Skip to content

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

feat(providers): add glm-5.2, kimi-k2.7-code, qwen3.7-plus to model catalogs

Sergey Kozyrenko2d8bce7ccb27
diff --git a/backend/pkg/providers/glm/models.yml b/backend/pkg/providers/glm/models.yml
index 76626eab..3f48963c 100644
--- a/backend/pkg/providers/glm/models.yml
+++ b/backend/pkg/providers/glm/models.yml
@@ -1,4 +1,12 @@
# GLM-5.x Series - Latest generation (200K context, 128K max output, hybrid thinking)
+- name: glm-5.2
+ description: GLM-5.2 - Newest flagship (improves on GLM-5.1), 200K context, hybrid thinking; the only GLM model that honors reasoning_effort (high/max).
+ thinking: true
+ price:
+ input: 1.40
+ output: 4.40
+ cache_read: 0.26
+
- name: glm-5.1
description: GLM-5.1 - Latest flagship designed for long-horizon tasks (8h sustained autonomous execution), Claude Opus 4.6-aligned coding, 200K context, hybrid thinking. Best for planning, mentor, and complex agentic engineering
thinking: true
diff --git a/backend/pkg/providers/kimi/models.yml b/backend/pkg/providers/kimi/models.yml
index b18d33e3..62f0ba9a 100644
--- a/backend/pkg/providers/kimi/models.yml
+++ b/backend/pkg/providers/kimi/models.yml
@@ -1,3 +1,12 @@
+# Kimi K2.7 Code - Code-specialized flagship model
+- name: kimi-k2.7-code
+ description: Kimi K2.7 Code - Code-specialist variant of K2.7 with native architecture. Stronger code generation and long-term reasoning than K2.6; supports thinking/non-thinking modes, 256k context, automatic context caching, ToolCalls, JSON Mode
+ thinking: true
+ price:
+ input: 1.20
+ output: 5.00
+ cache_read: 0.20
+
# Kimi K2.6 - Latest flagship multimodal model with native architecture
- name: kimi-k2.6
description: Kimi K2.6 - Latest and most intelligent multimodal model with native architecture, stronger long-term code writing, improved instruction compliance and self-correction. Supports text/image/video input, thinking/non-thinking modes, 256k context, automatic context caching, ToolCalls, JSON Mode, internet search
diff --git a/backend/pkg/providers/qwen/models.yml b/backend/pkg/providers/qwen/models.yml
index 6771f9d7..3162cf59 100644
--- a/backend/pkg/providers/qwen/models.yml
+++ b/backend/pkg/providers/qwen/models.yml
@@ -1,4 +1,13 @@
-# Qwen3.7 Series - Latest flagship Max (May 2026)
+# Qwen3.7 Series - Latest generation (May 2026)
+- name: qwen3.7-plus
+ description: Qwen3.7 Plus - Cost-efficient tier of the Qwen3.7 generation for the agent-centric era. Better cost-to-intelligence ratio than qwen3.7-max; supports hybrid thinking, long-horizon autonomous execution, and complex security reasoning workflows
+ thinking: true
+ release_date: 2026-05-21
+ price:
+ input: 1.0
+ output: 3.5
+ cache_read: 0.1
+
- name: qwen3.7-max
description: Qwen3.7 Max - Next-generation flagship designed for the agent-centric era with excellence in programming, productivity tasks, and long-term autonomous execution. Pure-text interface optimal for sophisticated penetration testing automation and complex agentic security workflows
thinking: true