{"data":[{"id":"fireworks-ai-firellava-13b","name":"firellava-13b","display_name":"FireLLaVA 13B","description":"A 13B-parameter multimodal vision-language model from Fireworks AI built on the LLaVA architecture for image understanding and visual question answering.","creator":"fireworks-ai","family":"llava","tier":"","version":null,"type":"language","size_in_bn":13,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"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":["fireworks_ai/accounts/fireworks/models/firellava-13b","fireworks-ai-firellava-13b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-19 08:02:10"},{"id":"llava-hf-llava-1-5-7b-hf","name":"llava-1-5-7b-hf","display_name":"LLaVA 1.5 7B HF","description":"7B multimodal vision-language model fine-tuned on GPT-generated instruction-following data, combining a visual encoder with a LLaMA/Vicuna language backbone.","creator":"llava-hf","family":"llava","tier":"","version":null,"type":"image-to-text","size_in_bn":null,"modalities":{"input":["image"],"output":["text"]},"context_window":null,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"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":false,"provider_count":0,"ids":["@cf/llava-hf/llava-1.5-7b-hf","llava-hf-llava-1-5-7b-hf"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-19 08:02:10"},{"id":"01-ai-llava-yi-34b","name":"llava-yi-34b","display_name":"LLaVA Yi 34B","description":"A 34B multimodal vision-language model combining the LLaVA architecture with Yi's base model for visual question answering and image understanding.","creator":"01-ai","family":"llava","tier":"","version":null,"type":"language","size_in_bn":34,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"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":["01-ai-llava-yi-34b","fireworks_ai/accounts/fireworks/models/llava-yi-34b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-19 08:02:10"}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":3},"meta":{"updated_at":"2026-06-19","request_id":"d1b3e62b-3d1c-4c4c-866f-db65f848f9ad","execution_ms":1}}