AI models & inference

Text summarization for agents digesting long documents: condenses audit reports and governance discussions into structured summaries with configurable length and format. Category: inference.

Improve AI search visibility and get cited by ChatGPT, Perplexity, Claude & Google AI Overviews. AEO/GEO/SEO strategy, AI visibility audits, schema markup, llms.txt. 0.05 USDC/query.

Which NAIC insurance model laws a given state has adopted, inverted from the NAIC state-page corpus. Give a state (name or code) and an optional model or topic filter and get the models it has adopted with each classification, citation and linkback.

FDA inspection history for a manufacturer from public FDA records. Give an FDA FEI number or firm name and get the inspection classifications (Official, Voluntary or No Action Indicated) with the trend, plus the Form-483 observation citations with their cited CFR clause and short description. Deterministic, no LLM. Risk indicators, not legal or regulatory advice.

Pick the cheapest LLM that passes your task and constraints. Give a task class and optional constraints such as minimum context, required tool-use, vision or reasoning, maximum input and output price per million tokens, a minimum coding benchmark and a provider filter, and get a ranked cheapest-first list of models that pass, plus a recommended pick and a deterministic rationale. Fused from open keyless catalogs LiteLLM, models dev and Aider with a citation on every model.

OpenAI-compatible chat completion, priced by counted input tokens + max output tokens at per-model rates

Deterministic, paid-per-render SVG bar chart generator for LLM agents. Accepts labeled scalar data and layout options, performs exact geometry math (min/max normalization, nice-interval y-axis ticks, label spacing, bar-width distribution), and returns schema-valid, escape-correct SVG with identical input always yielding byte-identical output.

Every model on the OpenRouter marketplace with per-million-token input and output pricing, cached-input rates where published, and context windows: several hundred rows, rebuilt daily. Each build carries a changes block diffing it against the previous published build, listing models added, models the marketplace dropped with their last known figures, and every price or context-window movement as from/to. Spot repricing without re-reading 400 unchanged rows.

OpenAI-compatible chat completion, priced by counted input tokens + max output tokens at per-model rates

UUIDs, hashes, base64, URL encoding, secure passwords and timestamp conversion. Deterministic, no inference, answers immediately. POST {"op":"uuid","n":2}. Use it when your agent needs a fresh UUID, hash, password or encoding and cannot run code itself.

Won exchange rate for one currency on a date: KEXIM deal basis rate plus TTB and TTS, with the official date and source.

Declared route labor and fixed-cost allowance. Ceiling elapsed seconds times declared hourly cents plus fixed cents per active route. Modeled arithmetic only; no payroll or tax rules. Uses the paid-qualified existing VRP planner unchanged, then checks this business rule against the actual proposed route. A rule violation yields dispatch_ready=false, never an assertion that the extra constraint was optimized.

LLM chat completion processed in Germany. No training on inputs; usage logs exclude prompt/completion content. Responses are temporarily cached for redelivery.

Name your token workload and get every current LLM ranked by estimated USD cost to run it, with per-million-token prices, cached-input rates, context windows and provider. Combines an operator-verified pricing table with the wider marketplace listing and says which source each row came from. Filter by minimum context window or by provider, or restrict to verified rows only. Use it to pick the cheapest model that can actually hold your prompt.

Text classification (sentiment analysis, topic tagging, intent detection, moderation labels...) into one of your own labels, with a confidence score, via Claude Haiku 4.5. JSON body: {text: string (max 8000 chars), labels: string[] (2 to 20 labels)}.

Summarize text (article, transcript, report) into a given number of sentences, via Claude Haiku 4.5. Preserves the source text's language. JSON body: {text: string (max 8000 chars), max_sentences?: integer 1-10 (default 3)}.

Translate text into any target language, via Claude Haiku 4.5. JSON body: {text: string (max 8000 chars), target_lang: string (e.g. French, es, Japanese)}.

Chat completions via Telnyx Inference (google/gemma-4-26B-A4B-it). OpenAI-compatible. $0.003139 USDC per call.

LLM completion per call on a stronger model, no account needed: POST a prompt or messages array, get the answer as JSON. 6,000 UTF-8 bytes in, 1,200 tokens out, fixed price per call, hard caps disclosed in every response, signed receipt included. Smaller and cheaper tier at /x402/chat.

Gemma pricing table: what every Gemma model costs per token right now — Gemma 3, Gemma 2 — from Google and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare Gemma inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

GLM pricing table: what every GLM model costs per token right now — GLM-4.6, GLM-4.5 Air — from Zhipu AI and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare GLM inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Jamba pricing table: what every Jamba model costs per token right now — Jamba 1.5 Large, Jamba Mini — from AI21 and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare Jamba inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Kimi pricing table: what every Kimi model costs per token right now — Kimi K2, Moonshot v1 — from Moonshot AI and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare Kimi inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Llama pricing table: what every Llama model costs per token right now — Llama 4 Scout, Llama 4 Maverick, Llama 3.3 — from Meta and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare Llama inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Cheapest-model query: returns the lowest-cost AI models matching your constraints — min_context (tokens), vision/function_calling/reasoning (true), max_input_per_mtok (USD cap), limit (default 5). Add expected_input/expected_output token counts to rank by blended USD per request instead of input price; exclude_preview=true skips pre-release models. Answers 'what is the cheapest model that can do X?' across 2,000+ models and 70+ providers.

Cheapest 128k-context LLM leaderboard: the 50 lowest-cost AI models with a 128,000-token context window or larger, ranked by inference cost per token across 70+ providers. Input, output and cache USD per 1M tokens with exact context window and capability flags joined in. The standard long-document tier, priced side-by-side. Refreshed hourly.

Cheapest long-context LLM leaderboard: the 50 lowest-cost AI models with a 200,000-token context window or larger, ranked by inference cost per token — Claude 5, Gemini 3, GPT-5, Llama 4 Scout and more across 70+ providers. Input, output and cache USD per 1M tokens with exact context window and max output tokens joined in. Refreshed hourly.

Cheapest million-token-context LLM leaderboard: every AI model with a 1,000,000-token context window or larger, ranked by inference cost per token — Gemini 3 Pro, Gemini 3 Flash, Llama 4 Scout, GPT-5 long-context tiers and more. Input, output and cache USD per 1M tokens with exact context window and max output joined in. Answers 'what is the cheapest model that fits my whole corpus?' Refreshed hourly.

Cheapest LLM leaderboard: the 50 lowest-cost AI models available anywhere right now, ranked by inference cost per token across 70+ providers (OpenAI, Anthropic, Google, Meta, xAI, Mistral, DeepSeek). Input, output, cache and batch USD per 1M tokens, with context window and capability flags joined in. The one call that answers 'what is the cheapest model I can use?' Refreshed hourly.

Cheapest reasoning-model leaderboard: the 50 lowest-cost AI models with extended reasoning / chain-of-thought support, ranked by inference cost per token — o3, Claude 5 thinking, Gemini 3 Pro, DeepSeek R1, Qwen QwQ and more across 70+ providers. Input, output and cache USD per 1M tokens with context windows joined in. Refreshed hourly.