Loaded Tokens. The latest AI news in five minutes or less.Get the briefing
Directory / Tools

Tools with a job. And a catch.

What it does, who it fits, and the line on the bill the homepage forgot to mention.

UseThe public docs say it does what you need. We read the docs. We did not test it.
WatchPromising, but something is missing: access, pricing, or proof.
IgnoreNot for you, at least not yet.

73 profiles · all readable free

toolWatch

Amazon Bedrock

AWS · Agent infrastructure

AWS access to foundation models and supporting services such as knowledge bases and guardrails.

Usage depends on provider, model, modality and service tier. Knowledge bases and other services can add separate charges.

Read the profile →
toolUse

Amazon Q Developer

AWS · Coding agents

A development assistant available in IDE and CLI workflows.

Free tier with limits; Pro $19/user/month, with higher allowances and administrative features.

Read the profile →
toolUse

AssemblyAI

AssemblyAI · Voice & audio

Speech-to-text with a published hourly rate, plus text to speech.

$50 in free credits. Universal-3.5 Pro pre-recorded is $0.21 an hour. Streaming bills the open socket, not just the audio. Text to speech is $15 per million characters.

Read the profile →
toolWatch

Cartesia

Cartesia · Voice & audio

Speech models and voice agents sold as credits.

Free is 20,000 credits a month. A $49 plan includes 1.25 million credits. Voice-agent minutes are a separate prepaid balance.

Read the profile →
toolUse

ChatGPT

OpenAI · AI for work

A conversational assistant with file, research and writing features that depend on plan.

Free version; paid plans are priced per user/month. The public page did not expose stable numeric paid amounts in our text capture.

Read the profile →
toolUse

Claude

Anthropic · AI for work

A conversational assistant available on web, desktop and mobile with plan-dependent tools.

Free $0; Pro $20/month billed monthly, or $200 billed up front annually. Limits apply.

Read the profile →
toolWatch

Claude Code

Anthropic · Coding agents

An agentic coding tool for repository and terminal workflows, described in its official overview.

Included with eligible Claude plans, including Pro; plan limits apply. API-backed usage follows separate billing.

Read the profile →
toolUse

Cloudflare AI Gateway

Cloudflare · Agent infrastructure

Gateway controls including analytics, caching and rate limiting.

Core features free. New-gateway logs follow Workers Logs billing; Unified Billing credit purchases have a 5% fee. Provider inference costs remain.

Read the profile →
toolWatch

ComfyUI

Comfy Org · Open source & local AI

A node graph for local image and video models.

Free under GPL-3.0. Nodes and models you add can carry other licenses.

Read the profile →
toolWatch

Microsoft Copilot Studio

Microsoft · Agents

A platform for creating, deploying and managing custom agents connected to business workflows.

Prepaid or pay-as-you-go consumption; public page lists 25,000-credit packs at $200/pack/month. Credit use varies by action.

Read the profile →
toolUse

CrewAI

crewAI · Open source & local AI

A Python framework for role-shaped agents.

The library is MIT. Model calls are billed by the provider you choose.

Read the profile →
toolWatch

Cursor CLI

Cursor · Coding agents

A command-line agent with interactive and non-interactive workflows documented by Cursor.

Uses Cursor plan and model rules: Free plus paid tiers; eligible third-party model usage draws prepaid credit.

Read the profile →
toolWatch

Cursor editor

Cursor · Coding agents

An AI coding environment with agent workflows and model selection.

Free $0; Plus $8/month; Premium $30/month. Third-party models on eligible tiers use prepaid credit at API list price.

Read the profile →
toolUse

Deepgram

Deepgram · Voice & audio

Speech-to-text, text-to-speech, and voice agents.

$200 free credit, then pay as you go. Nova-3 monolingual pre-recorded is $0.0043 a minute. Aura-2 is $0.030 per 1,000 characters.

Read the profile →
toolWatch

DeepSeek weights

DeepSeek · Models

Open-weight DeepSeek models. The license lives on the model card.

Weights are posted per model. There is no single price that covers every DeepSeek checkpoint.

Read the profile →
toolWatch

Devin

Cognition · Coding agents

A coding agent with a desktop app and cloud sessions.

Free is $0 with a light quota. Pro is $20 a month. Max is $200. Teams is $80 a month plus $40 per full seat. Extra use is API pricing.

