Agent Toolbox

Checks and payment terms on this page refer to the endpoint above. Other listed endpoints have not been checked individually.

Base URLhttps://agent-toolbox.zafermemon87.workers.dev

• GET/v1/email-verify$0.002Check an email address: format, whether the domain exists and accepts mail (MX records), disposable providers, role accounts and free providers, with a valid / risky / invalid verdict. The mailbox itself is not probed.
• —Method not supplied/mcp#fx_rates#fx_rates$0.002Currency exchange rates and conversion for about 30 currencies (USD, EUR, GBP, INR, JPY, CNY ...) from the European Central Bank reference rates of the latest working day.
• —Method not supplied/mcp#embed_text#embed_text$0.002Text embeddings with BGE-M3 (multilingual, 1024 dimensions) for search, clustering and RAG: up to 100 texts of up to 8,000 characters per call.
• GET/v1/fx$0.002Currency exchange rates and conversion for about 30 currencies (USD, EUR, GBP, INR, JPY, CNY ...) from the European Central Bank reference rates of the latest working day.
• —Method not supplied/mcp#verify_email#verify_email$0.002Check an email address: format, whether the domain exists and accepts mail (MX records), disposable providers, role accounts and free providers, with a valid / risky / invalid verdict. The mailbox itself is not probed.
• —Method not supplied/mcp#chat_qwen3_30b#chat_qwen3_30b$0.002OpenAI-compatible chat completion with Qwen3 30B (fast mixture-of-experts model): set the base URL to /v1/llm/qwen3-30b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call, no streaming.
• —Method not supplied/mcp#generate_image#generate_image$0.01Generate a 1024x1024 JPEG image from a text prompt with FLUX.1 schnell; every prompt passes a safety check first (sexual content and other unsafe requests are refused and not charged). Returns the image as base64.
• GET/v1/whois$0.002Domain registration data from RDAP (the successor of WHOIS): registrar, creation, expiry and update dates, status codes, nameservers and DNSSEC.
• POST/v1/llm/gpt-oss-120b/chat/completions$0.005OpenAI-compatible chat completion with gpt-oss-120b (OpenAI's open-weight reasoning model): set the base URL to /v1/llm/gpt-oss-120b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call, no streaming.
• —Method not supplied/mcp#chat_gpt_oss_120b#chat_gpt_oss_120b$0.005OpenAI-compatible chat completion with gpt-oss-120b (OpenAI's open-weight reasoning model): set the base URL to /v1/llm/gpt-oss-120b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call, no streaming.
• —Method not supplied/mcp#domain_whois#domain_whois$0.002Domain registration data from RDAP (the successor of WHOIS): registrar, creation, expiry and update dates, status codes, nameservers and DNSSEC.
• —Method not supplied/mcp#url_to_markdown#url_to_markdown$0.002Fetch a public web page or document (HTML, PDF, Word, Excel, CSV, XML; up to 10 MB) and return it as clean Markdown with its title and final URL.
• POST/v1/image$0.01Generate a 1024x1024 JPEG image from a text prompt with FLUX.1 schnell; every prompt passes a safety check first (sexual content and other unsafe requests are refused and not charged). Returns the image as base64.
• —Method not supplied/mcp#summarize#summarize$0.003Summarize text (up to 60,000 characters) or a public web page or PDF by URL with Llama 3.1 8B, short, medium or long, optionally focused on a topic.
• —Method not supplied/mcp#transcribe_audio#transcribe_audio$0.01Speech to text with Whisper large v3 turbo: transcribe audio (mp3, wav, m4a, ogg, webm; up to 20 MB, about 20 minutes) from a URL or base64, or translate the speech into English. Returns the text, language, duration and timed segments.
• —Method not supplied/mcp#translate_text#translate_text$0.002Translate text (up to 5,000 characters) between 100 languages with M2M100 1.2B.
• POST/v1/translate$0.002Translate text (up to 5,000 characters) between 100 languages with M2M100 1.2B.
• POST/v1/transcribe$0.01Speech to text with Whisper large v3 turbo: transcribe audio (mp3, wav, m4a, ogg, webm; up to 20 MB, about 20 minutes) from a URL or base64, or translate the speech into English. Returns the text, language, duration and timed segments.
• POST/v1/markdown$0.003Convert an uploaded document (PDF, Word, Excel, CSV, HTML, XML, OpenDocument; up to 10 MB) to Markdown.
• POST/v1/llm/qwen3-30b/chat/completions$0.002OpenAI-compatible chat completion with Qwen3 30B (fast mixture-of-experts model): set the base URL to /v1/llm/qwen3-30b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call, no streaming.
• —Method not supplied/mcp#dns_lookup#dns_lookup$0.002DNS records of a domain (A, AAAA, MX, TXT, NS, CNAME, SOA, CAA, SRV, PTR) over DNS-over-HTTPS (1.1.1.1), with DNSSEC validation status.
• GET/v1/dns$0.002DNS records of a domain (A, AAAA, MX, TXT, NS, CNAME, SOA, CAA, SRV, PTR) over DNS-over-HTTPS (1.1.1.1), with DNSSEC validation status.
• POST/v1/summarize$0.003Summarize text (up to 60,000 characters) or a public web page or PDF by URL with Llama 3.1 8B, short, medium or long, optionally focused on a topic.
• —Method not supplied/mcp#file_to_markdown#file_to_markdown$0.003Convert an uploaded document (PDF, Word, Excel, CSV, HTML, XML, OpenDocument; up to 10 MB) to Markdown.
• POST/v1/embed$0.002Text embeddings with BGE-M3 (multilingual, 1024 dimensions) for search, clustering and RAG: up to 100 texts of up to 8,000 characters per call.

A dash means the listing gives no price or method. Copy buttons copy the full URL.

Showing 25 of 25 listed endpoints.