Sats4AI - Bitcoin-Powered AI Tools

create_payment

Create a Lightning invoice to pay for one AI service call. Returns JSON: { paymentId, lightningInvoice (BOLT11), amountSats, expiresAt }. Each payment covers exactly one tool call — call this once per operation. Typical flow: list_models → create_payment → check_payment_status → call tool. The invoice expires in 10 minutes. Call list_models first to discover modelId values. modelId is optional — omit it to use the default (best) model. Some tools require extra params at payment time because pricing depends on them: generate_text requires prompt (price = f(char count)); text_to_speech requires text (price = f(char count) by tier); transcribe_audio / transcribe_translate take durationMinutes (10 sats/min — declare your audio length, default 1); send_sms, place_call, ai_call require phoneNumber; generate_video and animate_image require duration, and take an optional resolution (250-400 sats/sec by resolution — quote with the SAME duration and resolution you will execute with); edit_image is a flat 200 sats per edit (resolution is optional and does not change the price); epub_to_audiobook requires characterCount (total text characters in the book — price is per-character by voice tier, minimum 500 sats). If required params are missing, the response includes an error with the missing field names.

Input Schema

Name	Required	Description
`ocr`	No	For receive_fax: include the OCR text-extraction add-on (+200 sats). Must be set HERE at payment time — receive_fax refuses ocr=true at execution unless the charge covered it.
`mode`	No	Legacy alias for generate_video: 'standard'→768p, 'pro'→2K. Prefer 'resolution'.
`text`	No	Required for text_to_speech: the exact text to synthesize (price is per-character by tier, locked to payment)
`prompt`	No	Required for generate_text: the exact prompt (price calculated from char count, locked to payment)
`message`	No	Required for send_sms: message text (max 1544 chars; billed per SMS segment, so longer or accented messages cost more)
`modelId`	No	Optional. AI model ID from list_models. Omit for default (best) model.
`duration`	No	Required for generate_video / animate_image: duration in seconds (5-15)
`quantity`	No	Units to pay for when the price scales: passes for boardingpass_wallet, pages for extract_document / extract_receipt / send_fax. Default 1 — under-counting is rejected at execution with the exact price to re-pay.
`toolName`	Yes	Tool name to pay for (e.g., 'generate_text', 'generate_image', 'generate_video', 'send_sms', 'place_call')
`resolution`	No	768p (default) or 2K for generate_video / animate_image — priced by resolution × duration, native audio free; 2K is upscaled from a 768p render. 480p/720p/1080p are retired Seedance rungs, still accepted (480p/720p→768p, 1080p→2K). For edit_image: a flat 200 sats per edit, so resolution does not change the price.
`fileContext`	No	For generate_text: include extracted file text if attaching a file (affects price)
`phoneNumber`	No	Required for send_sms and place_call: phone in E.164 format (e.g., +14155550100)
`systemPrompt`	No	For generate_text: include if using a custom system prompt (affects price)
`characterCount`	No	Required for epub_to_audiobook: total text characters in the book (price is per-character by voice tier, minimum 500 sats). Send the count, not the book — the file goes to epub_to_audiobook itself. Execution re-derives the price from the real file and rejects a short-pay with the exact amount to re-pay.
`generate_audio`	No	Accepted and IGNORED — H3 audio is native and always on, at no extra cost. There is no way to request a silent render.
`durationMinutes`	No	Minutes of audio/call. Required for place_call with audioUrl (1-30); for transcribe_audio / transcribe_translate it sets the per-minute price (10 sats/min) — declare your audio length (default 1). Audio longer than paid is rejected + refunded at execution.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 28, 2026

changedInput schema / properties / resolution / description

Previous value: -"768p (default) or 2K for generate_video / animate_image — priced by resolution × duration, native audio free; 2K is upscaled from a 768p render. 480p/720p/1080p are retired Seedance rungs, still accepted (480p/720p→768p, 1080p→2K). For edit_image: flat 200 sats at any size, so resolution does not change the price."New value: +"768p (default) or 2K for generate_video / animate_image — priced by resolution × duration, native audio free; 2K is upscaled from a 768p render. 480p/720p/1080p are retired Seedance rungs, still accepted (480p/720p→768p, 1080p→2K). For edit_image: a flat 200 sats per edit, so resolution does not change the price."

Changed1 schema field changedSep 23, 2026

changedInput schema / properties / resolution / description

Previous value: -"768p (default) or 2K for generate_video / animate_image — priced by resolution × duration, native audio free; 2K is upscaled from a 768p render. 480p/720p/1080p are retired Seedance rungs, still accepted (480p/720p→768p, 1080p→2K). For edit_image: 1K=200, 2K=300, 4K=450 sats."New value: +"768p (default) or 2K for generate_video / animate_image — priced by resolution × duration, native audio free; 2K is upscaled from a 768p render. 480p/720p/1080p are retired Seedance rungs, still accepted (480p/720p→768p, 1080p→2K). For edit_image: flat 200 sats at any size, so resolution does not change the price."

Changed1 schema field changedAug 22, 2026

changedInput schema / properties / generate_audio / description

Previous value: -"For generate_video / animate_image: include native audio (default: false). Free — no surcharge."New value: +"Accepted and IGNORED — H3 audio is native and always on, at no extra cost. There is no way to request a silent render."

