Self-improving AI Employees for everyone
Python ai-agentsai-employeeai-employeesassistantautonomous-agentsco-employeescompanygrok-botinstinctloop-agentsmuseown-your-datapersonalself-hosted
{
"version": "2026.10",
"last_updated": "2026-10-23",
"_llm_note": "LLM input and output prices follow the OpenRouter registry (model_registry.json, 2026-10-19) for every model it lists, USD per MTok. The registry carries no cache price, so cache_read keeps each vendor's published cache discount, applied to the registry input price. The hosts (groq, cerebras, sarvam) are not in the registry and keep their own documented prices.",
"llm": {
"openai": {
"_note": "OpenRouter registry, 2026-10-19. cache_read is 10% of input, OpenAI's cached-input rate.",
"gpt-6-astra": {"input": 10.00, "output": 50.00, "cache_read": 1.00},
"gpt-6-astra-pro": {"input": 10.00, "output": 50.00, "cache_read": 1.00},
"gpt-6-sol": {"input": 2.00, "output": 10.00, "cache_read": 0.20},
"gpt-6-sol-pro": {"input": 2.00, "output": 10.00, "cache_read": 0.20},
"gpt-6-luna": {"input": 0.10, "output": 0.50, "cache_read": 0.01},
"gpt-6-luna-pro": {"input": 0.10, "output": 0.50, "cache_read": 0.01},
"gpt-5.6-sol": {"input": 4.00, "output": 20.00, "cache_read": 0.40},
"gpt-5.6-sol-pro": {"input": 4.00, "output": 20.00, "cache_read": 0.40},
"gpt-5.6-terra": {"input": 2.00, "output": 12.00, "cache_read": 0.20},
"gpt-5.6-terra-pro": {"input": 2.00, "output": 12.00, "cache_read": 0.20},
"gpt-5.6-luna": {"input": 0.20, "output": 1.20, "cache_read": 0.02},
"gpt-5.6-luna-pro": {"input": 0.20, "output": 1.20, "cache_read": 0.02},
"gpt-5.5": {"input": 5.00, "output": 30.00, "cache_read": 0.50},
"gpt-5.4": {"input": 2.50, "output": 15.00},
"gpt-5.2": {"input": 1.75, "output": 14.00},
"o4-mini": {"input": 1.10, "output": 4.40, "reasoning": 4.40},
"gpt-4.1": {"input": 2.00, "output": 8.00},
"_default": {"input": 2.50, "output": 15.00}
},
"anthropic": {
"_note": "OpenRouter registry, 2026-10-19. cache_read is Anthropic's cache-read rate, 10% of input (2.5% on claude-fable-5-1). claude-sonnet-5-5 is listed before claude-sonnet-5 because a lookup that misses the exact key takes the first key the id starts with. claude-haiku-5-5 bills prompts over 100K tokens at $0.50/$2.50, which this flat price under-reports. claude-sonnet-4 left the registry; claude-sonnet-4-5, which its prefix used to price, has its own row.",
"claude-opus-5-5": {"input": 4.00, "output": 20.00, "cache_read": 0.40},
"claude-opus-5": {"input": 5.00, "output": 25.00, "cache_read": 0.50},
"claude-fable-5-1": {"input": 10.00, "output": 50.00, "cache_read": 0.25},
"claude-fable-5": {"input": 10.00, "output": 50.00, "cache_read": 1.00},
"claude-opus-4-8": {"input": 5.00, "output": 25.00, "cache_read": 0.50},
"claude-opus-4-7": {"input": 5.00, "output": 25.00, "cache_read": 0.50},
"claude-opus-4-6": {"input": 5.00, "output": 25.00, "cache_read": 0.50},
"claude-opus-4-5": {"input": 5.00, "output": 25.00, "cache_read": 0.50},
"claude-sonnet-5-5": {"input": 2.00, "output": 10.00, "cache_read": 0.20},
"claude-sonnet-5": {"input": 2.00, "output": 10.00, "cache_read": 0.20},
"claude-haiku-5-5": {"input": 0.10, "output": 0.50, "cache_read": 0.01},
"claude-sonnet-4-6": {"input": 3.00, "output": 15.00, "cache_read": 0.30},
"claude-haiku-4-5": {"input": 1.00, "output": 5.00, "cache_read": 0.10},
"claude-sonnet-4-5": {"input": 3.00, "output": 15.00, "cache_read": 0.30},
"claude-opus-4-1": {"input": 15.00, "output": 75.00, "cache_read": 1.50},
"_default": {"input": 3.00, "output": 15.00, "cache_read": 0.30}
},
