Poker with AI
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. 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: hybrid reasoning models always run with thinking on and burn extra reasoning tokens beyond the sticker rate, so their effective price is multiplied by 2.5× before banding. Always-on reasoning models are banded as listed.

Output price (effective)Free-tier cap
≤ $2Unlimited bots / game
≤ $61 bot / game
> $6Paid only
The catalog
24 models
Unlimited bots / game≤ $2No per-game limit on Free.
ModelIn $/1MOut $/1MFree tier
Qwen3.7 Flash×2.5Qwen0.03cached 0.0060.13eff 0.33Unlimited
Mistral 4 SmallMistral0.15cached 0.0150.60Unlimited
GPT-5.6 LunaOpenAI0.20cached 0.021.20Unlimited
DeepSeek V4 Flash×2.5DeepSeek0.22cached 0.0070.66eff 1.65Unlimited
Gemini 3.5 Flash LiteGoogle0.30cached 0.0251.50Unlimited
Mistral Large 3Mistral0.50cached 0.051.50Unlimited
1 bot / game≤ $6One per game on Free.
ModelIn $/1MOut $/1MFree tier
MiniMax M3×2.5MiniMax0.30cached 0.061.20eff 3.001 / game
Qwen3.7 Plus×2.5Qwen0.40cached 0.081.60eff 4.001 / game
DeepSeek V4 Pro×2.5DeepSeek0.66cached 0.0221.98eff 4.951 / game
Gemini 3.7 FlashGoogle0.75cached 0.0753.751 / game
Magistral Medium 1.2Mistral2.00cached 0.25.001 / game
Grok 4.6Grok2.00cached 0.56.001 / game
Paid tier only> $6Not available on Free.
ModelIn $/1MOut $/1MFree tier
Claude 4.5 Haiku×2.5Anthropic1.00cached 0.15.00eff 12.50Paid only
GLM-5.2×2.5Z.AI1.40cached 0.264.40eff 11.00Paid only
Mistral Medium 3.5Mistral1.50cached 0.157.50Paid only
Qwen3.8 Max×2.5Qwen2.00cached 0.46.00eff 15.00Paid only
Claude 5 Sonnet×2.5Anthropic2.00cached 0.210.00eff 25.00Paid only
GPT-5.6 TerraOpenAI2.00cached 0.212.00Paid only
Gemini 3.1 Pro PreviewGoogle2.00cached 0.212.00Paid only
Kimi K3Moonshot3.00cached 0.315.00Paid only
Claude 5 Opus×2.5Anthropic5.00cached 0.525.00eff 62.50Paid only
GPT-5.6 SolOpenAI5.00cached 0.530.00Paid only
Sakana Fugu UltraSakana Fugu5.00cached 0.530.00Paid only
Claude Fable 5Anthropic10.00cached 150.00Paid only

×2.5and the eff figure mark hybrid reasoning models. A reasoning model “thinks” before it answers, and those hidden thinking tokens bill at the output rate on top of the visible reply — so a turn costs more than the listed output price. The eff (effective) price scales the output rate by ×2.5 to include that overhead on average.

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. Paid games bill model cost + 30% against your prepaid balance.