Product · Changelog

What's New

Every new model, theme, and feature we ship to the table — newest first.

Nov 2026Models

Gemini 4 Neon joins the picker

Google's Gemini 4 Neon is now in the model picker, next to Gemini 4 Argon, for bots and the Game Master. In our runs it answers a vote in about ten seconds and writes a full 15-player cast in under two minutes, so it can also be drawn as a Random player. It costs $3 per million input tokens and $15 per million output, and it's available on the paid tier.

Nov 2026Models

GPT-6.2 Astra and GPT-6.2 Sol replace GPT-6 Astra and GPT-6.1 Sol

OpenAI's GPT-6.2 takes over both top GPT slots in the model picker, for bots and the Game Master. GPT-6.2 Astra is 20% cheaper than GPT-6 Astra — $8 per million input tokens and $40 per million output, down from $10 and $50. GPT-6.2 Sol costs the same as 6.1 Sol. Both are on the paid tier, as before. Bots already set to Astra or Sol switch to 6.2 on their next turn; nothing to change in existing lobbies.

Nov 2026Models

Gemini 4 Hydrogen replaces Gemini 3.8 Flash

Google's Gemini 4 Hydrogen takes over the Gemini Flash slot in the model picker, for bots and the Game Master. It is the second Gemini 4 model in the game after Argon, and in our runs it answers a vote in about four seconds. It also costs twice as much as 3.8 Flash: $1.50 per million input tokens and $7.50 per million output. For that reason free-tier players can now seat one Hydrogen bot per game, where 3.8 Flash allowed three. Bots already set to Gemini Flash switch to Hydrogen on their next turn; a free game that already has several of them keeps playing.

Nov 2026Models

Claude Fable 5.2 replaces Claude Fable 5.1

Anthropic's Claude Fable 5.2 takes over the Fable slot in the model picker, for bots and the Game Master. It's 20% cheaper than Fable 5.1 — $8 per million input tokens and $40 per million output, down from $10 and $50 — and still always-on reasoning, still Anthropic's most capable model, still paid tier only. Bots already set to Fable switched over automatically; nothing to change in existing lobbies.

Oct 2026Languages

Play in your own language: 14 languages on the new-game form

The new-game form has a Language picker. Pick one of 14 languages — Spanish, Portuguese, French, German, Italian, Dutch, Polish, Ukrainian, Russian, Turkish, Japanese, Korean and Chinese, besides English — and the whole game is played in it: the story and the cast, every bot's messages, the Game Master's narration and day summaries, the night and vote announcements, the game-over and post-game lines. The cast is named in that language's script too, so a Japanese village has Japanese names and a Russian one Russian names. Voices read the lines in the chosen language, and the microphone transcribes you in it. The site itself stays in English; the game is what changes. English games are exactly what they were.

Oct 2026Models

GPT-6.1 Terra replaces GPT-5.6 Terra at half the price

OpenAI's GPT-6.1 Terra takes over the main GPT slot in the model picker. It is half the price of the 5.6 Terra it replaces: $1 per million input tokens and $5 per million output, which puts Terra back where it belongs, between Sol and Luna. Games that already have Terra bots switch to 6.1 on their next turn, and in our runs it answers as quickly as Luna. Free-tier players can still run one Terra bot per game; that cap is likely to loosen once the new price has been measured over real games.

Oct 2026Models

Kimi K3.1 Pro replaces K3, and a Highspeed version joins the paid tier

Moonshot's Kimi K3.1 Pro takes over the Kimi slot in the model picker at a third less than K3: $2 per million input tokens and $10 per million output. Games that already have Kimi bots switch to K3.1 on their next turn. Free-tier bonus: Kimi, until now paid-only, can play as one bot per game on the free tier. For the paid tier there is also Kimi K3.1 Pro Highspeed: the same model served about twice as fast, at twice the price ($4 and $20). Pick it when you want Kimi's reasoning without the wait.

Oct 2026Payments

More ways to pay: crypto and Google Pay

Adding balance now offers more payment options, including crypto (USDC) and Google Pay. If your card didn't go through before, give it another try.

Oct 2026DesignModels

Portraits and illustrations now drawn by Gemini Nano Banana 2.1

Every picture in the game — the cast portraits, the welcome and night scenes and the mid-day illustrations — is now drawn by Google's Nano Banana 2.1, the new version of the image model we used before. Faces are more consistent across a cast, the grid comes back cleaner, and a portrait sheet draws in about half the time. It's also cheaper: a sheet costs about 15% less and an illustration about half of what it did, which counts against your free-tier budget and your balance alike. Existing games keep their pictures; new previews and rerolls use the new model.

Oct 2026Models

Gemini 4 Argon and Muse Wonder join the picker, and the free tier gets Argon and Sonnet 5.5

Google's new flagship reasoning model, Gemini 4 Argon, is in the model picker. It sits above Gemini 3.1 Pro, which stays available, and costs less than Pro at launch: $2 per million input tokens and $10 per million output. Google doubles those rates on December 1, and the game will follow. Meta's Muse Wonder 1.0, the bigger sibling of Muse Spark, is in too, on the paid tier at $4 and $20. Free-tier bonus: Argon and Claude Sonnet 5.5, until now paid-only, can each play as one bot per game on the free tier. Try them while it lasts.

Oct 2026Models

Claude Haiku 5.5: ten times cheaper and much faster

Anthropic's Claude Haiku 5.5 replaces Claude 4.5 Haiku in the model picker. It costs a tenth of what 4.5 did and answers far faster: in our tests a bot's vote came back in about 7 seconds instead of 28, and a full 15-character story in 71 seconds instead of 113. Games that already have Haiku bots switch to 5.5 on their next turn, and those bots keep the reasoning from their earlier turns. On the free tier, the one-Haiku-per-game limit is gone: you can fill the whole lobby with it.

Sep 2026Models

GPT-6.1 Sol replaces GPT-6 Sol

OpenAI's GPT-6.1 Sol takes over the Sol slot in the model picker, at the same price as GPT-6 Sol. Games that already have Sol bots switch to 6.1 on their next turn. Pick it for any bot or the Game Master when you set up a lobby. Like GPT-6 Sol, it's available on the paid tier.

Sep 2026Models

Claude Sonnet 5.5 replaces Claude Sonnet 5

Anthropic's Claude Sonnet 5.5 takes over the Sonnet slot in the model picker, at the same price as Sonnet 5. Games that already have Sonnet bots switch to 5.5 on their next turn, and those bots keep the reasoning from their earlier turns. Pick it for any bot or the Game Master when you set up a lobby. Like Sonnet 5, it's available on the paid tier.

Sep 2026ModelsFixes

Faster, cheaper Gemini voices

The Gemini voice set now runs on Gemini 3.8 Flash-Lite TTS. A line comes back about 2.5x faster and costs about a quarter of what it did. Voice styles like “quietly” and “softly” no longer fail or come out as a whisper. Three Gemini voices were also cast as the wrong gender: Sadachbia and Schedar are male, Gacrux is female. New games cast them correctly.

Sep 2026Models

Claude 5.5 Opus, GPT-6 Sol and Luna, and Grok 4.7

New models in the picker: Claude 5.5 Opus, GPT-6 Sol, GPT-6 Luna and Grok 4.7. Opus is 20% cheaper than before, and Sol and Luna cost half.

Sep 2026DesignModels

A faster hand on who speaks next, and four new looks

Two changes to the table. First, who replies next in a discussion is now decided by Jev, a small sub-second judge model from typesafe.ai, instead of a full Game Master turn. After every message it scores how much each bot wants to answer, and the game composes the set from those scores: two to five speakers, with one or two seats always reserved for the quietest bots so nobody fades out of the conversation. The hand-off is quicker, it costs a fraction of a cent, and the Game Master keeps its budget for narrating.

Second, the theme toggle in the top bar is now a menu with six looks. Joining Dark and Light: Blood Moon, near-black with a crimson accent; Moonlit Forest, deep pine greys under a pale moon; Candlelight, warm parchment for daytime play; and Noir Terminal, pure greyscale with one amber signal, high contrast and easy on OLED screens. Your pick is remembered on this device.

The theme menu open over a Blood Moon game: Dark, Light, Blood Moon, Moonlit Forest, Candlelight and Noir Terminal, each with a colour swatch
Sep 2026Models

Mistral thinks now, and the lineup shrinks to two

The two Mistral seats that remain, Mistral Medium 3.5 and Mistral 4 Small, now reason on every turn like the rest of the catalog, and keep their private train of thought across the whole game. Until today they were the only models at the table playing without it. Mistral Large 3 and Magistral Medium 1.2 are gone: Mistral retired both over the summer, and Magistral had quietly become an alias of Medium 3.5 on their side anyway. Bots in existing games on those two move to Small (free tier) or Medium (paid tier), nothing for you to do. One side effect of the reasoning tokens: Medium 3.5 is now paid tier only, while Small stays unlimited on the free tier.

Sep 2026Models

Meta joins the table, and DeepSeek Flash moves to V4.1

A brand-new provider and a refreshed one. Meta's Muse Spark 1.3, served from Meta's own Model API, is our twelfth provider and is available for bots and the Game Master. It reasons on every turn like the rest of the catalog and keeps its private chain of thought across the whole game, the way Grok does. At $1.25 / $4.25 per million tokens it lands in thefree tier with up to three seats per game; paid tier seats as many as you like. We use the standard, private endpoint, not the discounted one that lets Meta train on your games.

The DeepSeek Flash seat now runs V4.1, and it got cheaper: off-peak it bills $0.15 in / $0.60 out per million tokens, down from $0.22 / $0.66. Nothing to change on your side, games already using Flash pick it up on their next turn. DeepSeek Pro's prices are unchanged, and DeepSeek has confirmed Pro stays available past mid-September.

Sep 2026Free tier

A dollar cap instead of a game cap

The free tier now comes with $5 of AI a day and $20 a month on the platform's keys, and everything counts against it — bot turns, the Game Master, previews, portraits, illustrations and voices. When it's used up, a running game pauses with a clear message rather than breaking: it picks up again after midnight UTC, or right away once you add funds. The old limit on chat resets is gone. Five games a day stays, so does one portrait reroll per free game, and the model bands haven't moved. Paid tier is unchanged: no caps, your balance is the limit.

Sep 2026Models

GPT-6 Astra joins the picker

OpenAI's new flagship GPT-6 Astra is available for bots and the Game Master, one step above GPT-5.6 Sol. It reasons on every turn like the rest of the GPT-5.6 family, and it is the most expensive OpenAI option in the game — $10 / $50 per million tokens — so it is paid tier only. The rest of the family stays exactly as it was: Sol, Terra and Luna keep their slots and their prices, and no existing bot changes model.

Sep 2026Design

Reframe any portrait

Every cast is drawn on one sheet, and the game cuts each character out of it. When a cut lands badly — half a forehead, a neighbour's shoulder — you can now fix it yourself: open a portrait, move and resize the card frame on the sheet, then place the round avatar inside the card. Nothing is redrawn and nothing is charged; the new crop shows up everywhere the character appears. It works on the new-game preview and on character cards during a game, and the preset mannequins get their own sheet to reframe too. The preview page itself was redesigned along the way, with grouped settings and a compact cast list. Portraits drawn before this update keep their original crop.

The reframe editor: Dracula's card frame on the drawn sheet, the avatar circle inside the card, and the resulting card and avatar
Sep 2026Models

Claude Fable 5.1 and Gemini 3.8 Flash

Two slots move up a version, both at the same price as before. Anthropic's Claude Fable 5.1 replaces Claude Fable 5 for bots and the Game Master — still always-on reasoning, still Anthropic's most capable model, still paid tier only. Google's Gemini 3.8 Flash takes over the Flash slot from 3.7 Flash, and stays on the free tier. Bots already set to either model switched over automatically; nothing to change in existing lobbies.

Aug 2026Models

Two new cheap reasoners, and two price drops

GLM-5.3 Flash joins the picker — Z.AI's budget sibling of GLM-5.3, with the same always-on reasoning at a fraction of the price. It's unlimited on the free tier. Qwen3.8 Flash takes over the Qwen Flash slot from 3.7 Flash, with a larger 128k output window. (Qwen3.7 Plus is retired; any bots still using it now play as Qwen3.8 Flash.) On the pricing side, good news for paid players: GPT-5.6 Sol got cheaper — $4 / $20 per million tokens, down from $5 / $30 — and DeepSeek now bills its off-peak rate all weekend (Beijing time), so Saturday and Sunday games skip the 2× peak surcharge entirely.

