Relace Search with Jev
Relace Search is a model from Relace, released 2025-12-08. It costs $1.00 per million input tokens and $3.00 per million output tokens, reads up to 256K tokens of context, and writes up to 128,000 tokens in one reply. Through llm11, set model to relace/relace-search.
- Input price
- $1.00 / 1M
- Output price
- $3.00 / 1M
- Context window
- 256K tokens
- Max output
- 128K tokens
- Released
- 2025-12-08
- Accepts
- text
Read from the live catalogue and refreshed daily. At blended list price, 31% of the 332 priced models we can call cost more.
Using Relace Search with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Relace Search does the answering when Jev sends it work, or when you name it yourself. At list price Relace Search falls in the llm11-balanced band, but no pack routes to it because Relace is not one of the labs the packs draw from. You can still pin it: pass relace/relace-search as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Relace Search with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00110 | $1.10 |
| Question over retrieved documents | 4,000 / 500 | $0.00550 | $5.50 |
| Long document summary | 30,000 / 1,000 | $0.033 | $33.00 |
Cheaper models to try
The catalogue has no benchmark score for Relace Search, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| DeepSeek DeepSeek V4 Pro 0813 | $0.475 | $4.20 | 1.05M | |
| Qwen Qwen3 Coder PlusRetires 2026-10-09 | $0.650 | $3.25 | 1M | |
| Qwen Qwen3 VL 235B A22B ThinkingRetires 2026-10-09 | $0.400 | $4.00 | 131K | |
| Qwen Qwen3.5 397B A17B | $0.550 | $3.50 | 262K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="relace/relace-search",
messages=[{"role": "user", "content": "Hello"}],
)More from Relace
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Relace Apply 3 | $0.850 | $1.25 | 256K |
Questions
- What is Relace Search with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Relace Search does the answering when Jev sends it work, or when you name it yourself. At list price Relace Search falls in the llm11-balanced band, but no pack routes to it because Relace is not one of the labs the packs draw from. You can still pin it: pass relace/relace-search as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Relace Search a System One model?
- No. Relace Search answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Relace Search cost?
- $1.00 per million input tokens and $3.00 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00550, so a thousand of them is about $5.50. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Relace Search context window?
- 256,000 tokens, with up to 128,000 tokens in a single reply.
- Does Relace Search support tool calling and structured output?
- The catalogue lists tool calling and structured output, but it does not list reasoning controls.
- Can I use Relace Search through llm11?
- Yes. Set model to relace/relace-search on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Relace Search?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Relace Search falls in the llm11-balanced band, but no pack routes to it because Relace is not one of the labs the packs draw from. You can still pin it: pass relace/relace-search as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Relace Search?
- Nearest in price and below it: DeepSeek DeepSeek V4 Pro 0813 at $0.475 in and $4.20 out, Qwen Qwen3 Coder Plus at $0.650 in and $3.25 out and Qwen Qwen3 VL 235B A22B Thinking at $0.400 in and $4.00 out. The catalogue has no benchmark score for Relace Search, so this is a price ordering. It does not claim these answer as well.