{"umans-kimi-k2.7":{"name":"umans-kimi-k2.7","display_name":"Umans Kimi K2.7 Code","description":"Kimi K2.7-Code via Umans Code - Moonshot's strongest coding model and the successor to Kimi K2.6. Built for complex, tool-heavy agentic coding; it reasons more efficiently than K2.6, so agent sessions run faster at the same depth.","base_model":{"name":"kimi-k2.7-code","provider":"Moonshot","oss_base":"Kimi K2.7-Code"},"capabilities":{"max_completion_tokens":262144,"recommended_max_tokens":32768,"context_window":262144,"supports_vision":true,"supports_tools":true,"reasoning":{"supported":true,"can_disable":false,"levels":[],"default_level":null}},"benchmarks":{}},"umans-glm-5.2":{"name":"umans-glm-5.2","display_name":"Umans GLM 5.2","description":"GLM 5.2 with composite vision capabilities. Text generation via GLM 5.2 and image preprocessing via Kimi. Vision works only on the Anthropic Messages API (`/v1/messages`) via a server-side handoff; it will be retired soon in favour of more efficient client-side image handling.","base_model":{"name":"GLM-5.2","family":"GLM"},"capabilities":{"max_completion_tokens":131072,"recommended_max_tokens":131071,"context_window":405504,"supports_vision":"via-handoff","supports_tools":true,"reasoning":{"supported":true,"can_disable":true,"levels":["none","high","max"],"default_level":"high"}},"benchmarks":{}},"umans-coder":{"name":"umans-coder","display_name":"Umans Coder","description":"Our recommended model for complex, coding-heavy workloads. Optimized for the best experience with coding agents like Claude Code.","base_model":{"name":"kimi-k2.7-code","provider":"Moonshot","oss_base":"Kimi K2.7-Code"},"capabilities":{"max_completion_tokens":262144,"recommended_max_tokens":32768,"context_window":262144,"supports_vision":true,"supports_tools":true,"reasoning":{"supported":true,"can_disable":false,"levels":[],"default_level":null}},"benchmarks":{}},"umans-glm-5.2-nvfp4":{"name":"umans-glm-5.2-nvfp4","display_name":"Umans GLM 5.2 NVFP4 (experimental, short test from Jun 29)","stage":"playground","lifecycle":{"playground_start_date":"2026-06-29"},"description":"Experimental NVFP4-quantized build of GLM 5.2, open for a short test window starting June 29, 2026 — temporary, not a permanent model. It isn't reachable before then: selecting it earlier returns errors (HTTP 500), so come back on the 29th. During the window — the published NVFP4 results look very flattering, but we're skeptical of its real quality and performance: this checkpoint was NOT QAT post-trained for NVFP4 (the QAT-on-NVFP4 models are where we've seen the best quality), so treat the benchmarks with caution. Play with it, push it, and see how far it gets you — for production work we recommend the fp8 `umans-glm-5.2`. It's offered at low capacity and low availability, so expect it to be flaky and to go down under load: crash it, give it a moment, and try again.","base_model":{"name":"GLM-5.2","family":"GLM"},"capabilities":{"max_completion_tokens":131072,"recommended_max_tokens":131071,"context_window":405504,"supports_vision":false,"supports_tools":true,"reasoning":{"supported":true,"can_disable":true,"levels":["none","high","max"],"default_level":"high"}},"benchmarks":{}},"umans-flash":{"name":"umans-flash","display_name":"Umans Flash","description":"Our fastest model for coding-agent workloads. Optimized for low-latency iteration with tools and coding assistants like Claude Code.","base_model":{"name":"Qwen3.6-35B-A3B","provider":"Qwen","oss_base":"Qwen3.6-35B-A3B"},"capabilities":{"max_completion_tokens":262144,"recommended_max_tokens":32768,"context_window":262144,"supports_vision":true,"supports_tools":true,"reasoning":{"supported":true,"can_disable":true,"levels":["none","low","medium","high"],"default_level":"medium"}},"benchmarks":{}},"umans-qwen3.6-35b-a3b":{"name":"umans-qwen3.6-35b-a3b","display_name":"Umans Qwen3.6 35B A3B","description":"Technical alias for `umans-flash`. Use `umans-flash` for the recommended fast coding-agent experience.","base_model":{"name":"Qwen3.6-35B-A3B","provider":"Qwen","oss_base":"Qwen3.6-35B-A3B"},"capabilities":{"max_completion_tokens":262144,"recommended_max_tokens":32768,"context_window":262144,"supports_vision":true,"supports_tools":true,"reasoning":{"supported":true,"can_disable":true,"levels":["none","low","medium","high"],"default_level":"medium"}},"benchmarks":{}}}