{"data":[{"id":"alibaba-qwen3-8-max","name":"qwen3-8-max","display_name":"Qwen3.8 Max","description":"A massive 2.4T-parameter MoE flagship LLM optimized for coding, knowledge work, and autonomous multi-day programming tasks with native visual understanding.","creator":"alibaba","family":"qwen","tier":"max","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":1000000,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"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":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-09-03","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["accounts/fireworks/models/qwen3p8-max","aihubmix/qwen3.8-max","alibaba-qwen3-8-max","alibaba/qwen3.8-max","alibaba/qwen3.8-max-0902","dashscope/qwen3.8-max","deepinfra/Qwen/Qwen3.8-Max","fireworks_ai/accounts/fireworks/models/qwen3p8-max","fireworks_ai/qwen3p8-max","novita/qwen/qwen3.8-max","openrouter/qwen/qwen3.8-max","openrouter/qwen/qwen3.8-max-0902","qwen_ai_platform/qwen3.8-max","qwen/qwen3.8-max","Qwen/Qwen3.8-Max","qwen/qwen3.8-max-0902","qwen3-8-max","qwen3-8-max-0803","qwen3.8-max","qwen3.8-max-0902","qwencloud/qwen3.8-max","scx-ai/Qwen3.8-Max"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-8-max","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":1.65,"max_input_per_1m":2,"min_output_per_1m":4.951,"max_output_per_1m":6,"min_cache_read_per_1m":0.169,"min_cache_write_per_1m":2.1125,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","other/scx-ai"],"provider_count":10},"providers":[],"regions":[],"region_info":{}}},{"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":943718,"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":19,"ids":["accounts/fireworks/models/glm-5p3","aihubmix/glm-5.3","azure_ai/FW-GLM-5.3","baseten/zai-org/GLM-5.3","databricks/databricks-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","huggingface-llm-glm-5-3","mistral/zai-glm-5-3","nebius/zai-org/GLM-5.3","novita/zai-org/glm-5.3","openrouter/z-ai/glm-5.3","openrouter/z-ai/glm-5.3:batch","perplexity/perplexity/glm-5.3","sail/zai-org/GLM-5.3","together_ai/zai-org/GLM-5.3","us.zai.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":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-5-3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.079,"max_input_per_1m":1.75,"min_output_per_1m":3.08,"max_output_per_1m":5.5,"min_cache_read_per_1m":0.059,"min_cache_write_per_1m":1.4,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":18},"providers":[],"regions":[],"region_info":{}}},{"id":"moonshot-kimi-k3","name":"kimi-k3","display_name":"Kimi K3","description":"A flagship reasoning-capable multimodal LLM with 2.8 trillion parameters, built on Kimi Delta Attention (a hybrid linear attention mechanism) with native visual understanding and tool-use support.","creator":"moonshot","family":"kimi","tier":"","version":"k3","type":"language","size_in_bn":2779.932,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":943718,"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":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":18,"ids":["accounts/fireworks/models/kimi-k3","aihubmix/kimi-k3","azure_ai/FW-Kimi-K3","baseten/moonshotai/Kimi-K3","databricks/databricks-kimi-k3","deepinfra/moonshotai/Kimi-K3","fireworks_ai/accounts/fireworks/models/kimi-k3","fireworks_ai/kimi-k3","github_copilot/kimi-k3","global.moonshotai.kimi-k3","huggingface-vlm-kimi-k3","in.moonshotai.kimi-k3","kimi-k3","kimi-k3-low","moonshot-kimi-k3","moonshot/kimi-k3","moonshotai.kimi-k3","moonshotai/kimi-k3","moonshotai/Kimi-K3","nebius/moonshotai/Kimi-K3","novita/moonshotai/kimi-k3","openrouter/moonshotai/kimi-k3","perplexity/perplexity/kimi-k3","sail/moonshotai/Kimi-K3","together_ai/moonshotai/Kimi-K3","us.moonshotai.kimi-k3"],"hf_likes":7099,"hf_downloads":2850,"hf_downloads_all_time":2855,"hf_trending_score":6642,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"moonshot-kimi-k3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.73,"max_input_per_1m":3.6,"min_output_per_1m":10,"max_output_per_1m":18,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":2.99999,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":17},"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":943718,"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":false,"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":15,"ids":["accounts/fireworks/models/glm-5p3-flash","aihubmix/glm-5.3-flash","azure_ai/FW-GLM-5.3-Flash","baseten/zai-org/GLM-5.3-Flash","databricks/databricks-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","nebius/zai-org/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","together_ai/zai-org/GLM-5.3-Flash","wandb/zai-org/GLM-5.3-Flash","z-ai/glm-5.3-flash","zai-org/glm-5.3-flash","zai-org/GLM-5.3-Flash","zai/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":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-5-3-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.11,"max_input_per_1m":0.188,"min_output_per_1m":0.35,"max_output_per_1m":0.625,"min_cache_read_per_1m":0.02,"min_cache_write_per_1m":0.15001,"min_reasoning_per_1m":null,"cheapest_providers":["other/sail"],"provider_count":14},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v4-1-flash","name":"deepseek-v4-1-flash","display_name":"DeepSeek V4.1 Flash Expires Exp","description":"A fast large language model in DeepSeek's V4.1 series, optimized for low-latency responses with tool-use and reasoning support.","creator":"deepseek","family":"v4","tier":"flash","version":"1","type":"language","size_in_bn":763.205,"modalities":{"input":["image","text"],"output":["text"]},"context_window":1049000,"max_output_tokens":943718,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"DeepSeek","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":true,"adaptive_reasoning":false},"release_date":"2026-09-10","earliest_deprecation_date":"2026-12-15","deprecated":false,"has_pricing":true,"provider_count":11,"ids":["accounts/fireworks/models/deepseek-v4p1-flash","azure_ai/deepseek-v4.1-flash","azure_ai/FW-DeepSeek-V4.1-Flash","baseten/deepseek-ai/DeepSeek-V4.1-Flash","deepseek-ai/DeepSeek-V4.1-Flash","deepseek-v4-1-flash","deepseek-v4-1-flash-non-reasoning","deepseek-v4.1-flash","deepseek/deepseek-v4.1-flash","deepseek/deepseek-v4.1-flash-expires-on-0910","deepseek/deepseek-v4.1-flash-z","fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash","fireworks_ai/deepseek-v4p1-flash","nebius/deepseek-ai/DeepSeek-V4.1-Flash","openrouter/deepseek/deepseek-v4.1-flash","openrouter/deepseek/deepseek-v4.1-flash:batch","prism/deepseek-v4.1-flash","sail/deepseek-ai/DeepSeek-V4.1-Flash","together_ai/deepseek-ai/DeepSeek-V4.1-Flash","wandb/deepseek-ai/DeepSeek-V4.1-Flash"],"hf_likes":1554,"hf_downloads":6,"hf_downloads_all_time":6,"hf_trending_score":1472,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-v4-1-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.3,"min_output_per_1m":0.6,"max_output_per_1m":1.2,"min_cache_read_per_1m":0.006,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/sail"],"provider_count":11},"providers":[],"regions":[],"region_info":{}}},{"id":"minimax-m3","name":"minimax-m3","display_name":"MiniMax