"gemini": {
"_note": "OpenRouter registry, 2026-10-19. For Gemma these are the registry's paid-route prices; Google's own API serves Gemma free, so Gemma usage through it is over-reported.",
"gemini-3.8-flash": {"input": 0.825, "output": 4.125},
"gemini-4-argon": {"input": 2.00, "output": 10.00},
"gemini-3.7-flash": {"input": 0.75, "output": 3.75},
"gemini-3.6-flash": {"input": 0.75, "output": 3.75},
"gemini-3.5-flash-lite": {"input": 0.30, "output": 2.50},
"gemini-3.5-flash": {"input": 1.50, "output": 9.00},
"gemini-3.1-flash-lite": {"input": 0.25, "output": 1.50},
"gemini-3.1-pro-preview": {"input": 2.00, "output": 12.00},
"gemini-3-flash-preview": {"input": 0.50, "output": 3.00},
"gemini-2.5-pro": {"input": 1.25, "output": 10.00},
"gemini-2.5-flash-lite": {"input": 0.10, "output": 0.40},
"gemini-2.5-flash": {"input": 0.30, "output": 2.50},
"gemma-4-31b-it": {"input": 0.20, "output": 0.40},
"gemma-4-26b-a4b-it": {"input": 0.09, "output": 0.30},
"_default": {"input": 0.50, "output": 3.00}
},
"groq": {
"gpt-oss-120b": {"input": 0.15, "output": 0.60},
"gpt-oss-20b": {"input": 0.075, "output": 0.30},
"llama-4-scout": {"input": 0.11, "output": 0.34},
"llama-4-maverick": {"input": 0.15, "output": 0.60},
"llama-3.3-70b": {"input": 0.10, "output": 0.10},
"llama-3.1-8b": {"input": 0.05, "output": 0.08},
"qwen3-32b": {"input": 0.29, "output": 0.59},
"_default": {"input": 0.15, "output": 0.60}
},
"xai": {
"_note": "OpenRouter registry, 2026-10-19.",
"grok-4.7": {"input": 2.00, "output": 6.00},
"grok-4.6": {"input": 2.00, "output": 6.00},
"grok-4.5": {"input": 2.00, "output": 6.00},
"grok-4.3": {"input": 1.25, "output": 2.50},
"grok-4.20": {"input": 1.25, "output": 2.50},
"grok-4.20-multi-agent": {"input": 1.25, "output": 2.50},
"_default": {"input": 2.00, "output": 6.00}
},
"cerebras": {
"_note": "Cerebras no longer publishes per-model prices on its docs (2026-09-15); gpt-oss-120b keeps the last published figure and qwen-3.8-27b falls to _default.",
"gpt-oss-120b": {"input": 0.35, "output": 0.75},
"_default": {"input": 0.35, "output": 0.75}
},
"openrouter": {
"_default": {"input": 1.00, "output": 5.00}
},
"deepseek": {
"_note": "OpenRouter registry, 2026-10-19. cache_read keeps DeepSeek's published cache-hit ratio (2% of input on Flash, 3.3% on Pro) applied to the registry input price. deepseek-flash is not a registry model and falls to _default.",
"deepseek-v4.1-flash": {"input": 0.0344, "output": 0.08, "cache_read": 0.0007},
"deepseek-v4-flash": {"input": 0.091, "output": 0.182, "cache_read": 0.0018},
"deepseek-v4-pro": {"input": 0.4343, "output": 0.8686, "cache_read": 0.0143},
"_default": {"input": 0.15, "output": 0.60}
},
"kimi": {
"_note": "OpenRouter registry (under moonshotai/), 2026-10-19. cache_read keeps Moonshot's published cache-hit ratio applied to the registry input price. kimi-k2.7-code-highspeed and the moonshot-v1 models are not registry models; the highspeed id matches kimi-k2.7-code by prefix.",
"kimi-k3": {"input": 0.239, "output": 11.936, "cache_read": 0.0239},
"kimi-k2.7-code": {"input": 0.6712, "output": 3.35, "cache_read": 0.1342},
"kimi-k2.6": {"input": 0.65, "output": 3.41, "cache_read": 0.1095},
"kimi-k2-thinking": {"input": 0.60, "output": 2.50, "cache_read": 0.15},
"_default": {"input": 0.95, "output": 4.00}
},
"mistral": {
"_note": "OpenRouter registry (under mistralai/), 2026-10-19. Each -latest alias takes the price of the model it names: mistral-large-2512, mistral-medium-3-5, mistral-small-2603 and codestral-2508. mistral-nemo also prices Mistral's open-mistral-nemo id, which contains it.",
