Models

Privatemode gives you access to the following models. For pricing and rate limits, see Pricing and Rate limits.

All chat models support streaming, tool calling, and structured outputs.

GLM-5.3

GLM-5.3 always performs reasoning steps to improve response quality. Use the reasoning_effort field to control how much the model reasons:

• max: maximum reasoning, at the highest latency and token cost. This is the default.
• high: less reasoning, for lower latency and token cost.
• low: least reasoning, for the lowest latency and token cost.

Any other value, including none, is silently mapped to max.

For example, to reduce latency at the cost of reasoning depth, extend your request with:

{
    "reasoning_effort": "low"
}

Reasoning can't be switched off. Use low to actually reduce reasoning.

Use the model ID glm-latest to always route to the latest available GLM model. The model ID glm-5.2 is deprecated and routes to GLM-5.3.

Kimi K2.6

The model supports images as input. Follow this guide to use the feature.

Kimi K2.6 performs reasoning steps to improve response quality. To disable reasoning and reduce latency at the cost of quality, extend your request with:

{
    "chat_template_kwargs": {"thinking": false}
}

Use the model ID kimi-latest to always route to the latest available Kimi model.

Qwen3-Embedding 4B

The model uses Matryoshka training and supports output dimensions of 1024 or 2560, set via the dimensions field in the embeddings request. For most tasks, 1024 dimensions is sufficient. For other dimensionalities, truncate the returned vector client-side and re-normalize it afterward.

Voxtral Mini 3B

Use sufficiently high-quality audio with adequate bit rates. Consider Whisper large-v3 if you face issues with low quality audio.

DeepSeek-OCR-2

This OCR model requires special prompt formatting. Follow this guide to use it correctly.