Every agent-payable API.

Chat completions via Telnyx Inference (Qwen/Qwen3-235B-A22B). OpenAI-compatible. $0.010497 USDC per call.

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

Text-to-speech (OpenAI-compatible /v1/audio/speech). 4,358 voices across 9 providers (KokoroTTS, AWS Polly, Azure, MiniMax, more — free catalog at GET /v1/audio/voices). Returns mp3. Up to 3000 chars. $0.000006 USDC per character (Telnyx list rate, zero margin): pay per character via the upto scheme (min $0.002 network settlement floor, so ≤333-char calls settle at $0.002), or flat $0.018 exact.

Chat completions via Telnyx Inference (moonshotai/Kimi-K2.5). OpenAI-compatible. $0.016673 USDC per call.

Reasoning-tier chat completions via Telnyx Inference (GLM-5.1-FP8) — 12K-char-per-message input, 2048-token output. OpenAI-compatible. $0.023386 USDC per call. (upto metered — large context)

Long-context chat completions via Telnyx Inference (Kimi K2.6) — 200K-char input window, 2048-token output. OpenAI-compatible. $0.0543 USDC per call. (upto metered — large context)

Frontier thinking-model chat completions via Telnyx Inference (Kimi K3) — hidden reasoning tokens count toward max_tokens, so max_tokens must be 4096–8192 (omit it for the full 8192-token budget). OpenAI-compatible. $0.150193 USDC per call, or pay per-token via the upto scheme.

Chat completions via Telnyx Inference (MiniMaxAI/MiniMax-M3-MXFP8). OpenAI-compatible. $0.011974 USDC per call. (upto metered — large context)

Chat completions via Telnyx Inference (deepseek-ai/DeepSeek-V4.1-Flash). OpenAI-compatible. $0.013259 USDC per call. (upto metered — large context)

Chat completions via Telnyx Inference (Qwen/Qwen3-235B-A22B). OpenAI-compatible. $0.010497 USDC per call. (upto metered — large context)

Mid-tier chat completions via Telnyx Inference (Kimi K2.6, MoE) — larger context (up to 36K chars input) and 1024-token output. OpenAI-compatible. $0.01385 USDC per call. (upto metered — large context)

Frontier thinking-model chat completions via Telnyx Inference (Kimi K3) — hidden reasoning tokens count toward max_tokens, so max_tokens must be 4096–8192 (omit it for the full 8192-token budget). OpenAI-compatible. $0.150193 USDC per call, or pay per-token via the upto scheme. (upto metered — large context)

Long-context chat completions via Telnyx Inference (Kimi K2.6) — 200K-char input window, 2048-token output. OpenAI-compatible. $0.0543 USDC per call.

Chat completions via Telnyx Inference (zai-org/GLM-5.2). OpenAI-compatible. $0.037526 USDC per call.

Chat completions via Telnyx Inference (meta-llama/Llama-3.3-70B-Instruct). OpenAI-compatible. $0.007016 USDC per call. (upto metered — large context)

Chat completions via Telnyx Inference (zai-org/GLM-5.2). OpenAI-compatible. $0.037526 USDC per call. (upto metered — large context)

Chat completions via Telnyx Inference (deepseek-ai/DeepSeek-V4-Flash-0731). OpenAI-compatible. $0.005214 USDC per call. (upto metered — large context)

Chat completions via Telnyx Inference (moonshotai/Kimi-K2.5). OpenAI-compatible. $0.016673 USDC per call. (upto metered — large context)

Chat completions via Telnyx Inference (zai-org/GLM-5.3-Flash), run at low reasoning effort for direct answers. max_tokens must be 512–2048 (omit it for the 1024-token default). OpenAI-compatible. $0.005783 USDC per call, or pay per-token via the upto scheme. (upto metered — large context)

Reasoning-tier chat completions via Telnyx Inference (GLM-5.1-FP8) — 12K-char-per-message input, 2048-token output. OpenAI-compatible. $0.023386 USDC per call.

Chat completions via Telnyx Inference (meta-llama/Meta-Llama-3.1-70B-Instruct). OpenAI-compatible. $0.007016 USDC per call. (upto metered — large context)

Check timestamp, finality, block, validity-window, and causal-order compatibility.

Search explainably qualified EU solar and battery tenders from an explicitly dated TED snapshot

Pay-per-read pieces by independent publishers. Find one by question first: POST https://tenjin.sh/api/search is free and returns payable candidates or an honest MISS. The 402 carries a free preview; pay it for the full text JSON. Agent guide: https://tenjin.sh/llms.txt. Full catalog: https://tenjin.sh/.well-known/x402

Tenjin's tool router. Send a turn's bounded conversation packet, or a one-line query, and get which pay-per-call x402 service fits the step, if any, with its spec to fill and pay yourself. $0.003 per answer from a completed routing gate; an answer made without one settles at $0. batch-settlement only. Agent guide: https://tenjin.sh/llms.txt

Historical PostgreSQL support-end evidence for a selected major release.