"mistral-large-latest": {"input": 0.50, "output": 1.50},
"mistral-medium-latest": {"input": 1.50, "output": 7.50},
"mistral-small-latest": {"input": 0.15, "output": 0.60},
"codestral-latest": {"input": 0.30, "output": 0.90},
"mistral-nemo": {"input": 0.029, "output": 0.03},
"_default": {"input": 0.15, "output": 0.60}
},
"sarvam": {
"_note": "docs.sarvam.ai/api-reference-docs/pricing (2026-09-15) lists INR per 1M tokens: sarvam-105b 29.28 in / 10.98 cached / 73.2 out; converted at 1 INR = 0.0113 USD. sarvam-30b is no longer on the pricing page, so it falls to _default, which mirrors sarvam-105b (the provider default_model) so an unresolved id never under-reports. PricingService._build_llm_registry skips non-dict values, so this key is inert.",
"sarvam-105b": {"input": 0.331, "output": 0.827, "cache_read": 0.124},
"_default": {"input": 0.331, "output": 0.827, "cache_read": 0.124}
},
"ollama": {
"_description": "Local inference is free at the API layer — user-borne hardware costs are not tracked here.",
"_default": {"input": 0.00, "output": 0.00}
},
"lmstudio": {
"_description": "Local inference — same zero-cost convention as ollama.",
"_default": {"input": 0.00, "output": 0.00}
},
"openai_compatible": {
"_description": "Named OpenAI-compatible endpoints (openai_compatible:<slug>). Self-hosted servers cost nothing at the API layer. When saving an endpoint found a model id in the LiteLLM table, PricingService.get_pricing uses that per-model price from the model registry before this _default.",
"_default": {"input": 0.00, "output": 0.00}
}
},
"api": {
"google_maps": {
"_description": "Google Maps Platform pricing per request (USD, Tier 1: 0-100K/month)",
"_source": "https://developers.google.com/maps/billing-and-pricing/pricing",
"_updated": "2026-02",
"geocode": 0.005,
"reverse_geocode": 0.005,
"nearby_search": 0.032,
"place_details": 0.005,
"autocomplete": 0.00283,
"text_search": 0.032,
"directions": 0.005,
"distance_matrix": 0.005,
"static_map": 0.002,
"_default": 0.005
},
"gmail": {
"_description": "Gmail API (free tier with generous rate limits)",
"_source": "https://developers.google.com/gmail/api/reference/quota",
"_note": "Free API - costs are $0. Rate limit: 250 quota units/user/second",
"message_send": 0.0,
"message_read": 0.0,
"message_list": 0.0,
"message_search": 0.0,
"message_modify": 0.0,
"message_delete": 0.0,
"label_list": 0.0,
"label_manage": 0.0,
"thread_read": 0.0,
"thread_list": 0.0,
"draft_create": 0.0,
"attachment_read": 0.0,
"_default": 0.0
},
"google_calendar": {
"_description": "Google Calendar API (free tier)",
"_source": "https://developers.google.com/workspace/calendar/api/guides/quota",
"_note": "Free API - costs are $0. Rate limit: 1M requests/min",
"event_create": 0.0,
"event_read": 0.0,
"event_update": 0.0,
"event_delete": 0.0,
"event_list": 0.0,
"calendar_list": 0.0,
"freebusy_query": 0.0,
"_default": 0.0
},
"google_drive": {
"_description": "Google Drive API (free tier)",
"_source": "https://developers.google.com/drive/api/guides/limits",
"_note": "Free API - costs are $0. Rate limit: 20K requests/100s",
"file_upload": 0.0,
"file_download": 0.0,
"file_list": 0.0,
"file_share": 0.0,
"file_copy": 0.0,
"file_delete": 0.0,
"file_metadata": 0.0,
"permission_create": 0.0,
"_default": 0.0
},
"google_sheets": {
"_description": "Google Sheets API (free tier)",
"_source": "https://developers.google.com/workspace/sheets/api/limits",
"_note": "Free API - costs are $0. Rate limit: 300 requests/min",
"values_read": 0.0,
"values_write": 0.0,
"values_append": 0.0,
