Skip to content

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.

Backfill DeepSeek V4 Flash 0731 entries in llm-info catalog (#10462)

Shahmir Varqhadeff2a2f8115
diff --git a/packages/llm-info/data/models.yml b/packages/llm-info/data/models.yml
index a07ee049e7..c7a1a6c801 100644
--- a/packages/llm-info/data/models.yml
+++ b/packages/llm-info/data/models.yml
@@ -793,6 +793,15 @@ github:
cost: {input: 0, output: 0}
ollama:
+ - name: DeepSeek V4 Flash 0731
+ model: deepseek-v4-flash:0731
+ description: "DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text]
+ output_types: [text]
+ release_date: 2026-07-31
+
- name: kimi-k3
model: kimi-k3
description: "Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model for complex coding, knowledge work, and long-horizon agentic workflows"
@@ -911,6 +920,16 @@ ollama:
release_date: 2026-02-15
wandb:
+ - name: DeepSeek V4 Flash 0731
+ model: deepseek-ai/DeepSeek-V4-Flash-0731
+ description: "DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text]
+ output_types: [text]
+ release_date: 2026-07-31
+ cost: {input: 0.13, output: 0.28}
+
- 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"