{"data":{"id":"z-ai","name":"Z.ai","website":"https://www.zhipuai.cn","categories":["text","image","video"],"docs_url":"https://docs.bigmodel.cn","notes":"GLM BigModel Open API. Approximate USD conversion of published list.","role":"lab","models":[{"id":"z-ai/glm-4.5","provider_id":"z-ai","name":"Z.ai: GLM 4.5","modalities":["text"],"context_window":131072,"family":"glm-4.5","status":"active","description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"created_at":1753471347,"canonical_slug":"z-ai/glm-4.5","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"z-ai","cheapest_provider_name":"Z.ai","cheapest_price":1,"savings_pct":null,"savings_basis":null},{"id":"z-ai/glm-4.5-air","provider_id":"z-ai","name":"Z.ai: GLM 4.5 Air","modalities":["text"],"context_window":131072,"family":"glm-4.5-air","status":"active","description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"created_at":1753471258,"canonical_slug":"z-ai/glm-4.5-air","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"novita","cheapest_provider_name":"Novita","cheapest_price":0.31,"savings_pct":27.1,"savings_basis":"lab"},{"id":"z-ai/glm-4.5v","provider_id":"z-ai","name":"Z.ai: GLM 4.5V","modalities":["text","image"],"context_window":65536,"family":"glm-4.5v","status":"active","description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"created_at":1754922288,"canonical_slug":"z-ai/glm-4.5v","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"novita","cheapest_provider_name":"Novita","cheapest_price":0.9,"savings_pct":null,"savings_basis":null},{"id":"z-ai/glm-4.6","provider_id":"z-ai","name":"Z.ai: GLM 4.6","modalities":["text"],"context_window":204800,"family":"glm-4.6","status":"active","description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"created_at":1759235576,"canonical_slug":"z-ai/glm-4.6","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.7,"savings_pct":30,"savings_basis":"lab"},{"id":"z-ai/glm-4.6v","provider_id":"z-ai","name":"Z.ai: GLM 4.6V","modalities":["image","text","video"],"context_window":131072,"family":"glm-4.6v","status":"active","description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"created_at":1765207462,"canonical_slug":"z-ai/glm-4.6-20251208","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"novita","cheapest_provider_name":"Novita","cheapest_price":0.45,"savings_pct":null,"savings_basis":null},{"id":"z-ai/glm-4.7","provider_id":"z-ai","name":"Z.ai: GLM 4.7","modalities":["text"],"context_window":204800,"family":"glm-4.7","status":"active","description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_p"],"created_at":1766378014,"canonical_slug":"z-ai/glm-4.7-20251222","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.59,"savings_pct":41,"savings_basis":"lab"},{"id":"z-ai/glm-4.7-flash","provider_id":"z-ai","name":"Z.ai: GLM 4.7 Flash","modalities":["text"],"context_window":200000,"family":"glm-4.7-flash","status":"active","description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1768833913,"canonical_slug":"z-ai/glm-4.7-flash-20260119","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"cloudflare","cheapest_provider_name":"Cloudflare","cheapest_price":0.145,"savings_pct":0.3,"savings_basis":"openrouter"},{"id":"z-ai/glm-5","provider_id":"z-ai","name":"Z.ai: GLM 5","modalities":["text"],"context_window":204800,"family":"glm-5","status":"active","description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1770829182,"canonical_slug":"z-ai/glm-5-20260211","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"gmicloud","cheapest_provider_name":"GMICloud","cheapest_price":0.93,"savings_pct":40,"savings_basis":"lab"},{"id":"z-ai/glm-5-turbo","provider_id":"z-ai","name":"Z.ai: GLM 5 Turbo","modalities":["text"],"context_window":202752,"family":"glm-5-turbo","status":"active","description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"created_at":1773583573,"canonical_slug":"z-ai/glm-5-turbo-20260315","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"z-ai","cheapest_provider_name":"Z.ai","cheapest_price":1.9,"savings_pct":null,"savings_basis":null},{"id":"z-ai/glm-5.1","provider_id":"z-ai","name":"Z.ai: GLM 5.1","modalities":["text"],"context_window":204800,"family":"glm-5.1","status":"active","description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1775578025,"canonical_slug":"z-ai/glm-5.1-20260406","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"chutes","cheapest_provider_name":"Chutes","cheapest_price":1.4,"savings_pct":34.9,"savings_basis":"lab"},{"id":"z-ai/glm-5.2","provider_id":"z-ai","name":"Z.ai: GLM 5.2","modalities":["text"],"context_window":1048576,"family":"glm-5.2","status":"active","description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1781631930,"canonical_slug":"z-ai/glm-5.2-20260616","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"morph","cheapest_provider_name":"Morph","cheapest_price":0.518,"savings_pct":75.9,"savings_basis":"lab"},{"id":"z-ai/glm-5.3","provider_id":"z-ai","name":"Z.ai: GLM 5.3","modalities":["text"],"context_window":1048576,"family":"glm-5.3","status":"active","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1787086655,"canonical_slug":"z-ai/glm-5.3-20260816","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"wafer","cheapest_provider_name":"Wafer","cheapest_price":0.402425,"savings_pct":81.3,"savings_basis":"lab"},{"id":"z-ai/glm-5.3:batch","provider_id":"z-ai","name":"Z.ai: GLM 5.3 (batch)","modalities":["text"],"context_window":1048576,"family":"glm-5.3","status":"active","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"created_at":1787086655,"canonical_slug":"z-ai/glm-5.3-20260816","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"z-ai/glm-5.3-flash","provider_id":"z-ai","name":"Z.ai: GLM 5.3 Flash","modalities":["text","image","video"],"context_window":1048576,"family":"glm-5.3-flash","status":"active","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1787752741,"canonical_slug":"z-ai/glm-5.3-flash-20260826","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"relace","cheapest_provider_name":"Relace","cheapest_price":0.0518,"savings_pct":78.2,"savings_basis":"lab"},{"id":"z-ai/glm-5.3-flash:batch","provider_id":"z-ai","name":"Z.ai: GLM 5.3 Flash (batch)","modalities":["text","image","video"],"context_window":1048576,"family":"glm-5.3-flash","status":"active","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1787752741,"canonical_slug":"z-ai/glm-5.3-flash-20260826","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"z-ai/glm-5.3-flashx","provider_id":"z-ai","name":"Z.ai: GLM 5.3 FlashX","modalities":["text","image","video"],"context_window":1048576,"family":"glm-5.3-flashx","status":"active","description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"created_at":1789744020,"canonical_slug":"z-ai/glm-5.3-flashx-20260918","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"z-ai","cheapest_provider_name":"Z.ai","cheapest_price":0.59,"savings_pct":null,"savings_basis":null},{"id":"z-ai/glm-5.3-prime","provider_id":"z-ai","name":"Z.ai: GLM 5.3 Prime","modalities":["text"],"context_window":1000000,"family":"glm-5.3-prime","status":"active","description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1790199651,"canonical_slug":"z-ai/glm-5.3-prime-20260921","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"alibaba","cheapest_provider_name":"Alibaba","cheapest_price":4.3,"savings_pct":null,"savings_basis":null},{"id":"z-ai/glm-5v-turbo","provider_id":"z-ai","name":"Z.ai: GLM 5V Turbo","modalities":["image","text","video"],"context_window":202752,"family":"glm-5v-turbo","status":"active","description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...","architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"created_at":1775061458,"canonical_slug":"z-ai/glm-5v-turbo-20260401","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":"atlascloud","cheapest_provider_name":"AtlasCloud","cheapest_price":1.9,"savings_pct":null,"savings_basis":null},{"id":"~z-ai/glm-flash-latest","provider_id":"z-ai","name":"Z.ai: GLM Flash Latest","modalities":["text","image","video"],"context_window":1048576,"family":"glm-flash-latest","status":"active","description":"This model always redirects to the latest model in the GLM Flash family.","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1787817633,"canonical_slug":"~z-ai/glm-flash-latest","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"~z-ai/glm-latest","provider_id":"z-ai","name":"Z.ai: GLM Latest","modalities":["text"],"context_window":1048576,"family":"glm-latest","status":"active","description":"This model always redirects to the latest GLM model from Z.ai.","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1787151053,"canonical_slug":"~z-ai/glm-latest","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"z-ai","creator_name":"Z.ai","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null}]}}