{"data":[{"id":"zhipu-glm-5-3","name":"glm-5-3","display_name":"GLM-5.3","description":"Z AI's flagship reasoning LLM sharing its base with GLM-5.2, with targeted improvements for complex software engineering and agentic tasks.","creator":"zhipu","family":"glm","tier":"","version":"5-3","type":"language","size_in_bn":753.33,"modalities":{"input":["image","text"],"output":["text"]},"context_window":1310720,"max_output_tokens":1024000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-18","earliest_deprecation_date":"2098-12-31","deprecated":false,"has_pricing":true,"provider_count":34,"ids":["accounts/fireworks/models/glm-5p3","aiand/zai-org/glm-5.3","aihubmix/glm-5.3","azure_ai/FW-GLM-5.3","baseten/zai-org/GLM-5.3","bigmodel/glm-5.3","clf_ai_gateway/glm-5.3","coralbricks/glm-5.3","databricks/databricks-glm-5-3","empiriolabs/glm-5-3","fireworks_ai/accounts/fireworks/models/glm-5p3","fireworks_ai/glm-5p3","friendliai/zai-org/GLM-5.3","glm-5-3","glm-5-3-low","glm-5.3","global.zai.glm-5.3","gmi/zai-org/GLM-5.3","huggingface-llm-glm-5-3","inferenceapis/glm-5.3","inferenceapis/zai-org/GLM-5.3","kyma/glm-5.3","mistral/zai-glm-5-3","nebius/zai-org/GLM-5.3","novita/zai-org/glm-5.3","opencode_go/glm-5.3","openrouter/z-ai/glm-5.3","openrouter/z-ai/glm-5.3:batch","perplexity/perplexity/glm-5.3","resetdata/zai/glm-5.3","sail/zai-org/GLM-5.3","sarvam/glm5.3","scx-ai/GLM-5.3","streamlake/GLM-5.3","tencent/glm-5.3","together_ai/zai-org/GLM-5.3","us.zai.glm-5.3","wandb/zai-org/GLM-5.3","z-ai/glm-5.3","zai-glm-5-3","zai-org/glm-5.3","zai-org/GLM-5.3","zai.glm-5.3","zai/glm-5.3","zhipu-glm-5-3"],"hf_likes":1181,"hf_downloads":0,"hf_downloads_all_time":0,"hf_trending_score":1143,"updated_at":"2026-11-22 08:02:29","pricing":{"model_id":"zhipu-glm-5-3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-11-22","ingestion_date":"2026-11-22","summary":{"currency":"USD","min_input_per_1m":0.0699,"max_input_per_1m":2.016,"min_output_per_1m":1.4,"max_output_per_1m":6.336,"min_cache_read_per_1m":0.0689,"min_cache_write_per_1m":1.4,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":33},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-5-3-flash","name":"glm-5-3-flash","display_name":"GLM-5.3 Flash","description":"A native multimodal LLM optimized for efficient coding and long-horizon agent tasks, using a hybrid sparse and linear attention architecture to maintain accuracy over long contexts.","creator":"zhipu","family":"glm","tier":"flash","version":"5-3","type":"language","size_in_bn":321.323,"modalities":{"input":["image","text","video"],"output":["text"]},"context_window":1310720,"max_output_tokens":1024000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-26","earliest_deprecation_date":"2098-12-31","deprecated":false,"has_pricing":true,"provider_count":30,"ids":["accounts/fireworks/models/glm-5p3-flash","aiand/zai-org/glm-5.3-flash","aihubmix/glm-5.3-flash","azure_ai/FW-GLM-5.3-Flash","baseten/zai-org/GLM-5.3-Flash","bigmodel/glm-5.3-flash","clf_ai_gateway/glm-5.3-flash","databricks/databricks-glm-5-3-flash","deepinfra/zai-org/GLM-5.3-Flash","empiriolabs/glm-5-3-flash","fireworks_ai/accounts/fireworks/models/glm-5p3-flash","fireworks_ai/glm-5p3-flash","friendliai/zai-org/GLM-5.3-Flash","glm-5-3-flash","gmi/zai-org/GLM-5.3-Flash","huggingface-vlm-glm-5-3-flash","inferenceapis/glm-5.3-flash","inferenceapis/zai-org/GLM-5.3-Flash","kyma/glm-5.3-flash","mistral/zai-glm-5-3-flash","nebius/zai-org/GLM-5.3-Flash","nvidia_nim/z-ai/glm-5.3-flash","opencode_go/glm-5.3-flash","openinfer/@oi/GLM-5.3-Flash","openrouter/z-ai/glm-5.3-flash","openrouter/z-ai/glm-5.3-flash:batch","perplexity/perplexity/glm-5.3-flash","sail/zai-org/GLM-5.3-Flash","sarvam/glm5.3-flash","streamlake/GLM-5.3-Flash","tencent/glm-5.3-flash","together_ai/zai-org/GLM-5.3-Flash","wally/glm-5.3-flash","wandb/zai-org/GLM-5.3-Flash","z-ai/glm-5.3-flash","zai-glm-5-3-flash","zai-org/glm-5.3-flash","zai-org/GLM-5.3-Flash","zai/glm-5.3-flash","zerogpu/glm-5.3-flash","zhipu-glm-5-3-flash"],"hf_likes":1107,"hf_downloads":0,"hf_downloads_all_time":0,"hf_trending_score":1073,"updated_at":"2026-11-22 