Introducing Liquid Inference by Architect, a new LLM model router where inference providers compete dynamically to offer lowest-cost tokens. Providers onboard in minutes, not weeks. Buyers have full price visibility and receive 20% of referred fees in free inference. More info: Liquid Inference can be used in place of any OpenAI or Anthropic API-compatible backend. Behind it, our team has leveraged our experience trading and building financial exchanges to create real-time two-sided price discovery for inference. Benefits for buyers and providers: INFERENCE BUYERS • Fully compatible with agentic coding tools: Claude Code, Codex, OpenCode, Cursor, Pi, Cline, and many more. Full multi-modal support. • Hundreds of open- and closed-weight models. Create routing rule presets or use our Auto routing algorithms. • Providers compete dynamically on price for every prompt, offering the lowest marginal cost. • Sign up for free with email, first 500 users get $20 of free inference. • Receive 20% of referred fees as free inference, 10% for second-level referrals. INFERENCE PROVIDERS • Onboard through the Liquid Inference app. We verify new providers in minutes, not weeks. • All prompts are OpenAI API standard. Simple REST/Websocket API to register models and quotes. • Update quotes dynamically based on your own costs. Monetize GPU capacity only when you want. • Standardize payouts via Stripe, full itemized records of all jobs performed.

Why has nobody made an *actually* open router? Feel like such an opportunity to have lower cost

Announcing Reservations on Liquid Inference. Inference buyers can now reserve batches of tokens in advance at fixed prices over any time period. Providers compete to offer the best terms and SLAs instantly. How it works: • Enter a lock-in duration from 1 to 12 months • Specify token rate and uptime requirements • Select from ZDR, SOC2, and other compliance/privacy features • Receive multiple quotes and terms • Negotiate through in-app messaging directly with providers • Optionally allow overage to automatically query the spot market Providers benefit from standardized contracts, automated billing, SLA monitoring, and zero additional fees to participate. Check it out and let us know, we’re here for all feedback.

Last month, we demonstrated high-rate alchemy: turning mercury into real, stable gold, beating CERN’s record by a factor of 10. Last week, we enriched isotopes in the world’s most powerful plasma centrifuge, beating the Soviet record that stood for 40 years. Now, we’re building a fusion reactor in San Francisco to achieve record power density.

Fifty providers are now in the Liquid Inference network, up 22 in a week, over half the size of competitors’ networks in two weeks since launch. Every frontier open-weight LLM is quoted, and we actively benchmark all model+provider pairs to ensure model weight fidelity.

"The man who does not use computation cannot compete with the man who avails himself of its secrets. No hedge fund can price second order effects faster than a 200-megawatt Jane Street data center. No lone genius can produce a better language model than Anthropic." @CooperVeit3 on the secretive, unborn market for compute: arenamag.com/articles/counti…

Guys, I found something new and fun — and there are a lot of free models right now, including the latest DeepSeek V4.1 Flash. Someone mashed model inference together with exchange mechanics. Picking inference used to mean shopping a price list. Liquid Inference flips it: inference as an exchange. Providers list offers per model; your request goes into an auction under your rules. You set a budget cap, time-to-first-token, and whether data can be retained. The system drops anything that fails those filters, then awards the lowest eligible bid (or fastest / smartest). Price locks before the first token; you settle on measured usage, with a receipt per job. OpenAI- and Anthropic-compatible — swap base URL + key and go. Coding agents like Cursor, Claude Code, and OpenCode plug in too. Public order book and price history; when supply and demand shift, prices move. This isn’t another aggregator gateway. It’s inference bidding with a real order book. Use the best models at the lowest prices — vendors compete on cost, users get the upside. Live right now: 894 models (chat / image / video / embeddings / speech), 104 providers, nearly a thousand offers, plus :cheapest / :fastest / :smartest or liquid.auto auto-routing. Try it: inference.ai.exchange/sign-u…

Architect made AI usage cheaper. Liquid Inference runs a live auction on every prompt so providers compete! inference.ai.exchange/sign-u…

Liquid Inference now supports images and video! Video inference costs aren’t optimized to the same level as text, and a fair auction brings iterative AI content creation in line. Access via our API or check out the compare tool in our web playground.

you can get kimi k3 on liquid inference for $0.39 per million input tokens and $0.57 output right now moonshot's own api is $3 and $15. the cheapest provider on openrouter is $0.73 and $10 it's still cheaper after their cache discounts too the difference is market design. on openrouter each provider lists a fixed price and openrouter spreads traffic across them. on liquid every request is an auction, providers can reprice any minute, and the cheapest offer that meets your speed and quality rules wins markets will exist for compute and tokens just like for other commodities

Onboarding to Liquid Inference takes 3 easy steps: 1. Fund your workspace - new accounts start with free credit 2. Make a Preset under Rules once, use it forever 3. Send your first prompt and compare costs and model output side by side