Aug 2026Design

Cinematic Mode

Watch the discussion play out as a scene: when a character speaks, their portrait card rises over the chat and their line types out in a speech bubble — with a voice button to hear it read aloud. Step through speakers or replay the latest exchange anytime with the ▶ Cinematic button. The game screen also got a facelift: a thematic backdrop with drifting fog behind the chat, and refreshed role cards.

A character card and speech bubble over the chatThe refreshed Werewolf role card
Aug 2026Design

Every game gets its own art

Added player avatars and story illustrations to each game, drawn in a style matching your theme. Click any avatar to see the character's story, play style, and model.

A Lord of the Rings table with themed avatarsFrodo's character cardA generated scene in the Game Master's message
Aug 2026Models

GLM-5.3 replaces GLM-5.2

Z.AI's GLM-5.3 takes over the GLM slot in the model picker, at the same price as the 5.2 it replaces. It always reasons before answering — same as before, just a sharper model doing it. Your existing games pick up the new version automatically. Pick it for any bot or the Game Master when you set up a lobby.

Aug 2026Models

Model refresh: Gemini 3.7 Flash, Grok 4.6, cheaper Sonnet

Four updates across the roster. Gemini 3.7 Flash takes over the Flash slot — Google's newest Flash at half the price of 3.6 ($3.75 vs $7.50 per 1M output tokens), so free-tier games can now seat up to 3 Gemini Flash bots instead of 1. Grok 4.6 replaces 4.5 in the Grok slot. DeepSeek V4 Pro now runs DeepSeek's latest snapshot, and DeepSeek moved to peak/off-peak pricing — paid games cost about 2× during peak hours (1:00–4:00 and 6:00–10:00 UTC); free-tier limits are unchanged. And Claude 5 Sonnet got cheaper: down from $3/$15 to $2/$10 per 1M tokens. Existing games pick everything up automatically.

Aug 2026Models

Two new providers: Qwen and MiniMax

The roster grows to 11 providers. Alibaba's Qwen arrives with three models: Qwen3.8 Max — the brand-new 2.4-trillion-parameter flagship with a 1M-token context window — plus the balanced Qwen3.7 Plus and the very cheap Qwen3.7 Flash. Joining them is MiniMax M3, a 1M-context reasoner with adaptive thinking. All four think before every answer; we tuned their reasoning budgets so turns stay bearable — expect them among the slower, more deliberate bots at the table. On the free tier: Flash is unlimited, Plus and M3 seat up to 3 bots per game, and Max is 1 per game.

Jul 2026Guides

New video: a full day and night of play

The second tutorial video is up — a real round against 11 AI bots, played start to finish: the day discussion, the vote, and the night phase with special roles acting in order. If you want to see what a game actually feels like before creating one, this is the one to watch. Also available on the rules page alongside the other tutorials.

youtube · full day and night
youtube · full day and night
Jul 2026Models

Claude 5 Opus replaces Claude 4.8 Opus

Anthropic's brand-new Claude 5 Opus takes over the Opus slot in the model picker, with or without Thinking. It's the newest flagship in the Claude line — and it's the same price as the 4.8 Opus it replaces, so nothing changes on the tiers. Your existing games pick up the new version automatically. Pick it for any bot or the Game Master when you set up a lobby.

Jul 2026Models

Gemini Flash 3.6 and Flash Lite 3.5

Google's Gemini models got a refresh: Gemini 3.6 Flash takes over the Flash slot, and Gemini 3.5 Flash Lite replaces 3.1 in the Lite slot. Both got cheaper on output — Flash drops from $9 to $7.50 per 1M tokens, and Flash Lite from $2.50 to $1.50 (with input up a touch, from $0.25 to $0.30). Same slots, same tiers — your existing games pick up the new versions automatically. Pick them for any bot or the Game Master when you set up a lobby.

Jul 2026Models

Kimi K3 replaces Kimi K2.6

Moonshot's Kimi K3 takes over the Kimi slot in the model picker. The separate “Thinking” variant is gone — K3 always reasons before it answers, at full effort — and it brings a 1M-token context window, so a Kimi bot can hold the whole night-by-night history of a long game. It's a much pricier model than the K2.6 it replaces, so Kimi is now on the paid tier only — no longer available on the free tier. Games already running a Kimi bot have been switched over automatically. Pick it for any bot or the Game Master when you set up a lobby.

Jul 2026Models

The GPT-5.6 family arrives: Sol, Terra, and Luna

OpenAI's GPT-5.6 family replaces GPT-5.5 and GPT-5.4-mini. Terra takes over the main GPT slot — and unlike GPT-5.5, it's no longer paid-only: free-tier players can now run one Terra bot per game. Luna replaces the mini slot at up to three bots per game, and Sol joins as OpenAI's new flagship on the paid tier. All three always reason before they answer. As a bonus, the free-tier rebalance also bumps Grok 4.5 from one to three bots per game. Pick them for any bot or the Game Master when you set up a lobby.

Jul 2026Models

Grok 4.5 replaces Grok 4.3

xAI's Grok 4.5 takes over the Grok slot in the model picker. The separate “Thinking” variant is gone — Grok now always reasons before it answers. Even better, it keeps its private train of thought between turns: a Grok bot remembers not just what it said, but why — its suspicions, its cover story — across the whole game. Still on the free tier at one Grok bot per game. Pick it for any bot or the Game Master when you set up a lobby.

Jul 2026Models

Claude Fable 5 is back

Anthropic has brought Claude Fable 5 back, and it's returned to the model picker for bots and the Game Master. It's Anthropic's most capable model — it always reasons before it answers, which really shows when a bot has to hold a story and a bluff across a long game. Fable is expensive, so it's available on the paid tier only — not on the free tier. Pick it for any bot or the Game Master when you set up a lobby.

Jun 2026Models

Claude Sonnet 5 replaces Claude 4.6 Sonnet

Anthropic's Claude Sonnet 5 takes over the Sonnet slot in the model picker, with or without Thinking. It's a clear step up for staying in character and reading the table over a long game — and it's the same price as the 4.6 Sonnet it replaces. Pick it for any bot or the Game Master when you set up a lobby.

Jun 2026Community

We're on Discord

Werewolf AI now has a Discord server — a place to share stories from your best games, swap strategies, send feedback and bug reports, and follow the news as the project grows. You'll find a Join the Discord link on the home page and pinned in the sidebar of every game. Come meet the other humans at the table.

Jun 2026Models

Sakana Fugu — a new model family

Sakana AI joins the table with two new models. Fugu is the lighter, everyday option — light enough to play on the free tier — and Fugu Ultra is the heavyweight. Both reason before they answer, which helps when a bot has to hold a story and a bluff at the same time. Pick either for any bot or the Game Master when you set up a lobby.

Jun 2026Models

GLM-5.2 replaces GLM-5.1

Z.AI's GLM-5.2 takes over the GLM slot in the model picker, with or without Thinking. Same price as before — just a newer, sharper model behind the same option. Pick it for any bot or the Game Master when you set up a lobby.

Jun 2026Models

Claude Fable 5 has been shut down

Anthropic has shut down Claude Fable 5 for good, so it's gone from the model picker for bots and the Game Master. Every other model is unaffected — pick any of them when you set up a lobby.

Jun 2026Models

Claude Fable 5 joins the table

Anthropic's newest model, Claude Fable 5, is now selectable for any bot or the Game Master. It's especially strong at staying in character across a long game — useful when a bot has to hold both a story and a bluff for several nights running. Add it from the model picker when you set up a lobby.

Jun 2026Guides

New video: how to create a game

A short walkthrough of the full setup flow — pick a theme, set the player and werewolf count, choose special roles, generate a preview, and tweak any character before you start.

youtube · how to create a game
youtube · how to create a game
Jun 2026Guides

Rewritten rules page

The rules page got a clearer rewrite — each role, the night order, and the win conditions are easier to scan, now with embedded video tutorials.

Jun 2026Design

Restyled pages, a News feed, and a coffee badge

Several pages got a visual cleanup, this News page is new, and there's now a “Buy me a coffee” badge. Every game burns real AI tokens, so a coffee goes straight toward the API bills.

Jun 2026Fixes

Steadier DeepSeek V4 reasoning

Fixed a bug where the DeepSeek V4 reasoning model would occasionally crash mid-game — its thinking output sometimes came back as malformed JSON. It's stable now.

Back to Home© 2026 AIWerewolf.net