{"data":[{"id":"mercury-edit-2","name":"Inception: Mercury Edit 2","created":1743465660,"input_modalities":["text"],"output_modalities":["text"],"context_length":128000,"max_output_length":32000,"pricing":{"prompt":"0.00000025","completion":"0.00000075","image":"0","request":"0","input_cache_reads":"0.000000025","input_cache_writes":"0"},"supported_sampling_parameters":["temperature","stop"],"supported_features":[],"description":"Mercury Edit 2 is a diffusion large language model (dLLM) for code editing. Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku and GPT-4o Mini while matching their performance.","openrouter":{"slug":"inception/mercury-edit-2"},"datacenters":[{"country_code":"US"}]},{"id":"mercury","name":"Inception: Mercury","created":1743465660,"input_modalities":["text"],"output_modalities":["text"],"context_length":128000,"max_output_length":32000,"pricing":{"prompt":"0.00000025","completion":"0.00000075","image":"0","request":"0","input_cache_reads":"0.000000025","input_cache_writes":"0"},"supported_sampling_parameters":["temperature","stop"],"supported_features":["tools","json_mode","structured_outputs"],"description":"Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude 3.5 Haiku while matching their performance. Mercury's speed enables developers to provide responsive user experiences, including with voice agents, search interfaces, and chatbots.","openrouter":{"slug":"inception/mercury"},"datacenters":[{"country_code":"US"}]},{"id":"mercury-coder","name":"Inception: Mercury Coder","created":1743465660,"input_modalities":["text"],"output_modalities":["text"],"context_length":128000,"max_output_length":32000,"pricing":{"prompt":"0.00000025","completion":"0.00000075","image":"0","request":"0","input_cache_reads":"0.000000025","input_cache_writes":"0"},"supported_sampling_parameters":["temperature","stop"],"supported_features":["tools","json_mode","structured_outputs"],"description":"Mercury Coder is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku and GPT-4o Mini while matching their performance. Mercury Coder's speed means that developers can stay in the flow while coding, enjoying rapid chat-based iteration and responsive code completion suggestions. On Copilot Arena, Mercury Coder ranks 1st in speed and ties for 2nd in quality.","openrouter":{"slug":"inception/mercury-coder"},"datacenters":[{"country_code":"US"}]},{"id":"mercury-edit","name":"Inception: Mercury Edit","created":1743465660,"input_modalities":["text"],"output_modalities":["text"],"context_length":128000,"max_output_length":32000,"pricing":{"prompt":"0.00000025","completion":"0.00000075","image":"0","request":"0","input_cache_reads":"0.000000025","input_cache_writes":"0"},"supported_sampling_parameters":["temperature","stop"],"supported_features":[],"description":"Mercury Edit is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku and GPT-4o Mini while matching their performance. Mercury Edit's speed means that developers can stay in the flow while coding, enjoying rapid chat-based iteration and responsive code completion suggestions. On Copilot Arena, Mercury Edit ranks 1st in speed and ties for 2nd in quality.","openrouter":{"slug":"inception/mercury-edit"},"datacenters":[{"country_code":"US"}]},{"id":"mercury-2","name":"Inception: Mercury 2","created":1743465660,"input_modalities":["text"],"output_modalities":["text"],"context_length":128000,"max_output_length":50000,"pricing":{"prompt":"0.00000025","completion":"0.00000075","image":"0","request":"0","input_cache_reads":"0.000000025","input_cache_writes":"0"},"supported_sampling_parameters":["temperature","stop"],"supported_features":["tools","json_mode","structured_outputs"],"description":"Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku and GPT-4o Mini while matching their performance. Mercury's speed means that users can stay in the flow, enjoying rapid chat-based iteration and responsive completion suggestions. On Copilot Arena, Mercury ranks 1st in speed and ties for 2nd in quality.","openrouter":{"slug":"inception/mercury-2"},"datacenters":[{"country_code":"US"}]}]}