M3","description":"A multimodal foundation model supporting text, image, and video inputs with a 1M-token context window, designed for long-horizon agentic tasks, coding, and reasoning.","creator":"minimax","family":"m3","tier":"","version":null,"type":"language","size_in_bn":427.04,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":524288,"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":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-05-31","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":13,"ids":["accounts/fireworks/models/minimax-m3","aihubmix/minimax-m3","azure_ai/FW-MiniMax-M3","deepinfra/MiniMaxAI/MiniMax-M3","fireworks_ai/accounts/fireworks/models/minimax-m3","fireworks_ai/minimax-m3","minimax-m3","minimax/minimax-m3","minimax/MiniMax-M3","minimax/minimax-m3-free","minimax/minimax-m3:batch","MiniMaxAI/MiniMax-M3","nebius/MiniMaxAI/MiniMax-M3","novita/minimax/minimax-m3","openrouter/minimax/minimax-m3","openrouter/minimax/minimax-m3:batch","tencent/minimax-m3","together_ai/MiniMaxAI/MiniMax-M3","wandb/MiniMaxAI/MiniMax-M3"],"hf_likes":320,"hf_downloads":442,"hf_downloads_all_time":442,"hf_trending_score":314,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"minimax-m3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.23,"max_input_per_1m":0.33,"min_output_per_1m":0.96,"max_output_per_1m":1.32,"min_cache_read_per_1m":0.05,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/wandb"],"provider_count":12},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-7-plus","name":"qwen3-7-plus","display_name":"Qwen3.7 Plus","description":"A cost-effective Qwen3.7-series LLM with strong vision-language, reasoning, and tool-use capabilities, optimized for balanced performance and efficiency.","creator":"alibaba","family":"qwen","tier":"plus","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"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":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-06-03","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen3p7-plus","aihubmix/qwen3.7-plus","alibaba-qwen3-7-plus","alibaba/qwen3.7-plus","dashscope/qwen3.7-plus","fireworks_ai/accounts/fireworks/models/qwen3p7-plus","fireworks_ai/qwen3p7-plus","openrouter/qwen/qwen3.7-plus","qwen_ai_platform/qwen3.7-plus","qwen/qwen3.7-plus","qwen3-7-plus","qwen3.7-plus","qwen3.7-plus-2026-05-26","qwen3.7-plus-us","qwencloud/qwen3.7-plus","together_ai/Qwen/Qwen3.7-Plus"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-7-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.282,"max_input_per_1m":0.4,"min_output_per_1m":1.128,"max_output_per_1m":1.6,"min_cache_read_per_1m":0.0564,"min_cache_write_per_1m":0.3525,"min_reasoning_per_1m":null,"cheapest_providers":["other/aihubmix"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"thinkingmachines-inkling","name":"inkling","display_name":"Inkling","description":"A 975B Mixture-of-Experts multimodal LLM with 41B active parameters from Thinking Machines Lab, supporting audio, vision, reasoning, and tool use as the first open-weights release from the creator.","creator":"thinkingmachines","family":"inkling_mm_model","tier":"","version":null,"type":"language","size_in_bn":952.378,"modalities":{"input":["audio","image","pdf","text"],"output":["text"]},"context_window":1048576,"max_output_tokens":471859,"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":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":"2026-07-17","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/inkling","baseten/thinkingmachines/inkling","deepinfra/thinkingmachines/Inkling","fireworks_ai/accounts/fireworks/models/inkling","inkling","openrouter/thinkingmachines/inkling","thinkingmachines-inkling","thinkingmachines/inkling","thinkingmachines/Inkling","thinkingmachines/inkling:batch","together_ai/thinkingmachines/Inkling"],"hf_likes":858,"hf_downloads":4,"hf_downloads_all_time":4,"hf_trending_score":844,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"thinkingmachines-inkling","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.95,"max_input_per_1m":1,"min_output_per_1m":4.05,"max_output_per_1m":4.05,"min_cache_read_per_1m":0.16,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"minimax-m2","name":"minimax-m2","display_name":"MiniMax M2","description":"MiniMax's second-generation MoE language model with reasoning and tool-use capabilities, built for complex agentic and productivity workflows.","creator":"minimax","family":"mixtral","tier":"","version":null,"type":"language","size_in_bn":228.704,"modalities":{"input":["text"],"output":["text"]},"context_window":1000000,"max_output_tokens":176947,"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":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-10-23","earliest_deprecation_date":"2027-03-30","deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/minimax-m2","fireworks_ai/accounts/fireworks/models/minimax-m2","huggingface-llm-minimax-m2","minimax-m2","minimax.minimax-m2","minimax/minimax-m2","minimax/MiniMax-M2","novita/minimax/minimax-m2","openrouter/minimax/minimax-m2"],"hf_likes":1491,"hf_downloads":69357,"hf_downloads_all_time":1925616,"hf_trending_score":0,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"minimax-m2","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.3,"max_input_per_1m":0.3,"min_output_per_1m":1.2,"max_output_per_1m":1.2,"min_cache_read_per_1m":0.03,"min_cache_write_per_1m":0.375,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","fireworks_ai","google_vertex_ai","minimax","novita","openrouter","vercel_ai_gateway"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"minimax-m1-80k","name":"minimax-m1-80k","display_name":"MiniMax M1 80k","description":"A long-context variant of MiniMax's open-weight hybrid MoE reasoning model supporting 80,000-token windows for extended document and multi-turn tasks.","creator":"minimax","family":"m1","tier":"","version":null,"type":"language","size_in_bn":456.09,"modalities":{"input":["text"],"output":["text"]},"context_window":1000000,"max_output_tokens":40000,"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":false,"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":3,"ids":["accounts/fireworks/models/minimax-m1-80k","fireworks_ai/accounts/fireworks/models/minimax-m1-80k","minimax-m1-80k","minimaxai/minimax-m1-80k","novita/minimaxai/minimax-m1-80k"],"hf_likes":691,"hf_downloads":743,"hf_downloads_all_time":101977,"hf_trending_score":0,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"minimax-m1-80k","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.55,"min_output_per_1m":0.1,"max_output_per_1m":2.