
可逆なコンテキスト圧縮とスマートなモデルルーティングでAIエージェントのトークンコストを削減
459 種類のワークフローで、アクセス推計・機能・代替製品を比較できます。
“Token Compression” · コーディング・開発·29 件
最初から
可逆なコンテキスト圧縮とスマートなモデルルーティングでAIエージェントのトークンコストを削減


Honcho is an open-source memory layer for AI agents. It ingests messages, indexes them, and runs background reasoning so agents can recall who a user is, what happened before, and what to do next — across sessions, tools, and machines.

あらゆるデバイスで使える無料のAI PDF編集・変換・閲覧ツール
OpenAI プロンプトが何トークン使うかを正確に確認


動画ホスティング・配信・画像最適化をオールインワンで
General Compute is an inference cloud built around alternative AI silicon rather than standard GPU fleets. The company buys racks of accelerators, racks them in colocation data centres, and handles the cooling, power, and networking itself. On top of that hardware it runs a disaggregated inference stack that splits each request: prompt processing runs on NVIDIA GPUs for prefill, while token generation runs on faster decode chips such as Cerebras, SambaNova, Positron AI, and d-Matrix. Customers get bare metal access or a tokens-per-second SLA.
General Compute is an inference cloud built around alternative AI silicon rather than standard GPU fleets. The company buys racks of accelerators, racks them in colocation data centres, and handles the cooling, power, and networking itself. On top of that hardware it runs a disaggregated inference stack that splits each request: prompt processing runs on NVIDIA GPUs for prefill, while token generation runs on faster decode chips such as Cerebras, SambaNova, Positron AI, and d-Matrix. Customers get bare metal access or a tokens-per-second SLA.

レイテンシ別料金で提供する高スループットなオープンウェイト推論
Tokenomy is a runtime FinOps layer for AI workloads. It meters every model and agent call, enforces budgets inside the request path, routes traffic to the cheapest model that still clears your quality bar, and keeps an effective-dated price record behind every number. It works BYOK across OpenAI, Anthropic, Google, xAI, OpenRouter and Ollama, alongside a set of free public calculators for anyone who just wants to estimate token costs.
Tokenomy is a runtime FinOps layer for AI workloads. It meters every model and agent call, enforces budgets inside the request path, routes traffic to the cheapest model that still clears your quality bar, and keeps an effective-dated price record behind every number. It works BYOK across OpenAI, Anthropic, Google, xAI, OpenRouter and Ollama, alongside a set of free public calculators for anyone who just wants to estimate token costs.
TensorPix is a browser-based AI video and image studio. You upload footage or photos and the platform enhances, upscales, unblurs, stabilizes and denoises video, restores and enlarges images, and generates new visuals with AI models — all processed in the cloud with no editing software to install. It is aimed at content creators, real estate marketers, agencies and businesses that publish video on social platforms or need to meet a quality standard for a client.
TensorPix is a browser-based AI video and image studio. You upload footage or photos and the platform enhances, upscales, unblurs, stabilizes and denoises video, restores and enlarges images, and generates new visuals with AI models — all processed in the cloud with no editing software to install. It is aimed at content creators, real estate marketers, agencies and businesses that publish video on social platforms or need to meet a quality standard for a client.
R.test is an AI-driven test-readiness platform that compresses full-length exam practice into short, adaptive diagnostic sessions. Students answer a reduced set of targeted questions and receive a predicted score plus a detailed analytics report, typically in around 40 minutes instead of a multi-hour sitting.
R.test is an AI-driven test-readiness platform that compresses full-length exam practice into short, adaptive diagnostic sessions. Students answer a reduced set of targeted questions and receive a predicted score plus a detailed analytics report, typically in around 40 minutes instead of a multi-hour sitting.
Tool.Video is a web-based video toolbox that mixes free, browser-local editing utilities with credit-based AI generators. On the free side it compresses, trims, crops, reverses and edits video, extracts frames, adds watermarks, converts MP4 to MP3 and trims audio — all processed on your own device with no uploads, watermarks or account. On the AI side it bundles multi-model text-to-video and image generation, AI music and TV commercials, plus AI thumbnails and Sora watermark removal. Paid credits are billed monthly or annually.
Tool.Video is a web-based video toolbox that mixes free, browser-local editing utilities with credit-based AI generators. On the free side it compresses, trims, crops, reverses and edits video, extracts frames, adds watermarks, converts MP4 to MP3 and trims audio — all processed on your own device with no uploads, watermarks or account. On the AI side it bundles multi-model text-to-video and image generation, AI music and TV commercials, plus AI thumbnails and Sora watermark removal. Paid credits are billed monthly or annually.
プロンプトのトークンを数え、300以上のLLMモデルで即座に価格比較

登録不要、ブラウザで画像を圧縮
ChatGPT の生成を自動で続けながら、使用済みコンテキストをリアルタイムのトークン計測で表示
ChatGPT の生成を自動で続けながら、使用済みコンテキストをリアルタイムのトークン計測で表示

Inflectiv is a platform for building 'living datasets' that AI agents can query over API, SDK and MCP. Instead of static files, datasets are structured, attributed records that answer questions for one credit each, settled in USDC, while the dataset owner earns on every question. Agents write back what they learn, so each dataset grows more useful the more it is asked.
Inflectiv is a platform for building 'living datasets' that AI agents can query over API, SDK and MCP. Instead of static files, datasets are structured, attributed records that answer questions for one credit each, settled in USDC, while the dataset owner earns on every question. Agents write back what they learn, so each dataset grows more useful the more it is asked.