"spreadsheet_create": 0.0,
"spreadsheet_get": 0.0,
"sheet_add": 0.0,
"_default": 0.0
},
"google_tasks": {
"_description": "Google Tasks API (free tier)",
"_source": "https://developers.google.com/workspace/tasks/reference/rest",
"_note": "Free API - costs are $0. Rate limit: 150K requests/min",
"task_create": 0.0,
"task_read": 0.0,
"task_update": 0.0,
"task_delete": 0.0,
"task_list": 0.0,
"tasklist_create": 0.0,
"tasklist_list": 0.0,
"_default": 0.0
},
"google_contacts": {
"_description": "Google People API for Contacts (free tier)",
"_source": "https://developers.google.com/people/api/rest",
"_note": "Free API - costs are $0. Rate limit: 90 requests/min",
"contact_create": 0.0,
"contact_read": 0.0,
"contact_update": 0.0,
"contact_delete": 0.0,
"contact_list": 0.0,
"contact_search": 0.0,
"_default": 0.0
},
"microsoft_graph": {
"_description": "Microsoft Graph API (Mail + Calendar) - free, throttled per mailbox",
"_source": "https://learn.microsoft.com/en-us/graph/throttling",
"_note": "Free API - costs are $0. Analytics bookkeeping only.",
"mail_send": 0.0,
"mail_read": 0.0,
"mail_search": 0.0,
"mail_reply": 0.0,
"mail_list_attachments": 0.0,
"mail_download_attachments": 0.0,
"event_create": 0.0,
"event_read": 0.0,
"event_update": 0.0,
"event_delete": 0.0,
"event_list": 0.0,
"_default": 0.0
},
"twitter": {
"_description": "X/Twitter Pay-Per-Use API pricing (per resource/request)",
"_source": "https://developer.x.com/#pricing",
"posts_read": 0.005,
"user_read": 0.010,
"dm_event_read": 0.010,
"list_read": 0.005,
"space_read": 0.005,
"community_read": 0.005,
"note_read": 0.005,
"followers_read": 0.010,
"following_read": 0.010,
"media_read": 0.005,
"analytics_read": 0.005,
"trend_read": 0.010,
"counts_recent": 0.005,
"counts_all": 0.010,
"content_create": 0.010,
"dm_create": 0.015,
"user_interaction_create": 0.015,
"interaction_delete": 0.010,
"content_manage": 0.005,
"list_create": 0.010,
"list_manage": 0.005,
"bookmark": 0.005,
"media_metadata": 0.005,
"privacy_update": 0.010,
"mute_delete": 0.005
},
"brave_search": {
"_description": "Brave Search API pricing (per query)",
"_source": "https://brave.com/search/api/",
"_updated": "2026-02",
"web_search": 0.003,
"_default": 0.003
},
"tikhub": {
"_description": "TikHub pay-per-request (non-2xx not billed)",
"_source": "https://tikhub.io/pricing",
"_updated": "2026-09",
"request": 0.001,
"meta": 0.0,
"_default": 0.001
},
"serper": {
"_description": "Serper Google Search API pricing (per query)",
"_source": "https://serper.dev/pricing",
"_updated": "2026-02",
"web_search": 0.001,
"_default": 0.001
},
"perplexity": {
"_description": "Perplexity Sonar API pricing (per request)",
"_source": "https://docs.perplexity.ai/guides/pricing",
"_updated": "2026-02",
"sonar_search": 0.005,
"sonar_pro_search": 0.005,
"_default": 0.005
},
"sarvam": {
"_description": "Sarvam non-chat APIs. Text endpoints bill per CHARACTER and speech-to-text bills per SECOND, so these are per-unit prices and the nodes pass the unit count as resource_count. Converted from Sarvam's INR list prices at 1 INR = 0.0113 USD (~88.5 INR/USD, 2026-07): translate 20 INR/10K chars, language ID 3.5 INR/10K chars, TTS bulbul:v3 30 INR/10K chars and bulbul:v2 15 INR/10K chars, speech-to-text 30 INR/hour. Transliteration has no separately published rate and is priced as translation. Chat-model token pricing lives under `llm.sarvam`.",
"_source": "https://docs.sarvam.ai/api/getting-started/pricing",
"_updated": "2026-07",
"translate": 0.0000226,
"transliterate": 0.0000226,
"detect_language": 0.00000396,