Read the profile →
toolWatch

ElevenLabs Scribe

ElevenLabs · Voice & audio

Speech-to-text tools for recorded and real-time transcription, with timestamps and speaker features.

Free and paid shared-credit plans. The speech-to-text page lists plan-specific minutes; Starter is $6/month before taxes after promotion.

Read the profile →
toolWatch

ElevenLabs Text to Speech

ElevenLabs · Voice & audio

Speech generation with plan-dependent voice features, credit usage and licensing.

Free $0/month with 10,000 shared credits; Starter $6/month after first-month promotions. Commercial license listed on Starter.

Read the profile →
toolUse

Exa

Exa · Search & research

A search API for agents, with contents and an answer endpoint.

Free credit is $10, resetting monthly. Lite search is $4 per 1,000 requests. Answer is $5 per 1,000. The first 10 results are in the base price.

Read the profile →
toolUse

Flowise

Flowise · Open source & local AI

A visual builder for LLM flows you host yourself.

Free under Apache 2.0. Any model you connect is billed separately.

Read the profile →
toolUse

FLUX.1 schnell

Black Forest Labs · Video

The Apache-licensed FLUX.1 schnell image model.

The schnell weights are free under Apache 2.0. Other FLUX checkpoints use other licenses.

Read the profile →
toolWatch

Gemini Developer API

Google · Models

A developer API with model-specific free and paid access.

Free and paid tiers vary by model. Some models have no free tier; thinking and tool-related tokens may be billable.

Read the profile →
toolUse

Gemini Omni

Google · Video

Google's native video model in the Gemini API.

Gemini Omni 1.2 Flash is generally available. Google's post prices 720p at $0.07 a second, 30 percent under Omni 1.1, for clips up to 15 seconds.

Read the profile →
toolUse

GitHub Copilot

GitHub · Coding agents

Coding assistance with completions, agent features and model access that vary by plan.

Free $0; Pro $10/user/month; Pro+ $39/user/month. Plan credits and model restrictions apply.

Read the profile →
toolWatch

GitHub Copilot CLI

GitHub · Coding agents

A terminal-based coding agent documented by GitHub.

Copilot CLI is listed in Copilot Free; paid plans expand allowances and model access. Credits vary by model.

Read the profile →
toolUse

Google AI Studio

Google · Build & deploy

Google’s browser-based starting point for exploring Gemini and developing API-backed workflows.

AI Studio access is listed in the Gemini API free tier; paid API usage and model eligibility are separate.

Read the profile →
toolWatch

GPT-Live

OpenAI · Voice & audio

OpenAI's live voice session, including outbound SIP.

gpt-live-1 is $0.05 a minute, billed per second. Backend model and tool use are charged separately. Realtime audio tokens are a different table, at $32 in and $64 out per million for gpt-realtime-2.1 audio.

Read the profile →
toolWatch

HeyGen

HeyGen · Video

Avatar video and translation.

Free is three watermarked videos a month. Creator is $29 a month. Pro starts at $49. Business is $149 plus $20 a seat.

Read the profile →
toolWatch

Hugging Face Inference Providers

Hugging Face · Agent infrastructure

Hosted access to inference providers with centralized pay-as-you-go billing.

Pay-as-you-go provider rates with no Hugging Face markup. PRO includes $2/month compute credits; free users must buy credits or upgrade.

Read the profile →
toolUse

Hugging Face Hub

Hugging Face · Models

A Hub for discovering and sharing models, datasets and Spaces.

Account upgrades include PRO $9/month and Team $20/user/month. Storage and compute charges are separate.

Read the profile →
toolWatch

Jan

Jan · Open source & local AI

A desktop app that runs local models and exposes a local API.

Free to download. The README states Apache 2.0. Confirm the LICENSE file you install.

Read the profile →
toolWatch

Kimi

Moonshot AI · Models

Moonshot's Kimi models, including open-weight checkpoints.

Weights are free to download where the model card allows it. Hosted Kimi is a separate account.

Read the profile →
toolUse

LangGraph

LangChain · Agents

An orchestration framework for stateful agent workflows, with explicit graph structure and execution control.

Self-managed runtime and model costs apply. Managed deployment and LangSmith features have separate pricing.

Read the profile →
toolUse

LangSmith

LangChain · Agent infrastructure

A platform for tracing, evaluation and agent-development workflows.

