Skip to content
youbot

◆ Changelog

Updates

New models, improvements and fixes — newest first.

  1. API

    Use you.bot from Claude, Cursor and VS Code (MCP)

    Connect https://you.bot/mcp to Claude, Claude Code, Cursor or VS Code and ask for images, videos, music and voice in plain words — paid from your credits. Sign in with one click or use an API key; setup is in the docs under Use with Claude & AI apps. Available on accounts that have topped up at least once.

  2. Improvement

    Top up with crypto

    Buy credit packs with USDT or USDC from the Billing page: choose your coin and wallet on the payment page and pay the price shown on the button. Crypto top-ups are final and can't be refunded.

  3. New model

    Gemini 4 Argon

    Google's flagship Gemini 4 model for hard reasoning, coding and long multi-step work, with a context window of over a million tokens — available through the chat API.

  4. New model

    Claude Haiku 5.5

    Anthropic's fastest, lowest-cost Claude for high-volume chat, coding and everyday tasks, available through the chat API.

  5. New model

    Claude Sonnet 5.5

    Anthropic's balanced Claude for everyday coding, writing and analysis, available through the chat API.

  6. New model

    Nano Banana 2.1

    Google's October update to Nano Banana 2 — text-to-image and image editing with up to six reference images, at 1K, 2K and 4K.

  7. New model

    Claude Opus 5.5 & GPT-6.1 Sol

    Anthropic's Claude Opus 5.5 for complex coding, research and agentic work, and OpenAI's GPT-6.1 Sol, the updated everyday GPT-6 — both available through the chat API.

  8. API

    Function calling

    Chat models whose API reference lists tools now take your function definitions and can answer with complete function calls, on streamed turns too. A model that doesn't support it refuses the request before anything is charged.

  9. New model

    GPT-6 Luna

    The lightest GPT-6 from OpenAI — fast, low-cost answers for high-volume work, available through the chat API.

  10. New model

    DeepSeek V4.1 Flash

    DeepSeek's fast V4.1 model — thinking on by default with a non-thinking mode, a 1M-token context and up to 384K tokens of output, available through the chat API.

  11. Improvement

    Streams open right away

    When a chat model hasn't started answering within about two seconds — typically while it searches the web — the stream now opens immediately and keeps the connection alive, so slow turns no longer look stuck or time out before the first word arrives.

  12. New model

    GPT-6 Sol

    The everyday GPT-6 from OpenAI — strong reasoning at a fraction of Astra's price, available through the chat API.

  13. Improvement

    Invoices for company purchases

    Add your company name, address and tax/VAT ID under Billing → Invoice details, then download an invoice for any payment. Receipts and invoices open as printable pages you can save as PDF.

  14. New model

    Grok 4.7

    xAI's frontier model for coding, agentic tasks and knowledge work, with a 500K-token context window, available through the chat API.

  15. New model

    Claude Fable 5.1

    Anthropic's model for demanding reasoning and long-horizon agentic work — long-running coding, multistep research and document work across a 1M-token context.

  16. New model

    GPT Image 2.5

    OpenAI's image model in two tiers — Flare for fast everyday images and Sunburst for edits where precision matters most — with text-to-image and image editing up to 4K.

  17. New model

    GPT-6 Astra

    OpenAI's frontier GPT-6 reasoning model with a 1M-token context window, available through the chat API.

  18. API

    Web search in chat

    Turn on web search for a request and supported chat models look up fresh information before answering. It's off unless you ask for it, so you're never billed for a search you didn't request — each model's page shows whether it can search.

  19. New model

    Gemini 3.8 Flash

    Google's newest Flash model — a 1M-token context window and up to 65,536 tokens of output, available through the chat API.

  20. New model

    Gemini Omni 1.1 Flash

    Google's multimodal video model — generate clips from a prompt or edit an existing video, from a low-cost 360p draft up to 4K.

  21. API

    Image input in chat

    Attach images to your messages on chat models that can read them. A model that can't see images refuses the request rather than answering about a picture it never received — and nothing is charged.