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-120b","name":"gpt-oss-120b","display_name":"GPT OSS 120B","description":"A 120-billion-parameter open-weights GPT model from OpenAI designed for reasoning-intensive tasks with implicit caching support.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":120,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"GPT","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":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-08-05","earliest_deprecation_date":"2027-07-01","deprecated":false,"has_pricing":true,"provider_count":24,"ids":["@cf/openai/gpt-oss-120b","accounts/fireworks/models/gpt-oss-120b","azure_ai/FW-GPT-OSS-120B","azure_ai/gpt-oss-120b","baseten/openai/gpt-oss-120b","bedrock_mantle/openai.gpt-oss-120b","bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b","bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b","bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0","bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0","cerebras/gpt-oss-120b","cloudflare/@cf/openai/gpt-oss-120b","crusoe/openai/gpt-oss-120b","databricks/databricks-gpt-oss-120b","deepinfra/openai/gpt-oss-120b","fireworks_ai/accounts/fireworks/models/gpt-oss-120b","fireworks_ai/gpt-oss-120b","gpt-oss-120b","gpt-oss-120b-low","gpt-oss-120b-maas","groq/openai/gpt-oss-120b","lemonade/gpt-oss-120b-mxfp-GGUF","nebius/openai/gpt-oss-120b","novita/openai/gpt-oss-120b","ollama/gpt-oss:120b-cloud","openai-gpt-oss-120b","openai-reasoning-gpt-oss-120b","openai.gpt-oss-120b-1:0","openai/gpt-oss-120b","openai/gpt-oss-120b:free","openrouter/openai/gpt-oss-120b","ovhcloud/gpt-oss-120b","publishers/google/models/gpt-oss-120b-maas","replicate/openai/gpt-oss-120b","sail/openai/gpt-oss-120b","sambanova/gpt-oss-120b","scaleway/openai/gpt-oss-120b","tensormesh/openai/gpt-oss-120b","together_ai/openai/gpt-oss-120b","vertex_ai/openai/gpt-oss-120b-maas","wandb/openai/gpt-oss-120b","watsonx/openai/gpt-oss-120b"],"hf_likes":4719,"hf_downloads":3524674,"hf_downloads_all_time":32348365,"hf_trending_score":25,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"openai-gpt-oss-120b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":0.8,"min_output_per_1m":0.17,"max_output_per_1m":0.8,"min_cache_read_per_1m":0.015,"min_cache_write_per_1m":0.15001,"min_reasoning_per_1m":null,"cheapest_providers":["other/wandb"],"provider_count":23},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-5-air","name":"glm-4-5-air","display_name":"GLM-4.5 Air","description":"A compact MoE variant of GLM-4.5 from Z AI, offering a lighter architecture while retaining strong agentic reasoning and tool-use performance.","creator":"zhipu","family":"glm4_moe","tier":"air","version":"4-5","type":"language","size_in_bn":110.469,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":98304,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-12-31","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":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-07-25","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/glm-4p5-air","fireworks_ai/accounts/fireworks/models/glm-4p5-air","glm-4-5-air","novita/zai-org/glm-4.5-air","openrouter/z-ai/glm-4.5-air","pinstripes/ps/glm-4.5-air","vercel_ai_gateway/zai/glm-4.5-air","z-ai/glm-4.5-air","z-ai/glm-4.5-air:free","zai-org/glm-4.5-air","zai/glm-4.5-air","zhipu-glm-4-5-air"],"hf_likes":599,"hf_downloads":389697,"hf_downloads_all_time":3025118,"hf_trending_score":2,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-4-5-air","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.125,"max_input_per_1m":0.22,"min_output_per_1m":0.45,"max_output_per_1m":1.1,"min_cache_read_per_1m":0.025,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/pinstripes"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-vl-235b-a22b-instruct","name":"qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct","description":"The flagship instruction-tuned vision-language MoE model in the Qwen3 series, with 235B total and 22B activated parameters for superior visual perception and reasoning.","creator":"alibaba","family":"qwen3_vl_moe","tier":"","version":null,"type":"language","size_in_bn":235,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":262144,"max_output_tokens":129024,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen3","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":true,"adaptive_reasoning":false},"release_date":"2025-09-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":9,"ids":["accounts/fireworks/models/qwen3-vl-235b-a22b-instruct","alibaba-qwen3-vl-235b-a22b-instruct","alibaba/qwen3-vl-235b-a22b-instruct","bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct","dashscope/qwen3-vl-235b-a22b-instruct","deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct","gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","novita/qwen/qwen3-vl-235b-a22b-instruct","openrouter/qwen/qwen3-vl-235b-a22b-instruct","qwen_ai_platform/qwen3-vl-235b-a22b-instruct","qwen/qwen3-vl-235b-a22b-instruct","Qwen/Qwen3-VL-235B-A22B-Instruct","qwen3-vl-235b-a22b-instruct","qwencloud/qwen3-vl-235b-a22b-instruct"],"hf_likes":383,"hf_downloads":947793,"hf_downloads_all_time":2172030,"hf_trending_score":0,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-vl-235b-a22b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.53,"min_output_per_1m":0.88,"max_output_per_1m":2.66,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-large-3","name":"mistral-large-3","display_name":"Mistral Large 3","description":"Mistral AI's third-generation flagship model, a multimodal Mixture-of-Experts architecture with 675B total parameters and 41B active