AI models & inference

NHTSA safety recalls for a vehicle by make/model/year: campaign number, affected component, summary, consequence, and remedy. Live gov data, no key.

Google's native generateContent wire on the nano tier. Send Gemini's own request shape (contents, systemInstruction, generationConfig, function declarations) and get Gemini's own response shape (candidates, usageMetadata) back. Point a Google GenAI SDK at this gateway and pay per request with USDC, no account. Also answers the Google-shaped path /v1beta/models/<model>:generateContent.

Google's generateContent wire priced from the request itself: the 402 quotes this exact body, from $0.001, with upto buyers settling actual usage. Use it when an agent built on the Gemini SDK needs a supported model paid per call without an API key.

Compress a string with Brotli (RFC 7932) and return it as base64. Brotli typically beats gzip by 15-25% on text - useful when bytes matter (e.g. cramming context into an LLM prompt, fitting under a transport cap). Slower than gzip; pick gzip if speed matters more than ratio.

Split text into overlapping chunks for RAG ingestion - by characters (default) or by exact LLM tokens. Returns the chunks plus offsets. Deterministic, no model needed.

Reloadpi — Order status and refund schema. Returns the fulfillment state machine, polling URL, and refund endpoint for any paid order.

Compares two submitted sample sets feature by feature and returns deterministic drift metrics. Continuous features are binned on the combined value range and receive PSI, Jensen-Shannon divergence and a Kolmogorov-Smirnov statistic; categorical features receive PSI and Jensen-Shannon divergence over exact category labels. The response names every feature, its sample counts, the metric values, the threshold used, and the reason a feature was flagged.

LLM chat completion per call — no account, no API key, no token math. Three flat-priced tiers: fast $0.002 (DeepSeek v4 Flash), smart $0.02 (GPT-5.4 mini), reasoning $0.03 (DeepSeek v4 Pro). Send OpenAI-style messages, get the assistant reply with finish_reason and token usage. Input capped per tier (16k-32k chars); the 402 quotes the exact tier price up front. Model or source unavailable means a 503 and you pay nothing. USDC on Base.

Chat completions via Telnyx Inference (google/gemma-2b-it). OpenAI-compatible. $0.002 USDC per call.

IBM watsonx pricing table: per-token cost of every AI model IBM watsonx serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside IBM watsonx and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

LLM completion per call, no account and no API key: POST a prompt (or a messages array) and get the model answer as JSON. Hard caps disclosed in every response (6,000 UTF-8 bytes in, 750 tokens out on this tier). Fixed price per call, signed receipt included so the answer stays auditable. Larger tier at /x402/chat-plus.

Embeds up to 32 texts on the local Ollama runtime. Returns explicit model and dimensions; no paid third-party API is called.

GPT pricing table: what every GPT model costs per token right now — GPT-5, GPT-5 mini, GPT-4o, GPT-4.1, o3 — from OpenAI 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 GPT inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Chat completions via Telnyx Inference (meta-llama/Meta-Llama-3.1-8B-Instruct). OpenAI-compatible. $0.002237 USDC per call.

Get a short completion from a capable model, paid per call, with a bounded output of 2000 tokens. LLM inference pay-per-call, no account, no API key: prompt in, completion out (DeepSeek v4, up to 2000 output tokens). STANDARD tier; /v1/llm/pro is the PRO tier with four times the output budget. Original note on $/c…

Get a long completion with a large output budget, same engine as /v1/llm. Long-form LLM inference: same engine as /v1/llm with a four times larger output budget, up to 8000 tokens, for answers the cheap route truncates. Body: {prompt, system?, max_tokens?}

General LLM completion: send a prompt (optional system role), get an answer. Reason, rewrite, classify, draft or answer. Flat price, input/output capped.

Groq model pricing — input/output $/M tokens, context windows — Ed25519 signed attestation

Google's fast model — great balance of speed, quality, and cost for everyday tasks

Accumulates simple daily degree-days above a supplied base temperature and combines threshold progress with mean humidity and host availability. The score is a deterministic planning heuristic over caller data; it does not identify a pest, ingest surveillance data, model population dynamics or prescribe pesticide use.

Google's latest fast multimodal model with a 1M-token context window

Moonshot AI's flagship model — strong reasoning and long-context capabilities

DeepSeek's flagship chat model — strong open-source reasoning and coding at low cost

Generate images from text prompts. Pay per call with USDC (x402) or credits - archtools.dev

GPTBot access audit fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

llms.txt available audit fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

llms.txt available decision fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

llms.txt available repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Amazon Seller Central and Ads inside Claude or ChatGPT. Real fees from your own settlements.

Let Claude, Cursor, or ChatGPT author Mermaid diagrams your team can read and share.