are GLM 5, Grok Build 0.1, and GLM 5V Turbo.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score