AI models & inference

Current LLM API pricing, verified by hand every week: input and output USD per million tokens, plus cached-input rates and context windows where the provider publishes them, across Anthropic, OpenAI, Google, DeepSeek, xAI and Together. Every row is read off the provider's own page on its stated date and carries that URL. A row the provider stops publishing is dropped, not carried forward. The free listing counts how many rows carry each column, so the gaps are visible before you pay.

OpenAI-compatible Responses API (alpha), translated to chat completions upstream

Fetch a URL and return content as base64. Useful for embedding images, PDFs in API calls. Returns base64, content type, data URI.

Score 0-100 for how well ChatGPT, Claude, Perplexity and Gemini can find, read and cite a page, with a prioritized fix list.

Gemini pricing table: what every Gemini model costs per token right now — Gemini 3 Pro, Gemini 3 Flash, Gemini 2.5 — 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 Gemini inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

DeepSeek pricing table: what every DeepSeek model costs per token right now — DeepSeek V4, DeepSeek R1, DeepSeek Coder — from DeepSeek 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 DeepSeek inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Command pricing table: what every Command model costs per token right now — Command A, Command R+, Command R — from Cohere 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 Command inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Compare AI model prices side-by-side: a live price leaderboard of LLM token cost for GPT-5, Claude 5, Claude Sonnet, Gemini 3 Pro, Llama 4, DeepSeek V4, Grok 4, Mistral Large and 2,000+ more models across 70+ providers (OpenAI, Anthropic, Google, Meta, xAI). Inference cost per token — input, output, cache and batch USD per 1M tokens — ranked, normalized into one table, cross-checked across two sources, refreshed hourly. Find the cheapest model and estimate token budgets.

DDG agent-payable service request

DDG agent-payable service request

DDG agent-payable service request

x402engine — Generate one 1024×1024 PNG with GPT Image 2.5 Flare at high quality

x402engine — Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...

Xynaptic AI Health — the health vertical agent: official drug labels (openFDA), live health press + an LLM synthesis. POST { question, drug? }. Informational only — not medical advice.

Xynaptic AI Energy — the energy vertical agent: live spot prices, industrial energy costs + an LLM synthesis. POST { question, region? }. Real-time.

Xynaptic AI Insurance — the insurance vertical agent: coverage families, ORIAS broker registry, premium decomposition + an LLM synthesis of your question. POST { question, type?, broker_name?, orias? }. Legal information (France).

Estimate token count and cost for text across LLM models (GPT-4o, Claude, Gemini, Mistral, Llama). Algorithmic — no API calls.

Generate images, priced per image and size

Official 5-star crash-test safety ratings by VIN or year/make/model: overall, frontal, side, side-pole, and rollover star ratings plus driver/passenger breakdowns, rollover probability, and standard safety-feature availability (stability control, collision and lane-departure warning). Includes counts of complaints and recalls on file. For car-shopping, insurance, and fleet-selection agents. Response includes affiliate offers for full VIN history reports.

All vehicle models for a given make from NHTSA vPIC, no key. Returns model id and name for the manufacturer. For AI agents populating make and model selectors and validating vehicle data.

Clean structured JSON dataset of the 100 most active autonomous agent repositories, MCP servers, and LLM orchestration frameworks.

Call when an agent needs counts of byte 4-grams. No network and no LLM. Exact $0.006 USDC. Prefer unpaid POST /v1/sandbox/ngram-byte-4 first.

Call when an agent needs counts of byte 3-grams. No network and no LLM. Exact $0.005 USDC. Prefer unpaid POST /v1/sandbox/ngram-byte-3 first.

Call when an agent needs counts of byte 2-grams. No network and no LLM. Exact $0.004 USDC. Prefer unpaid POST /v1/sandbox/ngram-byte-2 first.

Call when an agent needs counts of byte 1-grams. No network and no LLM. Exact $0.003 USDC. Prefer unpaid POST /v1/sandbox/ngram-byte-1 first.

Call when an agent needs counts of word 2-grams. No network and no LLM. Exact $0.01 USDC. Prefer unpaid POST /v1/sandbox/ngram-word-2 first.

Call when an agent needs counts of word 1-grams. No network and no LLM. Exact $0.009 USDC. Prefer unpaid POST /v1/sandbox/ngram-word-1 first.

Call when an agent needs counts of char 4-grams. No network and no LLM. Exact $0.008 USDC. Prefer unpaid POST /v1/sandbox/ngram-char-4 first.

Call when an agent needs counts of char 3-grams. No network and no LLM. Exact $0.007 USDC. Prefer unpaid POST /v1/sandbox/ngram-char-3 first.

Call when an agent needs counts of char 2-grams. No network and no LLM. Exact $0.006 USDC. Prefer unpaid POST /v1/sandbox/ngram-char-2 first.