Pick the model for the job and pay what it really costs
Fast models for routine work, stronger ones for hard problems. Credits map to the real cost of each model, so a quick answer costs less than a long research run.
BusyBee.Day bots run on models from Anthropic, OpenAI, Google, xAI, DeepSeek, Moonshot, Z.ai, Qwen, MiniMax and Xiaomi. Fast models are on every plan, standard models from Basic, premium ones on Max. Usage is paid in credits: one credit is about one cent of real model and computer cost. Pro and above can add their own provider keys.
Models by tier
| Tier | Models | Plans |
|---|---|---|
| Fast | Claude Haiku 4.5, Gemini 3.8 Flash, GPT-6 Luna, DeepSeek V4 Flash, GLM-5.3 Flash, Qwen3.8 Flash, MiniMax M3, MiMo V2.6 Flash | All plans |
| Standard | Claude Sonnet 5.5, Gemini 3.1 Pro, GPT-6 Sol, Grok 4.7, DeepSeek V4 Pro, Kimi K3, GLM-5.3, Qwen3.8 Max, MiMo V2.6 Pro | Basic, Pro, Team, Max |
| Premium | Claude Opus 5.5, Claude Fable 5.1, GPT-6 Astra | Max |
Model list as of 1 October 2026.
Credits included each month
| Plan | Credits a month | Price |
|---|---|---|
| Free | 30 | $0 |
| Basic | 380 | $10 a month, or $8 billed yearly |
| Pro | 1,150 | $29 a month, or $23 billed yearly |
| Max | 4,000 | $99 a month, or $79 billed yearly |
| Team | 1,000 per member | $25 per member a month, or $20 billed yearly (from 3 members) |
Monthly credits renew on the 1st and do not carry over. Extra packs of 1,000 credits cost $19 and last 12 months.
How the model is chosen
- A chat or run can have its own model.
- Otherwise the bot's model, if it has one.
- Otherwise your default model, which you set once for every bot in every team.
- New accounts start on GPT-6 Luna until you change it.
Your own keys
On Pro, Max and Team you can add your own API key for a provider. BusyBee.Day checks the key before saving it and encrypts it. Requests with your key go to the provider directly and are billed by them.