FAQ

Do I have to use a specific vendor SDK?

No. Call Bitdeer over HTTPS with your API key and any HTTP client. The SDK guides document the community openai packages for Python and JavaScript: set base_url / baseURL to https://api-inference.bitdeer.ai/v1 and pass your Bitdeer key.

How do I get an API key?

Log in to Bitdeer AI Console, navigate to Models → API Keys, and click Generate API Key. See the Authentication guide for step-by-step instructions.

What models are available?

Bitdeer AI self-deploys 9 chat models across text, vision, and audio. See the Model Catalog for the complete list.

Category	Model IDs
All models	`zai-org/GLM-5.2`, `moonshotai/Kimi-K2.6`, `Qwen/Qwen3.5-397B-A17B`, `MiniMaxAI/MiniMax-M2.5`, `nvidia/Nemotron-3-Nano-Omni-30B-A3B`, `nvidia/NVIDIA-Nemotron-3-Super-120B-A12B`, `deepseek-ai/DeepSeek-V4-Pro`, `XiaomiMiMo/MiMo-V2.5-Pro`, `nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B`
Vision (image)	`moonshotai/Kimi-K2.6`, `Qwen/Qwen3.5-397B-A17B`, `nvidia/Nemotron-3-Nano-Omni-30B-A3B`
Audio	`nvidia/Nemotron-3-Nano-Omni-30B-A3B`

Is streaming supported?

Yes. Set stream: true in your chat completion request to receive tokens via Server-Sent Events. See the Streaming guide.

What is the pricing model?

Bitdeer AI uses pay-per-token pricing with no minimum commitment. Input and output tokens are priced separately. See the Model Catalog for per-model pricing, or visit the Bitdeer Pricing page.

How do I report an issue?

Contact Bitdeer AI support at bitdeer.ai/en/contact. Include:

What you tried (endpoint, model, parameters)
What you expected
What happened (error message, response body)
The id field from the failing response