Auto x402 REST usage
One-shot prepaid tap: empty body buys a 100000-token openai/gpt-6-luna key
Model inference and embedding endpoints, including routers that front several providers. Context limits and prices change often, so treat the price with its check date.
One-shot prepaid tap: empty body buys a 100000-token openai/gpt-6-luna key
General LLM completion: send a prompt (optional system role), get an answer. Reason, rewrite, classify, draft or answer. Flat price, input/output capped.
Price a European option (call or put) with the Black-Scholes-Merton model, plus the greeks (delta, gamma, vega, theta, rho). Continuous dividend yield supported. Greeks are per unit: theta is per year, vega per 1.00 chan...
Chat completions via Telnyx Inference (deepseek-ai/DeepSeek-V4-Flash-0731). OpenAI-compatible. Up to $0.00527 USDC per call, quoted to your request (input + max_tokens at list rates, no markup).
Text completion using the model selected in the request body.
LLM chat completions API for DeepSeek 4.1 Uncens. with streaming answers. Pay in USDC on Base or Solana. Owner-set spend limits via MCP/API keys.
x402engine — Fast, affordable GPT-4o variant — great for simple tasks and high-volume use
NeuroSpark AI Inference: Chat completions from NeuroSpark’s hosted models: GLM-5.3, GLM-5.3-Flash, DeepSeek V4.1 Flash and Claude Sonnet 5. OpenAI-compatible inference with GLM-5.3, GLM-5.3-Flash, DeepSeek V4.1 Flash and...
Count DNA/RNA bases and ambiguities and calculate GC fraction on called bases only. Refuses mixed DNA/RNA alphabets; no sequence design or clinical inference.
GPT-OSS 120B: OpenAI's open-weight 120B. Reasoning at a low price.
Lowest-price LLM micro-completion for classify, extract, rewrite, yes/no and one-line answers. POST a short prompt (up to 2000 chars), get up to 128 tokens back.
AI model cost comparison: return suitable model options under the supplied constraints. Use it when an agent needs a routing decision.
Translation for agents handling multilingual DeFi content: converts protocol docs and error messages across languages with tone control and auto source-language detection. Category: inference.
Detect the language of a text without AI (55 languages, statistical langdetect model) with probability and alternatives. Fast and cheap for routing messages or choosing a translation.
Repair broken JSON, typical of LLM output: strips ```json fences, comments and surrounding text, trailing commas, single quotes, unquoted keys, Python True/None and unclosed brackets. Returns the object and clean JSON an...
GPT-5.6 Luna — fast, low-cost frontier model (Artificial Analysis Intelligence Index 51.2, GPQA Diamond 91.1%). Best for high-volume chat, classification, extraction, and lightweight agentic loops where latency and cost...
JSON Schema validator: check a JSON document or LLM structured output against a JSON Schema (draft-07, 2019-09, 2020-12). Returns valid true/false and every error with its JSON Pointer, keyword and message. Send json and...
OpenAI-compatible moderation, pay per request: one input in, flagged and categories out (Llama Guard 3, 14 hazard categories mapped onto OpenAI names). No account or API key; failed calls are not charged.
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 n...
Exact token count for text using OpenAI tokenizers. Body: {text, encoding?} where encoding is cl100k_base or o200k_base (default). Returns tokens and char_count. Use to budget prompts and context windows.
High-quality LLM translation with control: target language, optional formality and tone, auto source detection. Preserves nuance and idiom.
Fetches a public web page URL and returns its main article content as clean Markdown with title, byline and excerpt; strips navigation, ads and scripts. Useful for RAG ingestion and LLM context.
API prices of 400+ LLMs (OpenAI, Anthropic, Google, DeepSeek, Llama, Qwen...) per million input/output tokens with context length, searchable by name and sortable by price, context or newest.
Count a text's tokens and estimate the cost of one call on popular LLMs (or the models you list), input plus an expected number of output tokens, and whether it fits each context window.