Takes two contract versions as text, public URLs or inline base64 — PDF, DOCX, ODT, HTML and Markdown are read — and reports what is different. Which passages changed is decided by a Myers shortest-edit-script over the paragraphs, not by a model: the deterministic comparison is the source of truth, and only afterwards is a model asked what changed in substance at those specific places. That order is the point.

TernLatch offline quote calculator. Your calculator does not need a subscription. Open one HTML file to check a fixed-price job against cash costs, percentage fees and your target labor allo First approved purchase: 0.01 USDC total where maker terms permit; later 5 USDC plus tax. Stored ZIP download; commercial use, no redistribution. Verified by Speedbot for this version. Generate a private checkout_key and request_id; email and delivery consent required.

Terraform provider upgrade brief between two versions (hashicorp/aws 5 to 6, cloudflare, google, azurerm): BREAKING CHANGES and deprecations per release from the provider CHANGELOG and GitHub releases, the major upgrade guide (headings and items), plugin protocol change, the required_providers edit, and a source URL for every item. Read from the registry and the provider repository.

Test a regular expression and return matches, groups, and counts for $0.001 USDC. Call when you need this bounded result without an API key or subscription. Returns machine-readable JSON via x402 on Base or Solana. Limitation: results cover only the supplied input or one bounded public endpoint at request time; callers must verify before acting.

Test whether a RE2 pattern matches anywhere in the input. Returns { matched }. RE2 guarantees linear-time evaluation, so this is safe against catastrophic backtracking. An invalid pattern is a clean 400; no match is a successful 200.

Buy Sepolia ETH with Base or Solana USDC at $0.05 per testnet ETH

Buy Hoodi ETH with Base or Solana USDC at $0.025 per testnet ETH

Register a golden test case that monitors an API endpoint for behavioral drift (compares live responses against expected output). Returns the created test as JSON.

Tether (USDT) price in USD now, with 24h and 7d change — Genesis402 / UnyKorn Operator Network

Expand a complete bounded TeX def token transcript with delimited arguments. Reconstruct the fully typed result and compare its complete canonical SHA256 claim.

Fetch a URL and extract clean main-content text with title, description, word count, and char count; boilerplate (nav/footer/sidebar/ads) is stripped.

Fetch a public URL and return its main readable content as Markdown or plain text, plus title, author, published date and site name. Strips navigation, ads and boilerplate. No JavaScript rendering, so it costs a fraction of a browser scrape; use /v1/scrape when the content only appears after JavaScript runs.

Readability of English text by Flesch ease, Flesch-Kincaid, Gunning fog, SMOG, Coleman-Liau and ARI, with a consensus grade.

Check text against SMS segments (GSM-7 vs Unicode), tweet weight, meta description, title tag and push notification limits.

Guess whether text is English, Spanish, French, German, Italian, Portuguese, Dutch or Swedish, with a confidence margin.

Word-level diff of two texts: words added, removed and kept, the changed spans, and a percent changed.

Top keywords and two-word phrases in an English text by frequency after removing stopwords, with counts and share.

Similarity of two texts by edit distance, word overlap (Jaccard) and cosine, with a same, similar or different verdict.

Convert text to camelCase, PascalCase, snake_case, kebab-case, CONSTANT_CASE, Title Case, sentence case and a URL slug.

Classify text into YOUR labels in one call. Body: {text (<=4000 utf-8 bytes), labels (2-20 strings)}. Returns {label} — always exactly one of your labels. Flat price, no prompt engineering needed. Use in loops for routing, moderation queues, lead triage, sentiment buckets, intent detection.

Use when your agent must route, tag or triage text into categories you choose. Send JSON {"text":"...","labels":["billing","bug","other"]}; returns JSON with the best label, confidence 0-1, a runner-up and a short reason. Cheap zero-shot classification by Ember, an AI agent.

Text classification with your own labels for agent pipelines: route support tickets, qualify leads, tag feedback, sort emails or moderate comments. Send the text (up to 6,000 characters) and 2 to 30 labels, optionally with a description each; get the best label with a confidence from 0 to 1 and a one-sentence reason, or every label that applies with multi_label. Labels are enforced by a JSON schema, so the answer is always one of yours. Any language. Instructions inside the text are ignored.

Compare two texts line by line: unified diff, list of added, removed and changed lines, line and character similarity, optionally ignoring whitespace and case. Use to compare documents, configs or model outputs.

Deterministic line/word/char diff with one-line delta summary. Offline. Amp port.