parameters.","creator":"mistral","family":"mistral3","tier":"","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["image"],"output":["text"]},"context_window":262144,"max_output_tokens":256000,"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":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2025-12-02","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/mistral-large-3-fp8","azure_ai/mistral-large-3","fireworks_ai/accounts/fireworks/models/mistral-large-3-fp8","mistral-large-3","mistral/mistral-large-3"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"mistral-large-3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.5,"max_input_per_1m":1.2,"min_output_per_1m":1.2,"max_output_per_1m":1.8,"min_cache_read_per_1m":0.05,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["azure_aifoundry","mistral","vercel_ai_gateway"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-4b-instruct","name":"qwen3-4b-instruct","display_name":"Qwen3 4B Instruct","description":"An instruction-tuned 4B Qwen3 model offering efficient text generation and reasoning in a small parameter footprint.","creator":"alibaba","family":"qwen3","tier":"","version":null,"type":"language","size_in_bn":4,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"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":false,"structured_outputs":true,"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":2,"ids":["accounts/fireworks/models/qwen3-4b-instruct-2507","alibaba-qwen3-4b-instruct","fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507","huggingface-reasoning-qwen3-4b-instruct-2507","lemonade/Qwen3-4B-Instruct-2507-GGUF","qwen3-4b-2507-instruct","qwen3-4b-2507-instruct-reasoning","qwen3-4b-instruct","qwen3-4b-instruct-reasoning"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-4b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.01,"max_input_per_1m":0.2,"min_output_per_1m":0.03,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-distill-qwen-32b","name":"deepseek-r1-distill-qwen-32b","display_name":"DeepSeek R1 Distill Qwen 32B","description":"A 32B Qwen-based model distilled from DeepSeek R1's reasoning capabilities, offering high-quality chain-of-thought performance at a mid-scale parameter count.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":32000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-07-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-01-29","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","accounts/fireworks/models/deepseek-r1-distill-qwen-32b","cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","deepseek-llm-r1-distill-qwen-32b","deepseek-r1-distill-qwen-32b","deepseek/deepseek-r1-distill-qwen-32b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b","novita/deepseek/deepseek-r1-distill-qwen-32b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"],"hf_likes":1545,"hf_downloads":1046750,"hf_downloads_all_time":23929632,"hf_trending_score":3,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-r1-distill-qwen-32b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.9,"min_output_per_1m":0.15,"max_output_per_1m":4.881,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["nscale"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-vl-30b-a3b-instruct","name":"qwen3-vl-30b-a3b-instruct","display_name":"Qwen3 VL 30B A3B Instruct","description":"An instruction-tuned vision-language MoE model with 30B total and 3B activated parameters, offering strong multimodal understanding and generation capabilities.","creator":"alibaba","family":"qwen3_vl_moe","tier":"","version":null,"type":"language","size_in_bn":30,"modalities":{"input":["image","text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"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":true,"adaptive_reasoning":false},"release_date":"2025-10-06","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/qwen3-vl-30b-a3b-instruct","alibaba-qwen3-vl-30b-a3b-instruct","deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct","novita/qwen/qwen3-vl-30b-a3b-instruct","openrouter/qwen/qwen3-vl-30b-a3b-instruct","qwen/qwen3-vl-30b-a3b-instruct","Qwen/Qwen3-VL-30B-A3B-Instruct","qwen3-vl-30b-a3b-instruct"],"hf_likes":562,"hf_downloads":2219395,"hf_downloads_all_time":14070852,"hf_trending_score":2,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-vl-30b-a3b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.2,"min_output_per_1m":0.6,"max_output_per_1m":0.7,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","fireworks_ai","openrouter"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-72b-instruct","name":"qwen2-5-72b-instruct","display_name":"Qwen2.5 72B Instruct","description":"A 72-billion-parameter instruction-tuned LLM from Alibaba's Qwen2.5 series, excelling at natural language understanding, summarization, and dialogue.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":72,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"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":true,"adaptive_reasoning":false},"release_date":"2024-09-19","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen2p5-72b-instruct","alibaba-qwen2-5-72b-instruct","deepinfra/Qwen/Qwen2.5-72B-Instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct","huggingface-llm-qwen2-5-72b-instruct","hyperbolic/Qwen/Qwen2.5-72B-Instruct","nebius/Qwen/Qwen2.5-72B-Instruct","novita/qwen/qwen-2.5-72b-instruct","openrouter/qwen/qwen-2.5-72b-instruct","qwen/qwen-2.5-72b-instruct","Qwen/Qwen2.5-72B-Instruct","qwen2-5-72b-instruct","qwen2.5-72b-instruct","together_ai/Qwen/Qwen2.5-72B-Instruct"],"hf_likes":927,"hf_downloads":457915,"hf_downloads_all_time":5817981,"hf_trending_score":1,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen2-5-72b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.12,"max_input_per_1m":1.2,"min_output_per_1m":0.3,"max_output_per_1m":1.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["hyperbolic"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwq-32b-preview","name":"qwq-32b-preview","display_name":"QwQ 32B Preview","description":"An experimental 32B reasoning LLM from Alibaba's Qwen team, showcasing open-model capabilities comparable to leading closed frontier models on reasoning benchmarks.