Supported models and limits

Look up the AI models Autopilot supports and their context-window and output-token limits, organized by model.

Autopilot supports the following models. To configure your own subscription for any of them, refer to Configuring an LLM for Autopilot.

Unterstützte Modelle

Autopilot supports the following models:

• Anthropic.Claude-4-5-sonnet
• gpt-4o-2024-11-20
• gpt-5-1 (nicht im öffentlichen Sektor verfügbar)
• gpt-5-4 (nicht im öffentlichen Sektor verfügbar)
• gemini-2.5-pro (nicht im öffentlichen Sektor verfügbar)
• gemini-2.5-Flag (nicht im öffentlichen Sektor verfügbar)

This list reflects the models Autopilot supports. For the model actually in effect for a given tenant and feature, and its live status (Active, Blocked, Deprecating soon), routing region, and configuration history, see Model hub.

Model limits

The following context window and maximum output token limits are specific to each model. They are separate from product-level and feature-level limits, such as maximum test cases or maximum requirement-quality suggestions — for those, see Best practices and limitations.

Modell	Kontextfenster	Max. Ausgabetoken
GPT-4o (OpenAI)	128.000 Token	16.384 (16K) Token
GPT-5-Familie (OpenAI)	400.000 Token	Bis zu 128.000 Token
Claude Sonnet 4.5 (Anthropic)	200.000 Token	64.000 Token
Gemini 2.5 Pro (Google)	Bis zu ca. 1 Mio. Token (1.048.576)	Ca. 64.000 Token (65.535)
Gemini 2.5 Flash (Google)	Bis zu ca. 1 Mio. Token (geringere effektive Reasoning-Tiefe als Pro)	Ca. 64.000 Token (65.535)