Context length depends on the model you choose, and it can change as models are added, updated, or deprecated.
Some Venice models support much larger context windows than others, so the best place to check the current limit is the model details shown in Venice or the live model documentation. In Classic Chat, you can also view context window details in the model selector in the prompt bar by hovering over a model.
GLM 5.2 context in Classic Chat
GLM 5.2 comes in two versions in Classic Chat:
Plan-included GLM 5.2 runs on a much smaller working context (around 50k tokens), even though the interface may show a larger number. As a chat reaches that limit, older messages slide out.
Pay-per-use GLM 5.2 (coin icon) provides the full ~1M context window. Credits apply.
Larger Context Chat
Pro users can extend the context window on plan-included GLM 5.2 by enabling the "Larger Context Chat" setting in settings. GLM 5.2 is the only pro (plan-included) model available in this mode — pay-per-use models already provide full context.
If you plan to work with long prompts, long chats, or large files, check the model’s current context window before you start. See the current model docs at Models and API Pricing.
The largest context length available in the app is in agentic chat: venice.ai/chat/agent