# Liquid Inference (liquidinference.ai)

Routes each AI model request to the lowest-priced provider offer that meets your terms, with a capped price set before the job starts.

- Atlas card: https://inite.ai/en/atlas/liquidinference.ai
- Site: https://liquidinference.ai
- For: Developers and teams sending LLM requests through OpenAI or Anthropic-style code who want the cheapest qualifying model per prompt.
- Categories: agents
- Use not measured/100 · alive 100/100

## Used for

- route each prompt to the cheapest model meeting requirements
- cap per-job cost before requests start
- compare provider token prices for each request

## Price

Not read yet.

## For developers

- MCP server: ai.liquidinference/liquid (namespace; auth on 2026-11-04)
- Read 2026-11-04

## MCP server, measured daily

Server: https://router.inference.ai.exchange/mcp, checked every day since 2026-11-04 (1 checks).

- Answered: measuring, 1 daily checks so far
- Median first answer: 316 ms
- Sign-in: OAuth (the client signs the user in)
- Method: https://inite.ai/en/atlas/mcp/report

## Your data

- Certifications stated: none
- Read 2026-11-04

---

Source: INITE Atlas, https://inite.ai/en/atlas/liquidinference.ai. JSON: https://inite.ai/api/atlas/liquidinference.ai. MCP: https://inite.ai/api/mcp (atlas_lookup).