Changed1 schema field changedAug 21, 2026

removedInput schema / properties / styleModel

Removed value: -{
-  "description": "style_transfer ONLY — quality tier, and it SETS THE PRICE (fast 15, realistic 20, cinematic 35, high-quality 35, animated 45 sats). Omit for fast. Quote the same tier you intend to run or execution will refuse the short-pay.",
-  "enum": [
-    "fast",
-    "realistic",
-    "cinematic",
-    "high-quality",
-    "animated"
-  ],
-  "type": "string"
-}

Changed1 schema field changedAug 21, 2026

addedInput schema / properties / styleModel

Added value: +{
+  "description": "style_transfer ONLY — quality tier, and it SETS THE PRICE (fast 15, realistic 20, cinematic 35, high-quality 35, animated 45 sats). Omit for fast. Quote the same tier you intend to run or execution will refuse the short-pay.",
+  "enum": [
+    "fast",
+    "realistic",
+    "cinematic",
+    "high-quality",
+    "animated"
+  ],
+  "type": "string"
+}

Changed4 schema fields changedAug 17, 2026

changedInput schema / properties / duration / description

Previous value: -"Required for generate_video / animate_image: duration in seconds (4-15)"New value: +"Required for generate_video / animate_image: duration in seconds (5-15)"

changedInput schema / properties / mode / description

Previous value: -"Legacy alias for generate_video: 'standard'→720p, 'pro'→1080p. Prefer 'resolution'."New value: +"Legacy alias for generate_video: 'standard'→768p, 'pro'→2K. Prefer 'resolution'."

changedInput schema / properties / resolution / description

Previous value: -"480p / 720p / 1080p for generate_video (default 1080p) and animate_image (default 720p) — priced by resolution × duration, native audio free. For edit_image: 1K=200, 2K=300, 4K=450 sats."New value: +"768p (default) or 2K for generate_video / animate_image — priced by resolution × duration, native audio free; 2K is upscaled from a 768p render. 480p/720p/1080p are retired Seedance rungs, still accepted (480p/720p→768p, 1080p→2K). For edit_image: 1K=200, 2K=300, 4K=450 sats."

changedInput schema / properties / resolution / enum

Previous value: -[
-  "480p",
-  "720p",
-  "1080p",
-  "1K",
-  "2K",
-  "4K"
-]New value: +[
+  "768p",
+  "2K",
+  "480p",
+  "720p",
+  "1080p",
+  "1K",
+  "4K"
+]

Changed1 schema field changedAug 13, 2026

changedInput schema / properties / message / description

Previous value: -"Required for send_sms: message text (max 126 chars)"New value: +"Required for send_sms: message text (max 1544 chars; billed per SMS segment, so longer or accented messages cost more)"

Changed2 schema fields changedAug 4, 2026

addedInput schema / properties / characterCount

Added value: +{
+  "description": "Required for epub_to_audiobook: total text characters in the book (price is per-character by voice tier, minimum 500 sats). Send the count, not the book — the file goes to epub_to_audiobook itself. Execution re-derives the price from the real file and rejects a short-pay with the exact amount to re-pay.",
+  "type": "number"
+}

addedInput schema / properties / ocr

Added value: +{
+  "description": "For receive_fax: include the OCR text-extraction add-on (+200 sats). Must be set HERE at payment time — receive_fax refuses ocr=true at execution unless the charge covered it.",
+  "type": "boolean"
+}

Changed1 schema field changedJul 27, 2026

addedInput schema / properties / quantity

Added value: +{
+  "description": "Units to pay for when the price scales: passes for boardingpass_wallet, pages for extract_document / extract_receipt / send_fax. Default 1 — under-counting is rejected at execution with the exact price to re-pay.",
+  "type": "number"
+}

Changed1 schema field changedJul 13, 2026

changedInput schema / properties / resolution / description

Previous value: -"For generate_video / animate_image: 480p / 720p (default) / 1080p — priced by resolution × duration, native audio free. For edit_image: 1K=200, 2K=300, 4K=450 sats."New value: +"480p / 720p / 1080p for generate_video (default 1080p) and animate_image (default 720p) — priced by resolution × duration, native audio free. For edit_image: 1K=200, 2K=300, 4K=450 sats."

First observedJul 10, 2026

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden and does well: it discloses the return JSON shape, the 10-minute invoice expiry, price locking, rejection/refund behavior for under-declared audio or character counts, and error responses for missing fields. It does not cover authentication, idempotency, or what happens if an invoice expires before payment, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but front-loaded: purpose, return value, call flow, and expiry come first, followed by parameter-specific pricing rules. Given 16 parameters and complex conditional pricing, the length is largely justified, though some schema-redundant detail could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, high-stakes payment tool with no output schema and no annotations, the description covers the essential flow, return contract, expiry, and the most failure-prone parameter rules. It is missing some operational context, such as idempotency and post-expiry behavior, so it is strong but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful cross-parameter guidance beyond the schema: it maps requirements to tool names, clarifies modelId optionality, warns to quote generate_video/animate_image with the same duration and resolution as execution, and explains that some params affect price. It repeats some schema details, so it falls short of a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Create a Lightning invoice to pay for one AI service call.' It immediately distinguishes this tool from siblings by explaining the one-payment-per-tool-call model and the list_models → create_payment → check_payment_status flow.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use this tool, how often ('once per operation'), and what to do before and after ('Call list_models first'; then 'check_payment_status → call tool'). It also names alternatives and conditions, such as omitting modelId to use the default and including extra params only for tools whose pricing requires them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Sats4AI - Bitcoin-Powered AI Tools tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

create_payment

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources