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 (#10157)
github-actions[bot]959bddbde555
diff --git a/packages/llm-info/data/models.yml b/packages/llm-info/data/models.ymlindex 2c84fc0533..0a33127f64 100644--- a/packages/llm-info/data/models.yml+++ b/packages/llm-info/data/models.yml@@ -91,6 +91,46 @@ anthropic:cost: {input: 3, output: 15}openai:+ - name: GPT-5.6+ model: gpt-5.6+ description: "OpenAI's GPT-5.6 flagship tier for frontier reasoning, coding, and agentic workflows"+ roles: [chat, edit]+ capabilities: [thinking, tool_calling]+ input_types: [text, image, pdf]+ output_types: [text]+ release_date: 2026-07-09+ cost: {input: 5, output: 30}++ - name: GPT-5.6 Luna+ 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: 1, output: 6}++ - name: GPT-5.6 Sol+ model: gpt-5.6-sol+ description: "Flagship model in OpenAI's GPT-5.6 series, suited for complex reasoning, coding, and agentic workflows"+ roles: [chat, edit]+ capabilities: [thinking, tool_calling]+ input_types: [text, image, pdf]+ output_types: [text]+ release_date: 2026-07-09+ cost: {input: 5, output: 30}++ - name: GPT-5.6 Terra+ model: gpt-5.6-terra+ description: "Balanced model in OpenAI's GPT-5.6 series, suited for everyday coding, reasoning, and agentic workflows"+ roles: [chat, edit]+ capabilities: [thinking, tool_calling]+ input_types: [text, image, pdf]+ output_types: [text]+ release_date: 2026-07-09+ cost: {input: 2.5, output: 15}+- name: GPT-5.5model: gpt-5.5description: "OpenAI's frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks"@@ -240,6 +280,16 @@ bedrock:release_date: 2026-06-09cost: {input: 10, output: 50}+ - name: Claude Sonnet 5 (Global)+ model: global.anthropic.claude-sonnet-5+ description: "Anthropic's most agentic Sonnet model yet, built for planning, tool use, and autonomous multi-step work at Sonnet pricing"+ roles: [chat, edit]+ capabilities: [thinking, tool_calling]+ input_types: [text, image, pdf]+ output_types: [text]+ release_date: 2026-06-30+ cost: {input: 2, output: 10}+- name: Claude Sonnet 5model: anthropic.claude-sonnet-5description: "Anthropic's most agentic Sonnet model yet, built for planning, tool use, and autonomous multi-step work at Sonnet pricing"@@ -682,6 +732,16 @@ ollama:release_date: 2026-02-15wandb:+ - name: Granite 4.1 8B+ model: ibm-granite/granite-4.1-8b+ description: "Dense 8B decoder-only model from IBM's Granite 4.1 family with a 131K-token context window, designed for enterprise tasks"+ roles: [chat, edit]+ capabilities: [tool_calling]+ input_types: [text]+ output_types: [text]+ release_date: 2026-04-29+ cost: {input: 0.05, output: 0.1}+- name: DeepSeek V4-Flashmodel: deepseek-ai/DeepSeek-V4-Flashdescription: "DeepSeek V4-Flash is an MoE model with 1M context length great for coding, reasoning, and agentic workloads"@@ -722,6 +782,16 @@ wandb:release_date: 2026-04-07cost: {input: 1.4, output: 4.4}+ - name: Nemotron 3 Ultra+ model: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B+ description: "Open frontier-reasoning and orchestration model from NVIDIA with 55B active parameters out of 550B total (MoE)"+ roles: [chat, edit]+ capabilities: [thinking, tool_calling]+ input_types: [text]+ output_types: [text]+ release_date: 2026-06-04+ cost: {input: 0.75, output: 2.75}+- name: NVIDIA Nemotron 3 Super 120Bmodel: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8description: "120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications"