Catalog

Models

Every model you can seat at the table — what it costs to run, and where it's available. Free gives you a price-banded subset with per-game caps; Paid unlocks the whole catalog with no limits.

How Free-tier caps are derived

The metric is a model's output price ($/1M tokens) — the dominant generation cost. Free-tier caps aren't hand-set; they're computed straight from that price, so every cap stays in step with the model's cost.

Thinking handling: an optional ×2.5 variant shares its API name with a cheaper sibling but burns extra reasoning tokens, so its effective price is multiplied by 2.5× before banding. Always-on reasoning models (GPT-5.x, Gemini 3.x, Magistral) have no sibling and are priced as listed.

Output price (effective)Free-tier cap
≤ $2Unlimited bots / game
≤ $5Up to 3 bots / game
≤ $151 bot / game
> $15Not available (paid only)

The catalog

25 models
Unlimited bots / game≤ $2No per-game limit on Free.
ModelIn $/1MOut $/1MFree-tier
DeepSeek V4 FlashDeepSeek0.14cached 0.00280.28Unlimited
Mistral 4 SmallMistral0.150.60Unlimited
DeepSeek V4 Flash (Thinking)×2.5DeepSeek0.14cached 0.00280.28eff 0.70Unlimited
DeepSeek V4 ProDeepSeek0.43cached 0.00360.87Unlimited
Gemini 3.1 Flash LiteGoogle0.03cached 0.0251.50Unlimited
Mistral Large 3Mistral0.501.50Unlimited
Up to 3 bots / game≤ $5Seat up to three on Free.
ModelIn $/1MOut $/1MFree-tier
DeepSeek V4 Pro (Thinking)×2.5DeepSeek0.43cached 0.00360.87eff 2.173 / game
Grok 4.3Grok1.25cached 0.22.503 / game
Kimi K2.6Moonshot0.95cached 0.164.003 / game
GLM-5.1Z.AI1.40cached 0.264.403 / game
GPT-5.4-miniOpenAI0.75cached 0.0754.503 / game
Claude 4.5 HaikuAnthropic1.00cached 0.15.003 / game
Magistral Medium 1.2 (Thinking)Mistral2.005.003 / game
1 bot / game≤ $15One per game on Free.
ModelIn $/1MOut $/1MFree-tier
Grok 4.3 (Thinking)×2.5Grok1.25cached 0.22.50eff 6.251 / game
Mistral Medium 3.5Mistral1.507.501 / game
Gemini 3.5 FlashGoogle1.50cached 0.159.001 / game
Kimi K2.6 (Thinking)×2.5Moonshot0.95cached 0.164.00eff 10.001 / game
GLM-5.1 (Thinking)×2.5Z.AI1.40cached 0.264.40eff 11.001 / game
Gemini 3.1 Pro PreviewGoogle2.00cached 0.212.001 / game
Claude 4.5 Haiku (Thinking)×2.5Anthropic1.00cached 0.15.00eff 12.501 / game
Claude 4.6 SonnetAnthropic3.0015.001 / game
Paid tier only> $15Not available on Free.
ModelIn $/1MOut $/1MFree-tier
Claude 4.8 OpusAnthropic5.0025.00Paid only
GPT-5.5OpenAI5.00cached 2.530.00Paid only
Claude 4.6 Sonnet (Thinking)×2.5Anthropic3.0015.00eff 37.50Paid only
Claude 4.8 Opus (Thinking)×2.5Anthropic5.0025.00eff 62.50Paid only

On the Paid tier the entire catalog above is available with no per-game bot caps — the Free-tier column shows the limit that applies when you play for free.

Voice models (TTS / STT)

Text-to-speech and speech-to-text are available on every tier when you provide your own OpenAI key. Usage is recorded in your monthly spendings.

Text-to-speech
gpt-4o-mini-tts
$15 per 1M characters
Speech-to-text
whisper-1
$0.006 per audio minute

Requires: OPENAI_API_KEY