Liquid Inference changelog

version

3.11.0 → 4.0.1

file

absent → published

https://liquidinference.ai/llms.txt

+ # Liquid Inference+ > A live auction exchange for LLM inference. Send an ordinary OpenAI- or+ > Anthropic-shaped request; the exchange ranks the standing offers for the+ > model it names, fixes a price cap before the first token, and settles on+ > measured use.+ ## Site+ - [Liquid Inference](https://inference.ai.exchange/index.md): what the exchange is and how it works.+ - [Liquid CLI](https://inference.ai.exchange/cli.md): start a coding agent on the exchange from the terminal.+ - [Liquid MCP](https://inference.ai.exchange/mcp.md): give an agent the exchange as MCP tools.+ - [Liquid Enterprise](https://inference.ai.exchange/enterprise.md): organizations, your own cloud, guardrails and reserved capacity.+ - [Pricing](https://inference.ai.exchange/pricing.md): the monthly plans, the fee on Pay as you go, and how billing works.+ - [Prices](https://liquidinference.ai/prices.md): the best offer on the exchange against each creator's own API price, live from the book.+ ## Guides+ ### Get started+ - [Overview](https://liquidinference.ai/docs/overview.md): Buy inference, connect your tools, or sell your own models.+ - [Quickstart](https://liquidinference.ai/docs/quickstart.md): Make an API key and send your first request. Then read what it cost.+ - [Liquid CLI](https://liquidinference.ai/docs/cli.md): Install the CLI and sign in. Then start your coding agent on the exchange.+ - [API keys](https://liquidinference.ai/docs/keys.md): Make, limit and revoke API keys. Set scopes, spending limits and expiry.+ ### Buy+ - [Purchasing rules](https://liquidinference.ai/docs/rules.md): Choose the models, the ranking and the limits for each request.+ - [Bring your own key](https://liquidinference.ai/docs/byok.md): Connect your own cloud key. The exchange then sends requests through your account.+ - [Preferred providers](https://liquidinference.ai/docs/provider-preferences.md): Try providers in order, then use the rest of the eligible market.+ - [Receipts](https://liquidinference.ai/docs/receipts.md): Read the receipt of a job and check the charge.+ - [Fees](https://liquidinference.ai/docs/fees.md): The exchange fee: the percentage, the token floor, free offers and discounts.+ - [Workloads in the API](https://liquidinference.ai/docs/workloads-api.md): Send the profile of a saved workload, and what it does and does not do.+ - [Price and wait](https://liquidinference.ai/docs/price-and-wait.md): How the exchange adds the value of the wait to the charge, and how to change it.+ - [How performance is measured](https://liquidinference.ai/docs/performance-measurement.md): The base latency, prefill and output speed that the exchange measures.+ - [Axis routing](https://liquidinference.ai/docs/axis-routing.md): Rank offers by smartest, fastest or cheapest with a model-name suffix.+ - [Market data](https://liquidinference.ai/docs/market.md): Read the public book of offers, market depth and the live feed.+ - [Reservations](https://liquidinference.ai/docs/reservations.md): Buy a monthly pool of tokens from one provider at a fixed fee, through a preset.+ ### Router models+ - [Auto Router](https://liquidinference.ai/docs/auto.md): Let liquid.auto choose the model by published score and charge, within a cap.+ ### Capabilities+ - [Modalities](https://liquidinference.ai/docs/modalities.md): The map: what you can send, what you can buy, the formats, and what each costs.+ - [Image input](https://liquidinference.ai/docs/image-input.md): Send an image to a chat model.+ - [Audio input](https://liquidinference.ai/docs/audio-input.md): Send an audio clip to a chat model.+ - [Document input](https://liquidinference.ai/docs/document-input.md): Send a PDF to a chat model.+ - [Speech-to-text](https://liquidinference.ai/docs/speech-to-text.md): Buy a transcript of an audio file with an unchanged OpenAI client.+ - [Image generation](https://liquidinference.ai/docs/image-generation.md): Buy images with an unchanged OpenAI client.+ - [Speech](https://liquidinference.ai/docs/speech.md): Buy spoken audio from text.

Showing the first 40 of each.

version

3.10.1 → 3.11.0

version

3.8.0 → 3.10.1

version

3.7.0 → 3.8.0

version

3.6.0 → 3.7.0

version

3.5.0 → 3.6.0

version

3.3.0 → 3.5.0