A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
Python artificial-intelligencedagdata-sciencedata-visualizationdataflowdeveloper-toolsmachine-learningnotebookspipelinepythonreactivesqlweb-app
Update LLM model catalog (#10440)
github-actions[bot]f48b070f93d1
diff --git a/docs/guides/configuration/llm_providers.md b/docs/guides/configuration/llm_providers.mdindex aa8939c9bd..40283c2035 100644--- a/docs/guides/configuration/llm_providers.md+++ b/docs/guides/configuration/llm_providers.md@@ -319,7 +319,7 @@ Access curated open coding models tested and benchmarked for coding agents throu[ai.models]# Use opencode-go/ prefix for OpenCode Go models. Examples:chat_model = "opencode-go/kimi-k2.6"-edit_model = "opencode-go/qwen3.6-plus"+edit_model = "opencode-go/qwen3.7-plus"[ai.opencode_go]api_key = "your-opencode-api-key"diff --git a/packages/llm-info/data/models.yml b/packages/llm-info/data/models.ymlindex 7b2849c32d..a07ee049e7 100644--- a/packages/llm-info/data/models.yml+++ b/packages/llm-info/data/models.yml@@ -911,6 +911,16 @@ ollama:release_date: 2026-02-15wandb:+ - name: Kimi K3+ model: moonshotai/Kimi-K3+ description: "Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model for complex coding, knowledge work, and long-horizon agentic workflows"+ roles: [chat, edit]+ capabilities: [thinking, tool_calling]+ input_types: [text, image]+ output_types: [text]+ release_date: 2026-07-16+ cost: {input: 3, output: 15}+- name: MiniMax M3model: MiniMaxAI/MiniMax-M3description: "Multimodal foundation model from MiniMax with a 1M-token context window, suited for long-horizon agentic work and coding"@@ -1072,6 +1082,26 @@ wandb:cost: {input: 0.05, output: 0.1}opencode-go:+ - name: Qwen3.8 Max+ model: qwen3.8-max+ description: "Flagship multimodal reasoning model in Alibaba's Qwen3.8 series, intended for complex reasoning, visual understanding, and agentic workflows"+ roles: [chat, edit]+ capabilities: [thinking, tool_calling]+ input_types: [text, image]+ output_types: [text]+ release_date: 2026-08-03+ cost: {input: 2, output: 6}++ - name: GPT-5.6 Luna (2x usage)+ model: gpt-5.6-luna+ description: "Fast, cost-efficient model in OpenAI's GPT-5.6 series, suited for high-volume, latency-sensitive chat and lightweight agentic workflows"+ roles: [chat, edit]+ capabilities: [thinking, tool_calling]+ input_types: [text, image, pdf]+ output_types: [text]+ release_date: 2026-07-09+ cost: {input: 0.1, output: 0.6}+- name: Kimi K3 (2x usage)model: kimi-k3description: "Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model for complex coding, knowledge work, and long-horizon agentic workflows"@@ -1182,16 +1212,6 @@ opencode-go:release_date: 2026-05-21cost: {input: 2.5, output: 7.5}- - name: Qwen3.6 Plus- model: qwen3.6-plus- description: "Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference"- roles: [chat, edit]- capabilities: [thinking, tool_calling]- input_types: [text, image]- output_types: [text]- release_date: 2026-04-02- cost: {input: 0.5, output: 3}-- name: MiniMax M3 (3x usage)model: minimax-m3description: "Multimodal foundation model from MiniMax with a 1M-token context window, suited for long-horizon agentic work and coding"