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":16384,"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":["accounts/fireworks/models/qwen-qwq-32b-preview","alibaba-qwq-32b-preview","fireworks_ai/accounts/fireworks/models/qwen-qwq-32b-preview","qwq-32b-preview","QwQ-32B-Preview"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwq-32b-preview","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.9,"max_input_per_1m":0.9,"min_output_per_1m":0.9,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-5v","name":"glm-4-5v","display_name":"GLM-4.5V","description":"A multimodal MoE vision-language model from Z AI based on GLM-4.5 Air, delivering strong visual reasoning and tool-use performance.","creator":"zhipu","family":"glm4v_moe","tier":"","version":"4-5v","type":"language","size_in_bn":107.711,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":32000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-12-31","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":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":"2025-08-11","earliest_deprecation_date":"2026-12-31","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/glm-4p5v","fireworks_ai/accounts/fireworks/models/glm-4p5v","glm-4-5v","glm-4-5v-reasoning","novita/zai-org/glm-4.5v","openrouter/z-ai/glm-4.5v","z-ai/glm-4.5v","zai-org/glm-4.5v","zai/glm-4.5v","zhipu-glm-4-5v"],"hf_likes":717,"hf_downloads":44600,"hf_downloads_all_time":417587,"hf_trending_score":2,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-4-5v","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.6,"max_input_per_1m":1.2,"min_output_per_1m":1.2,"max_output_per_1m":1.8,"min_cache_read_per_1m":0.11,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","novita","openrouter","vercel_ai_gateway","z_ai"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-32b-instruct","name":"qwen2-5-32b-instruct","display_name":"Qwen2.5 32B Instruct","description":"A 32-billion-parameter instruction-tuned LLM from Alibaba's Qwen2.5 series, optimized for following complex instructions and text generation tasks.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"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":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":["accounts/fireworks/models/qwen2p5-32b-instruct","alibaba-qwen2-5-32b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-32b-instruct","huggingface-llm-qwen2-5-32b-instruct","nebius/Qwen/Qwen2.5-32B-Instruct","qwen2.5-32b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen2-5-32b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.9,"max_input_per_1m":0.9,"min_output_per_1m":0.9,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v2-5","name":"deepseek-v2-5","display_name":"DeepSeek V2.5","description":"An upgraded DeepSeek model merging the capabilities of DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct into a single unified assistant.","creator":"deepseek","family":"deepseek-v2","tier":"","version":"2.5","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"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":true,"provider_count":1,"ids":["accounts/fireworks/models/deepseek-v2p5","deepseek-v2-5","deepseek-v2-5-sep-2024","fireworks_ai/accounts/fireworks/models/deepseek-v2p5"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-v2-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":1.2,"max_input_per_1m":1.2,"min_output_per_1m":1.2,"max_output_per_1m":1.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-distill-llama-8b","name":"deepseek-r1-distill-llama-8b","display_name":"DeepSeek R1 Distill Llama 8B","description":"A compact 8B Llama-based model distilled from DeepSeek R1, delivering strong reasoning performance in a lightweight architecture.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":true,"provider_count":3,"ids":["accounts/fireworks/models/deepseek-r1-distill-llama-8b","deepseek-llm-r1-distill-llama-8b","deepseek-r1-distill-llama-8b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b","nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-r1-distill-llama-8b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.025,"max_input_per_1m":0.2,"min_output_per_1m":0.025,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["nscale"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-coder-7b-instruct","name":"qwen2-5-coder-7b-instruct","display_name":"Qwen2.5 Coder 7B Instruct","description":"A 7-billion-parameter instruction-tuned code LLM from Alibaba's Qwen2.5-Coder series, designed for responsive code generation and developer assistance.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"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":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":3,"ids":["accounts/fireworks/models/qwen2p5-coder-7b-instruct","alibaba-qwen2-5-coder-7b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct","huggingface-llm-qwen2-5-coder-7b-instruct","nscale/Qwen/Qwen2.5-Coder-7B-Instruct","qwen2-5-coder-7b-instruct","qwen2.5-coder-7b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen2-5-coder-7b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.01,"max_input_per_1m":0.2,"min_output_per_1m":0.03,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","nscale"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-2-7b-chat","name":"llama-2-7b-chat","display_name":"Llama 2 7B Chat","description":"A 7B Llama 2 model fine-tuned with RLHF for dialogue use cases, offering an efficient and accessible conversational LLM.","creator":"meta","family":"llama","tier":"","version":"2","type":"language","size_in_bn":7,"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":4,"ids":["@cf/meta/llama-2-7b-chat-fp16","accounts/fireworks/models/llama-v2-7b-chat","anyscale/meta-llama/Llama-2-7b-chat-hf","cloudflare/@cf/meta/llama-2-7b-chat-fp16","cloudflare/@cf/meta/llama-2-7b-chat-int8","fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat","llama-2-chat-7b","meta-llama-2-7b-chat","replicate/meta/llama-2-7b-chat"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-llama-2-7b-chat","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.556,"min_output_per_1m":0.15,"max_output_per_1m":6.667,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["replicate"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-mixtral-8x22b-instruct","name":"mistral-mixtral-8x22b-instruct","display_name":"Mixtral 8x22B Instruct","description":"The instruction-tuned version of Mistral AI's Mixtral 8x22B MoE model, optimized for following complex instructions and multi-turn dialogue.","creator":"mistral","family":"mixtral","tier":"","version":null,"type":"language","size_in_bn":22,"modalities":{"input":["pdf","text"],"output":["text"]},"context_window":65536,"max_output_tokens":52428,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-01-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Mistral","capabilities":{"function_calling":true,"parallel_function_calling":false,"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":true,"adaptive_reasoning":false},"release_date":"2024-04-17","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/mixtral-8x22b-instruct","anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1","fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct","fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf","huggingface-llm-mistralai-mixtral-8x22B-instruct-v0-1","mistral-8x22b-instruct","mistral-mixtral-8x22b-instruct","mistral/mixtral-8x22b-instruct","mistralai/mixtral-8x22b-instruct","nscale/mistralai/mixtral-8x22b-instruct-v0.1","ollama/mixtral-8x22B-Instruct-v0.1","openrouter/mistralai/mixtral-8x22b-instruct","vercel_ai_gateway/mistral/mixtral-8x22b-instruct"],"hf_likes":748,"hf_downloads":28279,"hf_downloads_all_time":6052030,"hf_trending_score":0,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"mistral-mixtral-8x22b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.6,"max_input_per_1m":2,"min_output_per_1m":0.6,"max_output_per_1m":6,"min_cache_read_per_1m":0.2,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["nscale"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-2-13b-chat","name":"llama-2-13b-chat","display_name":"Llama 2 13B Chat","description":"A 13B Llama 2 model fine-tuned with RLHF for dialogue use cases, optimized for helpful and safe conversational interactions.","creator":"meta","family":"llama","tier":"","version":"2","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":4,"ids":["accounts/fireworks/models/llama-v2-13b-chat","anyscale/meta-llama/Llama-2-13b-chat-hf","fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat","llama-2-chat-13b","meta-llama-2-13b-chat","meta.llama2-13b-chat-v1","replicate/meta/llama-2-13b-chat"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-llama-2-13b-chat","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.75,"min_output_per_1m":0.2,"max_output_per_1m":1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["replicate"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-1-7b","name":"qwen3-1-7b","display_name":"Qwen3 1.7B","description":"A 1.7-billion-parameter base LLM from Alibaba's Qwen3 series, balancing compact size with reasoning and language generation capabilities.","creator":"alibaba","family":"qwen3","tier":"","version":null,"type":"language","size_in_bn":1.7,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":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":["accounts/fireworks/models/qwen3-1p7b","alibaba-qwen3-1-7b","fireworks_ai/accounts/fireworks/models/qwen3-1p7b","huggingface-asr-qwen3-asr-1-7b","huggingface-reasoning-qwen3-1-7b","qwen3-1.7b","qwen3-1.7b-instruct","qwen3-1.7b-instruct-reasoning"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-1-7b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.1,"min_output_per_1m":0.1,"max_output_per_1m":0.1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-0-6b","name":"qwen3-0-6b","display_name":"Qwen3 0.6B","description":"A 0.6-billion-parameter base LLM from Alibaba's Qwen3 series, designed for ultra-lightweight deployment and on-device language tasks.","creator":"alibaba","family":"qwen3","tier":"","version":null,"type":"language","size_in_bn":0.6,"modalities":{"input":["text"],"output":["text"]},"context_window":40960,"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":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":["accounts/fireworks/models/qwen3-0p6b","alibaba-qwen3-0-6b","fireworks_ai/accounts/fireworks/models/qwen3-0p6b","qwen3-0.6b","qwen3-0.6b-instruct","qwen3-0.6b-instruct-reasoning"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-0-6b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.1,"min_output_per_1m":0.1,"max_output_per_1m":0.1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"nousresearch-chronos-hermes-2-13b","name":"chronos-hermes-2-13b","display_name":"Chronos Hermes 2 13B","description":"A 13B-parameter merged LLM combining Chronos and Nous Hermes Llama 2, blending imaginative writing style with coherent instruction-following.","creator":"nousresearch","family":"llama","tier":"","version":"2","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":["accounts/fireworks/models/chronos-hermes-13b-v2","fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2","nousresearch-chronos-hermes-2-13b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"nousresearch-chronos-hermes-2-13b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-13b","name":"meta-codellama-13b","display_name":"Code Llama 13B","description":"A 13B-parameter Code Llama model fine-tuned for general code synthesis and understanding across multiple programming languages.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":13,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"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":["accounts/fireworks/models/code-llama-13b","fireworks_ai/accounts/fireworks/models/code-llama-13b","meta-codellama-13b","meta-textgeneration-llama-codellama-13b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-13b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-13b-instruct","name":"meta-codellama-13b-instruct","display_name":"Code Llama 13B Instruct","description":"A 13B-parameter instruction-tuned Code Llama model designed to follow natural language instructions for code generation and understanding.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":13,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"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":["accounts/fireworks/models/code-llama-13b-instruct","fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct","meta-codellama-13b-instruct","meta-textgeneration-llama-codellama-13b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-13b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-13b-python","name":"meta-codellama-13b-python","display_name":"Code Llama 13B Python","description":"A 13B-parameter Code Llama model specialized for Python code synthesis, completion, and understanding.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":13,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"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":["accounts/fireworks/models/code-llama-13b-python","fireworks_ai/accounts/fireworks/models/code-llama-13b-python","meta-codellama-13b-python","meta-textgeneration-llama-codellama-13b-python"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-13b-python","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-34b","name":"meta-codellama-34b","display_name":"Code Llama 34B","description":"A 34B-parameter Code Llama model offering strong general code synthesis and understanding across multiple programming languages.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":34,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"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":["accounts/fireworks/models/code-llama-34b","fireworks_ai/accounts/fireworks/models/code-llama-34b","meta-codellama-34b","meta-textgeneration-llama-codellama-34b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-34b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.9,"max_input_per_1m":0.9,"min_output_per_1m":0.9,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-34b-instruct","name":"meta-codellama-34b-instruct","display_name":"Code Llama 34B Instruct","description":"A 34B-parameter instruction-tuned Code Llama model designed to follow natural language instructions for code generation tasks.