Developer $0/seat/month plus usage, up to 5,000 base traces/month. Plus $39/seat/month plus usage.

Read the profile →
toolWatch

Llama

Meta · Models

Meta's Llama open-weight models.

Weights are free under the Llama community license, which is not an OSI open-source license.

Read the profile →
toolUse

llama.cpp

llama.cpp · Open source & local AI

A local inference engine for GGUF-style model files.

The engine is free under the repository license. You supply the model.

Read the profile →
toolWatch

LM Studio

LM Studio · Open source & local AI

A desktop app for chatting with local models.

Free to download. The desktop app is not open source.

Read the profile →
toolWatch

Luma Dream Machine

Luma AI · Video

Hosted video and image generation.

Plus is $30 a month, or $25 billed yearly, with 10,000 credits. Pro is $90, or $75 yearly, with 40,000 credits.

Read the profile →
toolWatch

Make

Make · Agents

Hosted scenarios that connect apps, billed in credits.

Free includes 1,000 credits a month. Most actions cost one credit. Credits expire at the end of the term. AI steps can cost more.

Read the profile →
toolWatch

Microsoft 365 Copilot

Microsoft · AI for work

Workplace AI integrated with Microsoft 365 applications, with license-dependent capabilities.

Plan and license dependent; the public page combines annual commitments, promotions and advanced-AI consumption billing. Verify the eligible SKU.

Read the profile →
toolWatch

MiniMax weights

MiniMax · Models

MiniMax open-weight checkpoints.

Download terms are on the model card. A hosted MiniMax plan is a different product.

Read the profile →
toolUse

Mistral OCR

Mistral AI · Agent infrastructure

A document OCR API for extracting content from documents, documented in Mistral’s document AI guide.

OCR is billed per 1,000 pages rather than ordinary chat tokens; downstream model use is separate.

Read the profile →
toolWatch

Mistral open weights

Mistral · Models

Mistral models you can download, as distinct from the paid API.

Some Mistral checkpoints are Apache 2.0. The hosted API is a separate bill. Read the card.

Read the profile →
toolWatch

Mistral Studio

Mistral · Agents

Mistral's hosted place to run agents and workflows.

The announcement describes managed agents, workflows, and apps in the cloud, a VPC, or on premises. It does not list a starter price.

Read the profile →
toolWatch

Mistral Vibe

Mistral AI · Agents

An assistant experience with chat, search, creation and coding access described on the pricing page.

Free access with limits; Pro and Team subscriptions available. Limits, taxes and API-credit benefits vary by plan.

Read the profile →
toolWatch

n8n

n8n · Open source & local AI

A workflow tool with AI nodes. Source-available, not OSI open source.

Starter is 20 euros a month billed annually. Pro is 50 euros. The community edition is free for your own internal use.

Read the profile →
toolUse

Ollama

Ollama · Open source & local AI

A local runner for open-weight chat models.

Free to download. The app license is MIT. Each model you pull has its own license.

Read the profile →
toolWatch

Open WebUI

Open WebUI · Open source & local AI

A chat interface you host in front of Ollama or another model server.

Free to self-host. The license restricts branding changes above a stated user count.

Read the profile →
toolUse

OpenAI Responses API

OpenAI · Models

A model API surface with usage billed at the selected model and tool rates.

No separate Responses API fee; model tokens and tool usage are billed. Example: GPT-6.1 Terra standard short-context $1/M input and $5/M output tokens.

Read the profile →
toolWatch

Perplexity Agent API

Perplexity · Search & research

An API providing third-party model access with token-based billing and separately priced tools.

Model-specific token rates; tool calls such as web search add separate charges. See the public API rate card.

Read the profile →
toolUse

Perplexity Search API

Perplexity · Search & research

A web-search API with separate request-based billing listed in Perplexity’s rate card.

Search API: $5 per 1,000 successful requests; Fast Search: $1 per 1,000 successful requests. No token billing for Search API.

Read the profile →
toolWatch

Perplexity Teammates

Perplexity · Agents

Personal agents that run long projects, remember goals and files across runs, and report back.

Perplexity Max subscribers; web now, iOS soon

Read the profile →
toolWatch

Qwen

Alibaba Cloud · Models

Alibaba's Qwen open-weight family.

Many Qwen cards use Apache 2.0. Confirm the card. A hosted DashScope bill is separate.

