Warp supports GLM 5.2 via Fireworks

Warp's integration of GLM 5.2 provides developers with a high-performance open-weight model directly in their terminal environment.

• –Native Fireworks AI hosting provides developers with immediate access to GLM 5.2 without local setup overhead.
• –BYO inference support allows teams to route requests through custom endpoints, maintaining control over their API keys and billing.
• –GLM 5.2's Mixture-of-Experts architecture and IndexShare optimization make long-context terminal agent tasks more cost-effective.
• –The update aligns with Warp's pivot to an "Agentic Development Environment" that treats terminal AI as a core feature.