08:02:29","pricing":{"model_id":"zhipu-glm-5-3-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-11-22","ingestion_date":"2026-11-22","summary":{"currency":"USD","min_input_per_1m":0.06,"max_input_per_1m":0.272,"min_output_per_1m":0.2,"max_output_per_1m":1.56,"min_cache_read_per_1m":0.012,"min_cache_write_per_1m":0.15001,"min_reasoning_per_1m":null,"cheapest_providers":["other/clf-ai-gateway"],"provider_count":30},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v4-1-flash-interactive","name":"deepseek-v4-1-flash-interactive","display_name":"DeepSeek V4.1 Flash Interactive","description":"Low-latency Flash-tier DeepSeek V4.1 LLM tuned for interactive, real-time conversational use.","creator":"deepseek","family":"v4","tier":"flash","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image"],"output":["text"]},"context_window":1048576,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["deepseek-v4-1-flash-interactive","sarvam/deepseekv4.1-flash-1017-interactive"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29","pricing":{"model_id":"deepseek-v4-1-flash-interactive","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-11-22","ingestion_date":"2026-11-22","summary":{"currency":"USD","min_input_per_1m":0.2659574468,"max_input_per_1m":0.2659574468,"min_output_per_1m":1.117021277,"max_output_per_1m":1.117021277,"min_cache_read_per_1m":0.0053191489,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["sarvam"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-4","name":"gemma-4","display_name":"Gemma 4","description":"Google DeepMind's fourth-generation open multimodal LLM series, supporting text and image input with text output generation.","creator":"google","family":"gemma","tier":"","version":"4","type":"language","size_in_bn":null,"modalities":{"input":["image","text"],"output":["text"]},"context_window":262144,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["gemma-4-e2b","gemma-4-e2b-non-reasoning","gemma-4-e4b","gemma-4-e4b-non-reasoning","google-gemma-4","publishers/google/models/gemma4","sarvam/gemma4"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29","pricing":{"model_id":"google-gemma-4","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-11-22","ingestion_date":"2026-11-22","summary":{"currency":"USD","min_input_per_1m":0.3723404255,"max_input_per_1m":0.3723404255,"min_output_per_1m":0.9574468085,"max_output_per_1m":0.9574468085,"min_cache_read_per_1m":0.1063829787,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["sarvam"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"sarvam-105b","name":"sarvam-105b","display_name":"Sarvam 105B","description":"A 105-billion-parameter large language model from Sarvam AI, designed for multilingual tasks with a focus on Indian languages.","creator":"sarvam","family":"sarvam","tier":"","version":null,"type":"language","size_in_bn":105,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["sarvam-105b","sarvam/sarvam-105b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29","pricing":{"model_id":"sarvam-105b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-11-22","ingestion_date":"2026-11-22","summary":{"currency":"USD","min_input_per_1m":0.1063829787,"max_input_per_1m":0.1063829787,"min_output_per_1m":0.2659574468,"max_output_per_1m":0.2659574468,"min_cache_read_per_1m":0.0026595745,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["sarvam"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"sarvam-105b-conversations","name":"sarvam-105b-conversations","display_name":"Sarvam 105B Conversations","description":"105B LLM from Sarvam tuned for conversational use, with a focus on Indian languages.","creator":"sarvam","family":"sarvam","tier":"","version":null,"type":"language","size_in_bn":105,"modalities":{"input":["text"],"output":["text"]},"context_window":32000,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["sarvam-105b-conversations","sarvam/sarvam-105b-conversations"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29","pricing":{"model_id":"sarvam-105b-conversations","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-11-22","ingestion_date":"2026-11-22","summary":{"currency":"USD","min_input_per_1m":0.1063829787,"max_input_per_1m":0.1063829787,"min_output_per_1m":0.2659574468,"max_output_per_1m":0.2659574468,"min_cache_read_per_1m":0.0026595745,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["sarvam"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":6},"meta":{"updated_at":"2026-11-22","request_id":"c32b0768-ba1d-4f7a-a608-e1aee08e3b42","execution_ms":11}}