Relace Search
Tool-capable chat model for instruction following and agentic application workflows.
- Capability
- —No ECI score yet
- Input
- $1.00per 1M tokens
- Output
- $3.00per 1M tokens
- Context
- 256K128K max output
What it costs
- Input
- $1.00per million tokens
- Output
- $3.00per million tokens
- Blended (3:1)
- $1.50pricier than 65% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $3.50 |
| Team assistant25M input + 5M output tokens | $40.00 |
| Production app250M input + 50M output tokens | $400.00 |
Median of 3 paid API providers on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Relace Search yet.
The details
- Lab
- Relace
- Released
- Dec 8, 2025
- Context window
- 256,000 tokens
- Max output
- 128,000 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Weights
- Proprietary
- Availability
- 3 API providerslisted on models.dev
More from Relace
About Relace Search
How much does Relace Search cost?
Relace Search costs $1.00 input / $3.00 output per million tokens (median across 3 API providers). At a 3:1 input-to-output mix that is $1.50 per million tokens, more expensive than 65% of the 445 priced models we track.
What is the context window of Relace Search?
Relace Search accepts up to 256,000 tokens per request and can write up to 128,000 tokens in one response.
How good is Relace Search?
Epoch AI has not published a Capabilities Index score for Relace Search yet.
Is Relace Search open source?
No. Relace Search is proprietary; you use it through an API or partner platforms.
What inputs does Relace Search support?
Relace Search accepts text and replies in text. It is not a dedicated reasoning model, supports tool calling.
When was Relace Search released?
Relace released Relace Search on Dec 8, 2025.
What are the best alternatives to Relace Search?
The closest current models from other labs on capability, price and release date are MiMo-V2-Pro (Xiaomi, $1.00 / $3.00), Grok 4.20 (Non-Reasoning) (xAI, $1.25 / $2.50), Hermes 4 405B (Nous Research, $1.00 / $3.00) and Qwen3 VL 235B A22B Thinking (Alibaba (Qwen), $0.50 / $3.95).