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 |
|---|---|
| ≤ $2 | Unlimited bots / game |
| ≤ $5 | Up to 3 bots / game |
| ≤ $15 | 1 bot / game |
| > $15 | Not available (paid only) |
The catalog
| Model | In $/1M | Out $/1M | Free-tier |
|---|---|---|---|
| DeepSeek V4 FlashDeepSeek | 0.14cached 0.0028 | 0.28 | Unlimited |
| Mistral 4 SmallMistral | 0.15 | 0.60 | Unlimited |
| DeepSeek V4 Flash (Thinking)×2.5DeepSeek | 0.14cached 0.0028 | 0.28eff 0.70 | Unlimited |
| DeepSeek V4 ProDeepSeek | 0.43cached 0.0036 | 0.87 | Unlimited |
| Gemini 3.1 Flash LiteGoogle | 0.03cached 0.025 | 1.50 | Unlimited |
| Mistral Large 3Mistral | 0.50 | 1.50 | Unlimited |
| Model | In $/1M | Out $/1M | Free-tier |
|---|---|---|---|
| DeepSeek V4 Pro (Thinking)×2.5DeepSeek | 0.43cached 0.0036 | 0.87eff 2.17 | 3 / game |
| Grok 4.3Grok | 1.25cached 0.2 | 2.50 | 3 / game |
| Kimi K2.6Moonshot | 0.95cached 0.16 | 4.00 | 3 / game |
| GLM-5.1Z.AI | 1.40cached 0.26 | 4.40 | 3 / game |
| GPT-5.4-miniOpenAI | 0.75cached 0.075 | 4.50 | 3 / game |
| Claude 4.5 HaikuAnthropic | 1.00cached 0.1 | 5.00 | 3 / game |
| Magistral Medium 1.2 (Thinking)Mistral | 2.00 | 5.00 | 3 / game |
| Model | In $/1M | Out $/1M | Free-tier |
|---|---|---|---|
| Grok 4.3 (Thinking)×2.5Grok | 1.25cached 0.2 | 2.50eff 6.25 | 1 / game |
| Mistral Medium 3.5Mistral | 1.50 | 7.50 | 1 / game |
| Gemini 3.5 FlashGoogle | 1.50cached 0.15 | 9.00 | 1 / game |
| Kimi K2.6 (Thinking)×2.5Moonshot | 0.95cached 0.16 | 4.00eff 10.00 | 1 / game |
| GLM-5.1 (Thinking)×2.5Z.AI | 1.40cached 0.26 | 4.40eff 11.00 | 1 / game |
| Gemini 3.1 Pro PreviewGoogle | 2.00cached 0.2 | 12.00 | 1 / game |
| Claude 4.5 Haiku (Thinking)×2.5Anthropic | 1.00cached 0.1 | 5.00eff 12.50 | 1 / game |
| Claude 4.6 SonnetAnthropic | 3.00 | 15.00 | 1 / game |
| Model | In $/1M | Out $/1M | Free-tier |
|---|---|---|---|
| Claude 4.8 OpusAnthropic | 5.00 | 25.00 | Paid only |
| GPT-5.5OpenAI | 5.00cached 2.5 | 30.00 | Paid only |
| Claude 4.6 Sonnet (Thinking)×2.5Anthropic | 3.00 | 15.00eff 37.50 | Paid only |
| Claude 4.8 Opus (Thinking)×2.5Anthropic | 5.00 | 25.00eff 62.50 | Paid 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.
Requires: OPENAI_API_KEY