Read the profile →
toolWatch

Replit Agent

Replit · Coding agents

A hosted agent that builds and deploys apps inside Replit.

Free mode is listed. Personal is $20 a month or $18 billed annually, with $20 toward models. Commercial is $100 or $90 billed annually.

Read the profile →
toolWatch

Runway

Runway · Video

A hosted studio for AI video and images.

Free includes 125 one-time credits. Standard is $12 a month billed yearly. Pro is $28. Max is $76. Models spend credits at different rates.

Read the profile →
toolWatch

Stable Diffusion

Stability AI · Video

The Stable Diffusion image models.

Weights are free to download under the license on the model card, which adds use restrictions.

Read the profile →
toolWatch

Synthesia

Synthesia · Video

Scripted avatar video.

Basic is free. Starter is $19 a month, or $14 a month billed yearly. Pro is sold in credit tiers.

Read the profile →
toolWatch

Tavily

Tavily · Search & research

Search API credits for agents.

Free Researcher plan: 1,000 API credits a month, no card. Paid use is pay as you go. Credit cost depends on the request type.

Read the profile →
toolWatch

v0

Vercel · Build & deploy

A generation and editing product with visual design, code and Vercel deployment workflows.

Free and paid plans; paid usage includes credit allowances and additional-credit purchases. Confirm the selected billing term.

Read the profile →
toolUse

Vercel AI SDK

Vercel · Build & deploy

A TypeScript toolkit with provider abstractions and UI building blocks for AI applications.

Model provider and hosting charges remain separate. The SDK overview does not quote a per-request SDK subscription.

Read the profile →
toolUse

vLLM

vLLM · Open source & local AI

An Apache-licensed server for open-weight models.

Free under Apache 2.0. You pay for the GPUs.

Read the profile →
toolUse

Whisper

OpenAI · Voice & audio

OpenAI's open speech-recognition models and code.

The repository is free to download. OpenAI's hosted transcription API is a separate, metered product.

Read the profile →
toolUse

Cloudflare Workers AI

Cloudflare · Agent infrastructure

Managed model inference integrated with the Workers platform.

10,000 neurons/day free allocation; paid usage above that is $0.011/1,000 neurons on Workers Paid. Model units vary.

Read the profile →
toolWatch

Zapier MCP

Zapier · Agents

An MCP connection layer for actions in applications connected to Zapier.

Included in every Zapier plan; each tool call uses two tasks from the shared task quota.

Read the profile →
toolUse

Zapier workflows

Zapier · Agents

Task-based automation combining app workflows, data tables and forms.

Free and paid task-based plans; allowance, task type and billing commitment affect the bill.

Read the profile →
toolUseevidence limited

Claude Code 2.1.319

Anthropic · Coding agents

Background MCP tasks and a permissions.denyInsteadOfPrompting setting for unattended runs.

Existing Claude Code plans

Read the profile →
toolWatch

Web Answer on Bedrock AgentCore

AWS · Agent infrastructure

One call returns a synthesized, cited web answer for your agent, over MCP.

Per-tool-call pricing; US East (N. Virginia) only

Read the profile →
toolUseevidence limited

Codex CLI 0.167

OpenAI · Coding agents

An agent command center (codex agents) that flags unread results across several agents.

Free CLI; model usage billed by plan

Read the profile →
toolWatch

Cursor Live Apps

Cursor · Build & deploy

A cloud agent builds the app, sets up a database and auth, and publishes it to a shareable link.

Requires a cloud agent on a paid Cursor plan

Read the profile →
toolWatch

Tencent Hy4

Tencent · Models

Open-source-bound model with vision and computer use; weights promised "in the coming days."

About $0.90 / $2.70 per million tokens

Read the profile →
toolWatch

Gemini 4 Carbon

Google · Models

Google's strongest model for cybersecurity and long-horizon tasks.

$2 / $10 per million tokens introductory, when available

Read the profile →
toolIgnore

Genie 4

Google DeepMind · Models

Real-time interactive world simulation with native audio.

Research preview, waitlist

Read the profile →
toolUseevidence limited

GPT-6.1 Terra

OpenAI · Models

Fast, cheaper model for computer use, visual reasoning, writing and coding.

API prices 50% below GPT-5.6 Terra (reported $1 / $5 per million tokens)

Read the profile →
A twice-a-week note, if you want it.