{"modelId":"z-ai/glm-5.3-flash","inputCostPerToken":{"amount":80,"scale":9,"currency":"USD"},"outputCostPerToken":{"amount":500,"scale":9,"currency":"USD"},"costPerImage":{"amount":0,"scale":9,"currency":"USD"},"cacheReadCostPerToken":{"amount":12,"scale":9,"currency":"USD"},"metadata":{"verifiable":true,"contextLength":1048576,"modelDisplayName":"GLM 5.3 Flash","modelDescription":"GLM-5.3-Flash is a native multimodal mixture-of-experts model for coding, agentic workflows, reasoning, tool use, and visual understanding.","modelIcon":"https://avatars.githubusercontent.com/u/223098841?v=4","ownedBy":"nearai","aliases":["zai-org/GLM-5.3-Flash","GLM-5.3-Flash","glm-5.3-flash","zai-org/GLM-5.1-FP8","zai-org/GLM-5-FP8","glm-latest","zai-org/GLM-latest","GLM-5","zai-org/GLM-4.7","glm","GLM-5.1","zai-org/GLM-5.1","z-ai/glm-5.2","deepseek-ai/DeepSeek-V4-Flash"],"providerType":"vllm","providerConfig":{"long_context":{"inference_url":"https://glm-5-3-flash-long.completions.near.ai","max_context_tokens":1048576,"base_max_context_tokens":100000}},"attestationSupported":true,"architecture":{"inputModalities":["text","image"],"outputModalities":["text"]},"huggingFaceId":"zai-org/GLM-5.3-Flash","quantization":"fp8","maxOutputLength":1048576,"supportedSamplingParameters":["temperature","top_p","top_k","min_p","frequency_penalty","presence_penalty","repetition_penalty","max_tokens","stop","seed","logit_bias"],"supportedFeatures":["tools","structured_outputs","reasoning","json_mode"],"isReady":true,"openrouterSlug":"z-ai/glm-5.3-flash"}}