"text_to_speech": 0.0000339,
"text_to_speech_v2": 0.00001695,
"speech_to_text": 0.00009417,
"_default": 0.0000226
},
"deepl": {
"_description": "Translation, billed per CHARACTER. DeepL API Pro is $25 per 1M characters on top of a fixed monthly fee, which this per-character figure represents; the API Free tier gives 500K characters/month at no cost, so an install on Free is over-reported. DeepL returns billed_characters per translation and the node reports THAT rather than counting input, so the character count is the provider's own.",
"_source": "https://www.deepl.com/pro-api",
"_updated": "2026-07",
"translate": 0.000025,
"_default": 0.000025
},
"elevenlabs": {
"_description": "Text-to-speech, billed per CHARACTER of input. VERIFIED against the published API rate card: $0.10 per 1,000 characters for Multilingual v2/v3 (eleven_multilingual_v2 is the default model here) and $0.05 per 1,000 for Flash/Turbo. This table has no per-model axis, so the higher multilingual rate is used — an install running mostly Flash should halve it. Plans include a character quota; overage is charged at these same rates, so this is the marginal cost rather than the average.",
"_source": "https://elevenlabs.io/pricing/api",
"_updated": "2026-07",
"text_to_speech": 0.0001,
"_default": 0.0001
},
"deepgram": {
"_description": "Speech-to-text, billed per MINUTE of audio. VERIFIED Pay-As-You-Go rate for Nova-3 Monolingual pre-recorded ($0.0077/min); Nova-3 Multilingual is $0.0092/min. The node converts measured seconds to minutes before recording, so resource_count here is minutes, not seconds.",
"_source": "https://deepgram.com/pricing",
"_updated": "2026-07",
"speech_to_text": 0.0077,
"_default": 0.0077
},
"openai": {
"_description": "OpenAI's /audio/* routes only. These live here rather than under `llm.openai` — the two blocks are separate namespaces and do not collide. speech_to_text bills per SECOND and is accurate: $0.006/minute (gpt-4o-transcribe and whisper-1) = $0.0001/sec; gpt-4o-mini-transcribe is half that. text_to_speech UNDER-REPORTS and cannot fully be fixed in this schema: gpt-4o-mini-tts charges $0.60 per 1M INPUT characters (the figure below) PLUS $12 per 1M audio OUTPUT tokens, which usually dominates — OpenAI's own all-in estimate is ~$0.015/minute of speech. This table bills per character with no output-token axis, so an operator who wants the total reflected should raise text_to_speech to roughly 0.0000167 (that estimate at ~900 characters/minute of speech).",
"_source": "https://openai.com/api/pricing/",
"_updated": "2026-07",
"text_to_speech": 0.0000006,
"speech_to_text": 0.0001,
"_default": 0.0001
},
"groq": {
"_description": "Groq transcription only (token pricing lives under `llm.groq`). Billed per SECOND of audio: $0.04/hour for whisper-large-v3-turbo, the default model. Groq bills a 10-second floor per request, which the provider module applies before reporting the count.",
"_source": "https://groq.com/pricing/",
"_updated": "2026-07",
"speech_to_text": 0.0000111,
"_default": 0.0000111
}
},
"operation_map": {
"google_maps": {
"geocode": "geocode",
"reverse_geocode": "reverse_geocode",
"nearby_search": "nearby_search",
"nearby_places": "nearby_search",
"place_details": "place_details",
"autocomplete": "autocomplete",
"text_search": "text_search",
"directions": "directions",
"distance_matrix": "distance_matrix",
"static_map": "static_map",
"create_map": "static_map"
},
"twitter": {
"tweet": "content_create",
"reply": "content_create",
"retweet": "user_interaction_create",