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":34,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"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":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":3,"ids":["accounts/fireworks/models/code-llama-34b-instruct","anyscale/codellama/CodeLlama-34b-Instruct-hf","fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct","meta-codellama-34b-instruct","meta-textgeneration-llama-codellama-34b-instruct","perplexity/codellama-34b-instruct","together_ai/togethercomputer/CodeLlama-34b-Instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-34b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.35,"max_input_per_1m":1,"min_output_per_1m":0.9,"max_output_per_1m":1.4,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["perplexity"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-34b-python","name":"meta-codellama-34b-python","display_name":"Code Llama 34B Python","description":"A 34B-parameter Code Llama model specialized for Python code synthesis and understanding with enhanced Python-specific capabilities.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":34,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"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":["accounts/fireworks/models/code-llama-34b-python","fireworks_ai/accounts/fireworks/models/code-llama-34b-python","meta-codellama-34b-python","meta-textgeneration-llama-codellama-34b-python"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-34b-python","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.9,"max_input_per_1m":0.9,"min_output_per_1m":0.9,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-70b","name":"meta-codellama-70b","display_name":"Code Llama 70B","description":"A 70B-parameter Code Llama model delivering high-capability code synthesis and understanding across a wide range of programming languages.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"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":["accounts/fireworks/models/code-llama-70b","fireworks_ai/accounts/fireworks/models/code-llama-70b","meta-codellama-70b","meta-textgeneration-llama-codellama-70b","meta-textgenerationneuron-llama-codellama-70b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-70b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.9,"max_input_per_1m":0.9,"min_output_per_1m":0.9,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-70b-instruct","name":"meta-codellama-70b-instruct","display_name":"Code Llama 70B Instruct","description":"A 70B-parameter instruction-tuned Code Llama model designed to follow natural language instructions for complex code generation tasks.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"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":3,"ids":["accounts/fireworks/models/code-llama-70b-instruct","anyscale/codellama/CodeLlama-70b-Instruct-hf","fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct","meta-codellama-70b-instruct","meta-textgeneration-llama-codellama-70b-instruct","perplexity/codellama-70b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-70b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.7,"max_input_per_1m":1,"min_output_per_1m":0.9,"max_output_per_1m":2.8,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["perplexity"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-70b-python","name":"meta-codellama-70b-python","display_name":"Code Llama 70B Python","description":"A 70B-parameter Code Llama model specialized for Python code synthesis and understanding, offering the highest capacity in the Python-focused Code Llama series.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"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":["accounts/fireworks/models/code-llama-70b-python","fireworks_ai/accounts/fireworks/models/code-llama-70b-python","meta-codellama-70b-python","meta-textgeneration-llama-codellama-70b-python"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-70b-python","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.9,"max_input_per_1m":0.9,"min_output_per_1m":0.9,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-7b","name":"meta-codellama-7b","display_name":"Code Llama 7B","description":"A 7B parameter Code Llama model fine-tuned on code data for general code synthesis and understanding across multiple programming languages.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"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":false,"structured_outputs":true,"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":2,"ids":["accounts/fireworks/models/code-llama-7b","fireworks_ai/accounts/fireworks/models/code-llama-7b","llamagate/codellama-7b","meta-codellama-7b","meta-textgeneration-llama-codellama-7b","meta-textgenerationneuron-llama-codellama-7b","publishers/meta/models/codellama-7b-hf"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-7b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.06,"max_input_per_1m":0.2,"min_output_per_1m":0.12,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/llamagate"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-7b-instruct","name":"meta-codellama-7b-instruct","display_name":"Code Llama 7B Instruct","description":"A 7B instruction-tuned Code Llama model that follows natural language instructions to generate and explain code across multiple programming languages.