z-ai
Z.ai: GLM 5.3 Flash (batch)
z-ai/glm-5.3-flash:batch
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.
- Context window: 1,048,576 tokens
- Input: text, image, video
- Output: text
- Pricing: $0.05/M input tokens, $0.18/M output tokens
RuntimeWire coverage
- Paper Instruments launches Ultramarine 1 Flash for professional work
- Cantina releases an open-weights model trained for vulnerability research
- Cantina releases open-weight security model trained on 50 vulnerability cases
- Inception launches Mercury Voice for faster AI phone agents
- Bolt launches Forge with 50x more usage and an opt-in data trade
- DeAlignAI publishes altered GLM-5.3-Flash weights, claims 320/320 harmful-prompt compliance
- OrcaRouter replaces Qwen3.8-27B with GLM-5.3 Flash on its free tier
- Warp launches Factory Benchmarks to test agents on work teams actually do
View on OpenRouter. Model data sourced from OpenRouter.