  22. New model

    Kimi K3

    Moonshot AI's model for coding and long agentic work, with a 1M-token context — now live through the chat API.

  23. New model

    Wan 3.0 Video & Wan 3.0 Video Prime

    Wan's newest video models — text-to-video, first/last-frame control and reference-guided video from images, clips and audio, up to 1080p with optional sound.

  24. New model

    Kling O3

    Kling 3.0 Omni — cinematic text-, image- and reference-to-video plus video transformation, with native sound, multi-shot prompting and up to 4K.

  25. New model

    Grok 4.6

    xAI's Grok 4.6 for reasoning and generation, available through the chat API.

  26. New model

    Grok Imagine Image 2.0

    xAI's fast, stylised image model — up to 12 images per request in seven aspect ratios.

  27. New model

    Gemini 3.7 Flash

    Google's Flash model with a 1M-token context window and up to 65,536 tokens of output, available through the chat API.

  28. New model

    Seedance 2.5

    ByteDance's video model — text-to-video, first/last-frame control and reference-guided video from images, clips and audio, up to 1080p with optional generated sound.

  29. New model

    MiniMax H3 (Hailuo-03)

    MiniMax's Hailuo-03 video model — text-, image- and reference-to-video at 768p or 2K.

  30. New model

    Claude Opus 5

    Anthropic's Claude Opus 5 for frontier reasoning and generation, available through the chat API.

  31. New model

    Gemini 3.1 Flash TTS & Gemini 2.5 Pro Preview TTS

    Google's text-to-speech models are now live — expressive voices with control over tone and emotion, and studio-quality audio.

  32. New model

    Gemini 3.6 Flash

    Google's speed-optimized Flash model for fast everyday answers, available through the chat API.

  33. New model

    PixVerse V6

    PixVerse's stylized, high-motion text-to-video model — up to 1080p, with optional sound and multi-clip output.

  34. New model

    Coming soon: Kimi K3, Gemini TTS & ElevenLabs V3

    Kimi K3 (Moonshot AI), Gemini 3.1 Flash TTS, Gemini 2.5 Pro Preview TTS and ElevenLabs V3 — preview them on the market now; API access lands as soon as they're live.

  35. Improvement

    Mobile & pricing improvements

    Smoother navigation on phones and tablets, and clearer per-configuration labels and pricing on the Pricing page.

  36. New model

    GPT-5.6 Terra, Luna & Sol

    OpenAI's GPT-5.6 in three price/performance tiers — Terra, Luna and Sol — for coding, reasoning and agentic work, available through the chat API.

  37. New model

    Seedance 2.0 Mini

    ByteDance's cost-efficient video model — text- & image-to-video with consistent characters and cinematic motion.

  38. New model

    Grok 4.5

    xAI's latest frontier model for coding, agentic tasks and knowledge work, available through the chat API.

  39. New model

    Grok 4.3

    xAI's flagship reasoning model with text + image input and both standard and deep-reasoning modes.

  40. New model

    Seedream 5.0 Pro

    ByteDance's multimodal image model for controlled generation, precise editing and multilingual visuals.

  41. New model

    Nano Banana 2 Lite

    Google's Gemini 3.1 Flash-Lite Image — fast 1K image generation and prompt-based editing.

  42. New model

    Claude Sonnet 5

    Anthropic's agentic, multimodal model with configurable effort levels, available through the chat API.

  43. New model

    Veo 3.1 & Veo 3.1 Fast

    Text & image to video with native audio is now available, plus a lower-latency Fast tier for rapid iteration.

  44. New model

    Suno V4.5 Plus

    Generate full songs with vocals from a text prompt, with an instrumental-only option.

  45. API

    Unified task API

    One submit-then-poll pattern across every model family, with normalized result URLs.

  46. New model

    Nano Banana Pro

    Fast, photoreal image generation and editing, with reference-image support.

  47. Improvement

    Automatic refunds

    Credits are now automatically refunded when an upstream job fails before producing a result.

  48. Fix

    More reliable polling

    Resolved an issue where some long-running video tasks reported status late.