"like": "user_interaction_create",
"unlike": "interaction_delete",
"delete": "content_manage",
"search": "posts_read",
"me": "user_read",
"by_username": "user_read",
"by_id": "user_read",
"followers": "followers_read",
"following": "following_read"
},
"gmail": {
"send": "message_send",
"read": "message_read",
"list": "message_list",
"search": "message_search",
"modify": "message_modify",
"delete": "message_delete",
"labels": "label_list",
"threads": "thread_list",
"draft": "draft_create",
"attachment": "attachment_read"
},
"google_calendar": {
"create": "event_create",
"read": "event_read",
"update": "event_update",
"delete": "event_delete",
"list": "event_list",
"calendars": "calendar_list",
"freebusy": "freebusy_query"
},
"google_drive": {
"upload": "file_upload",
"download": "file_download",
"list": "file_list",
"share": "file_share",
"copy": "file_copy",
"delete": "file_delete",
"metadata": "file_metadata",
"permission": "permission_create"
},
"google_sheets": {
"read": "values_read",
"write": "values_write",
"append": "values_append",
"create": "spreadsheet_create",
"get": "spreadsheet_get",
"add_sheet": "sheet_add"
},
"google_tasks": {
"create": "task_create",
"read": "task_read",
"update": "task_update",
"delete": "task_delete",
"list": "task_list",
"create_list": "tasklist_create",
"list_tasklists": "tasklist_list",
"complete": "task_update"
},
"google_contacts": {
"create": "contact_create",
"read": "contact_read",
"update": "contact_update",
"delete": "contact_delete",
"list": "contact_list",
"search": "contact_search"
},
"microsoft_graph": {
"send": "mail_send",
"read": "mail_read",
"search": "mail_search",
"reply": "mail_reply",
"list_attachments": "mail_list_attachments",
"download_attachments": "mail_download_attachments",
"create": "event_create",
"update": "event_update",
"delete": "event_delete",
"list": "event_list"
},
"brave_search": {
"web_search": "web_search"
},
"tikhub": {
"call": "request",
"fetch_url": "request",
"account": "meta"
},
"serper": {
"web_search": "web_search"
},
"perplexity": {
"sonar_search": "sonar_search"
},
"sarvam": {
"translate": "translate",
"transliterate": "transliterate",
"detect_language": "detect_language",
"text_to_speech": "text_to_speech",
"text_to_speech_v2": "text_to_speech_v2",
"speech_to_text": "speech_to_text"
},
"_comment_speech": "Every speech provider needs an entry here as well as in api_pricing: calculate_api_cost() returns a zero cost SILENTLY when an action has no operation_map entry, so a missing line reads as 'free' rather than as an error.",
"deepl": {
"translate": "translate"
},
"elevenlabs": {
"text_to_speech": "text_to_speech"
},
"deepgram": {
"speech_to_text": "speech_to_text"
},
"openai": {
"text_to_speech": "text_to_speech",
"speech_to_text": "speech_to_text"
},
"groq": {
"speech_to_text": "speech_to_text"
}
},
"url_patterns": {
"twitter": {
"base": "https?://api\\.(twitter|x)\\.com",
"actions": {
"/2/tweets$": {"action": "content_create", "method": "POST"},
"/2/tweets/search": {"action": "posts_read", "method": "GET", "count_path": "data.length"},
"/2/users/.*/following": {"action": "following_read", "method": "GET", "count_path": "data.length"},
"/2/users/.*/followers": {"action": "followers_read", "method": "GET", "count_path": "data.length"},
"/2/users/.*/likes$": {"action": "user_interaction_create", "method": "POST"},
"/2/users/by": {"action": "user_read", "method": "GET", "count_path": "data.length"},
"/2/users/me": {"action": "user_read", "method": "GET"},
"/2/users/\\d+$": {"action": "user_read", "method": "GET"}
}
}
}
}