{"object":"list","data":[{"id":"moonshotai/kimi-k3.1-pro","name":"moonshotai/kimi-k3.1-pro","object":"model","created":1793855475,"owned_by":"ai&","provider":"moonshotai","context_window":1048576,"max_output_tokens":131072,"capabilities":["chat","reasoning","vision","document","tool_calling"],"reasoning_efforts":["low","high","max"],"reasoning_effort_default":"high","description":"Kimi K3.1 Pro is Moonshot AI’s new high-performance open-weight model for advanced coding, reasoning, and intelligent agents. With native text and image understanding and a one-million-token context window, it helps tackle complex research, creative projects, and demanding multistep workflows.","currency":"usd","input_per_1m":"2.000000","output_per_1m":"10.000000","cached_input_per_1m":"0.200000","deprecation_date":null},{"id":"deepseek-ai/deepseek-v4.1-flash-1017","name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1793327162,"owned_by":"ai&","provider":"deepseek-ai","context_window":1048576,"max_output_tokens":384000,"capabilities":["chat","reasoning","vision","document","tool_calling"],"reasoning_efforts":["none","low","high","xhigh","max"],"reasoning_effort_default":"high","description":"DeepSeek V4.1 Flash (1017) for economical reasoning, coding and long-context work","currency":"usd","input_per_1m":"0.300000","output_per_1m":"0.600000","cached_input_per_1m":"0.020000","deprecation_date":null},{"id":"meta/muse-spark-open","name":"meta/muse-spark-open","object":"model","created":1793337365,"owned_by":"ai&","provider":"meta","context_window":1048576,"max_output_tokens":943718,"capabilities":["chat","reasoning","video","vision","tool_calling"],"reasoning_efforts":["low","medium","high","xhigh"],"reasoning_effort_default":"xhigh","description":"Meta's open multimodal model for agents, reasoning over text, images and video with 1M context","currency":"usd","input_per_1m":"1.250000","output_per_1m":"4.250000","cached_input_per_1m":"0.150000","deprecation_date":null},{"id":"zai-org/glm-5.3","name":"zai-org/glm-5.3","object":"model","created":1787960214,"owned_by":"ai&","provider":"zai-org","context_window":1048576,"max_output_tokens":131072,"capabilities":["reasoning","tool_calling"],"reasoning_efforts":["low","high","max"],"reasoning_effort_default":"max","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","currency":"usd","input_per_1m":"1.000000","output_per_1m":"4.000000","cached_input_per_1m":"0.300000","deprecation_date":null},{"id":"zai-org/glm-5.3-flash","name":"zai-org/glm-5.3-flash","object":"model","created":1790908926,"owned_by":"ai&","provider":"zai-org","context_window":1048550,"max_output_tokens":131072,"capabilities":["reasoning","tool_calling","vision","video","document","chat"],"reasoning_efforts":["low","high","max"],"reasoning_effort_default":"max","description":"Multimodal GLM model for coding and agents with a million-token context","currency":"usd","input_per_1m":"0.150000","output_per_1m":"0.500000","cached_input_per_1m":"0.030000","deprecation_date":null},{"id":"qwen/qwen3.8-27b","name":"qwen/qwen3.8-27b","object":"model","created":1787794591,"owned_by":"ai&","provider":"Qwen","context_window":262144,"max_output_tokens":32768,"capabilities":["reasoning","tool_calling","vision","video","document"],"reasoning_efforts":["none","low","medium","xhigh"],"reasoning_effort_default":"xhigh","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","currency":"usd","input_per_1m":"0.400000","output_per_1m":"3.000000","cached_input_per_1m":"0.200000","deprecation_date":null},{"id":"moonshotai/kimi-k3","name":"moonshotai/kimi-k3","object":"model","created":1785204108,"owned_by":"ai&","provider":"moonshotai","context_window":1048576,"max_output_tokens":131072,"capabilities":["reasoning","tool_calling","vision","document"],"reasoning_efforts":["low","high","max"],"reasoning_effort_default":"max","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","currency":"usd","input_per_1m":"3.000000","output_per_1m":"12.500000","cached_input_per_1m":"0.500000","deprecation_date":null},{"id":"google/gemma-4-31b-it","name":"google/gemma-4-31b-it","object":"model","created":1775474514,"owned_by":"ai&","provider":"google","context_window":262144,"max_output_tokens":32768,"capabilities":["reasoning","tool_calling","vision","video","document"],"reasoning_efforts":["none","high"],"reasoning_effort_default":"none","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","currency":"usd","input_per_1m":"0.200000","output_per_1m":"0.500000","cached_input_per_1m":"0.050000","deprecation_date":null},{"id":"motif-technologies/motif-3","name":"Motif-Technologies/Motif-3","object":"model","created":1786511501,"owned_by":"ai&","provider":"Motif-Technologies","context_window":262144,"max_output_tokens":262144,"capabilities":["chat","reasoning","tool_calling"],"reasoning_efforts":["none","high"],"reasoning_effort_default":"high","description":"Motif 3 is a large-scale, decoder-only Mixture-of-Experts (MoE) language model with 314 billion total parameters and 13.2 billion parameters activated per token.","currency":"usd","input_per_1m":"0.500000","output_per_1m":"2.000000","cached_input_per_1m":"0.200000","deprecation_date":null},{"id":"qwen/qwen3.6-27b","name":"qwen/qwen3.6-27b","object":"model","created":1780245077,"owned_by":"ai&","provider":"qwen","context_window":262144,"max_output_tokens":65536,"capabilities":["reasoning","tool_calling","vision","video","document"],"reasoning_efforts":["none","high"],"reasoning_effort_default":"high","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","currency":"usd","input_per_1m":"0.320000","output_per_1m":"3.200000","cached_input_per_1m":"0.200000","deprecation_date":null},{"id":"deepseek-ai/deepseek-v4-pro","name":"deepseek-ai/DeepSeek-V4-Pro","object":"model","created":1780245364,"owned_by":"ai&","provider":"deepseek-ai","context_window":1048576,"max_output_tokens":384000,"capabilities":["reasoning","tool_calling"],"reasoning_efforts":["none","high","max"],"reasoning_effort_default":"high","description":"Open MoE flagship with million-token context for coding and long agent runs","currency":"usd","input_per_1m":"1.000000","output_per_1m":"2.500000","cached_input_per_1m":"0.250000","deprecation_date":null},{"id":"openai/gpt-oss-120b","name":"openai/gpt-oss-120b","object":"model","created":1775474514,"owned_by":"ai&","provider":"openai","context_window":131072,"max_output_tokens":32768,"capabilities":["reasoning","tool_calling"],"reasoning_efforts":["low","medium","high"],"reasoning_effort_default":"medium","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","currency":"usd","input_per_1m":"0.150000","output_per_1m":"0.600000","cached_input_per_1m":"0.080000","deprecation_date":null}]}