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Other","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":"2025-04-14","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["accounts/fireworks/models/code-llama-7b-instruct","alfredpros/codellama-7b-instruct-solidity","cloudflare/@hf/thebloke/codellama-7b-instruct-awq","fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct","meta-codellama-7b-instruct","meta-textgeneration-llama-codellama-7b-instruct"],"hf_likes":17,"hf_downloads":45,"hf_downloads_all_time":17680,"hf_trending_score":0,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-7b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-codellama-7b-python","name":"meta-codellama-7b-python","display_name":"Code Llama 7B Python","description":"A 7B Code Llama variant further fine-tuned specifically on Python code for improved Python synthesis and understanding tasks.","creator":"meta","family":"codellama","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"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/code-llama-7b-python","meta-codellama-7b-python","meta-textgeneration-llama-codellama-7b-python","meta-textgenerationneuron-llama-codellama-7b-python"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"meta-codellama-7b-python","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"google-codegemma-2b","name":"codegemma-2b","display_name":"CodeGemma 2B","description":"Lightweight 2B-parameter code generation model built on Gemma, supporting text-to-text and text-to-code tasks with a small footprint.","creator":"google","family":"gemma","tier":"","version":null,"type":"language","size_in_bn":2,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"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":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":["accounts/fireworks/models/codegemma-2b","fireworks_ai/accounts/fireworks/models/codegemma-2b","google-codegemma-2b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"google-codegemma-2b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.1,"min_output_per_1m":0.1,"max_output_per_1m":0.1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"google-codegemma-7b","name":"codegemma-7b","display_name":"CodeGemma 7B","description":"7B-parameter code generation model built on Gemma, offering strong text-to-code and code completion capabilities for developer workflows.","creator":"google","family":"gemma","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"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":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":["accounts/fireworks/models/codegemma-7b","fireworks_ai/accounts/fireworks/models/codegemma-7b","google-codegemma-7b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"google-codegemma-7b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen1-5-7b-coder","name":"qwen1-5-7b-coder","display_name":"CodeQwen 1.5 7B","description":"A 7B code-specialized model from Alibaba's Qwen1.5 series, trained on 3 trillion tokens of code data with group query attention.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":65536,"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":true,"provider_count":1,"ids":["accounts/fireworks/models/code-qwen-1p5-7b","alibaba-qwen1-5-7b-coder","fireworks_ai/accounts/fireworks/models/code-qwen-1p5-7b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen1-5-7b-coder","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepcogito-cogito-1-3b-preview-llama","name":"cogito-1-3b-preview-llama","display_name":"Cogito V1 Preview Llama 3B","description":"A compact 3B-parameter hybrid reasoning LLM from Deep Cogito built on the Llama architecture, balancing efficiency with instruction-following capability.","creator":"deepcogito","family":"llama","tier":"","version":"1","type":"language","size_in_bn":3,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":true,"provider_count":1,"ids":["accounts/fireworks/models/cogito-v1-preview-llama-3b","deepcogito-cogito-1-3b-preview-llama","fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepcogito-cogito-1-3b-preview-llama","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.1,"min_output_per_1m":0.1,"max_output_per_1m":0.1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepcogito-cogito-1-70b-preview-llama","name":"cogito-1-70b-preview-llama","display_name":"Cogito V1 Preview Llama 70B","description":"A 70B-parameter hybrid reasoning LLM from Deep Cogito built on the Llama architecture, designed for complex multi-step reasoning and instruction-following.","creator":"deepcogito","family":"llama","tier":"","version":"1","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":true,"provider_count":1,"ids":["accounts/fireworks/models/cogito-v1-preview-llama-70b","deepcogito-cogito-1-70b-preview-llama","fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepcogito-cogito-1-70b-preview-llama","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.9,"max_input_per_1m":0.9,"min_output_per_1m":0.9,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepcogito-cogito-1-8b-preview-llama","name":"cogito-1-8b-preview-llama","display_name":"Cogito V1 Preview Llama 8B","description":"An 8B-parameter hybrid reasoning LLM from Deep Cogito built on the Llama architecture, combining efficient inference with strong reasoning capabilities.","creator":"deepcogito","family":"llama","tier":"","version":"1","type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":true,"provider_count":1,"ids":["accounts/fireworks/models/cogito-v1-preview-llama-8b","deepcogito-cogito-1-8b-preview-llama","fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-8b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepcogito-cogito-1-8b-preview-llama","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepcogito-cogito-1-14b-preview-qwen","name":"cogito-1-14b-preview-qwen","display_name":"Cogito V1 Preview Qwen 14B","description":"A 14B-parameter hybrid reasoning LLM from Deep Cogito built on the Qwen2 architecture, combining instruction-following with chain-of-thought reasoning.","creator":"deepcogito","family":"qwen2","tier":"","version":"1","type":"language","size_in_bn":14,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":true,"provider_count":1,"ids":["accounts/fireworks/models/cogito-v1-preview-qwen-14b","deepcogito-cogito-1-14b-preview-qwen","fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-14b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepcogito-cogito-1-14b-preview-qwen","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepcogito-cogito-1-32b-preview-qwen","name":"cogito-1-32b-preview-qwen","display_name":"Cogito V1 Preview Qwen 32B","description":"A 32B-parameter hybrid reasoning LLM from Deep Cogito built on the Qwen2 architecture, offering strong instruction-following and multi-step reasoning.","creator":"deepcogito","family":"qwen2","tier":"","version":"1","type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":true,"provider_count":1,"ids":["accounts/fireworks/models/cogito-v1-preview-qwen-32b","deepcogito-cogito-1-32b-preview-qwen","fireworks_ai/accounts/fireworks/models/cogito-v1-preview-qwen-32b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepcogito-cogito-1-32b-preview-qwen","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.9,"max_input_per_1m":0.9,"min_output_per_1m":0.9,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":true,"next_token":"NTA","total_count":183},"meta":{"updated_at":"2026-10-12","request_id":"83dee1d7-d952-4ad5-890f-3d776f142db5","execution_ms":18}}