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.

Update and curate LLM model catalog (#11468)

github-actions[bot]8d972fdfcd22
diff --git a/packages/llm-info/data/models.yml b/packages/llm-info/data/models.yml
index a1a94391b5..d89c190601 100644
--- a/packages/llm-info/data/models.yml
+++ b/packages/llm-info/data/models.yml
@@ -736,35 +736,6 @@ bedrock:
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- - name: Claude Fable 5 (Global)
- model: global.anthropic.claude-fable-5
- description: "Anthropic's Mythos-class model built for demanding reasoning, coding, and long-horizon agentic work"
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image, pdf]
- output_types: [text]
- release_date: 2026-06-09
- cost: {input: 10, output: 50}
- reasoning_options:
- - type: effort
- values: [low, medium, high, xhigh, max]
- limits: {context: 1000000, output: 128000}
-
- - name: Claude Sonnet 5 (Global)
- model: global.anthropic.claude-sonnet-5
- description: "Anthropic's Sonnet model, 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}
- reasoning_options:
- - type: toggle
- - type: effort
- values: [low, medium, high, xhigh, max]
- limits: {context: 1000000, output: 128000}
-
- name: Claude Opus 4.8 (Global)
model: global.anthropic.claude-opus-4-8
description: "Modest but tangible improvement over Claude Opus 4.7"
@@ -933,7 +904,7 @@ azure:
cost: {input: 10, output: 50}
reasoning_options:
- type: effort
- values: [low, medium, high, xhigh, max]
+ values: [low, medium, high, xhigh]
limits: {context: 1000000, output: 128000}
- name: Grok 4.6
@@ -1017,7 +988,7 @@ azure:
cost: {input: 5, output: 30}
reasoning_options:
- type: effort
- values: [low, medium, high]
+ values: [medium]
limits: {context: 400000, output: 128000}
- name: Claude Fable 5
@@ -1031,7 +1002,7 @@ azure:
cost: {input: 10, output: 50}
reasoning_options:
- type: effort
- values: [low, medium, high, xhigh, max]
+ values: [low, medium, high, xhigh]
limits: {context: 1000000, output: 128000}
- name: Claude Sonnet 5
@@ -1120,27 +1091,58 @@ azure:
model: deepseek-v4-flash
description: "Efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window"
roles: [chat, edit]
- capabilities: [thinking]
+ capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-04-24
cost: {input: 0.19, output: 0.51}
- reasoning_options: []
+ reasoning_options:
+ - type: effort
+ values: [none, low, high, max]
limits: {context: 1000000, output: 384000}
- name: DeepSeek-V4-Pro
model: deepseek-v4-pro
description: "Large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window"
roles: [chat, edit]
- capabilities: [thinking]
+ capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-04-24
cost: {input: 1.74, output: 3.48}
- reasoning_options: []
+ reasoning_options:
+ - type: effort
+ values: [none, low, high, max]
limits: {context: 1000000, output: 384000}
ollama:
+ - name: MiniMax-M3.1-Flash
+ model: minimax-m3.1-flash
+ description: "Multimodal model from MiniMax for coding, computer use, and complex multi-step agent workflows"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text, image]
+ output_types: [text]
+ release_date: 2026-10-19
+ cost: {input: 0.15, output: 0.6}
+ reasoning_options:
+ - type: effort
+ values: [low, medium, high, xhigh, max]
+ limits: {context: 1000000, output: 512000}
+
+ - name: Beam 1.0 501B A23B
+ model: beam
+ description: "Open-weight reasoning model from Reflection for coding and long-running agent workflows, with 501B total and 23B active parameters"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text]
+ output_types: [text]
+ release_date: 2026-10-05
+ reasoning_options:
+ - type: effort
+ values: [low, medium, high, xhigh, max]
+ limits: {context: 1048576, output: 131072}
+
- name: DeepSeek V4.1 Flash 1017
model: deepseek-v4.1-flash:1017
description: "October 17 update of DeepSeek V4.1 Flash for coding and end-to-end project development, with faster task completion and shorter outputs"
@@ -1166,8 +1168,9 @@ ollama:
release_date: 2026-10-15
cost: {input: 1.25, output: 4.25}
reasoning_options:
+ - type: toggle
- type: effort
- values: [low, medium, high, xhigh]
+ values: [low, medium, high, max]
limits: {context: 1048576, output: 131072}
- name: Mistral Large 4
@@ -1178,7 +1181,7 @@ ollama:
input_types: [text, image]
output_types: [text]
release_date: 2026-10-06
- cost: {input: 1.36, output: 4.18}
+ cost: {input: 0.68, output: 2.09}
reasoning_options:
- type: effort
values: [none, high]
@@ -1206,11 +1209,11 @@ ollama:
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
- release_date: 2026-08-12
+ release_date: 2026-08-13
reasoning_options:
- type: toggle
- type: effort
- values: [high, max]
+ values: [low, high, max]
limits: {context: 1048576, output: 1048576}
cost: {input: 0.66, output: 1.98}
@@ -1219,7 +1222,7 @@ ollama:
description: "Native multimodal model from Z.ai optimized for efficient coding and long-horizon agent tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
- input_types: [text, image, pdf]
+ input_types: [text, image]
output_types: [text]
release_date: 2026-08-26
reasoning_options:
@@ -1298,7 +1301,7 @@ ollama:
reasoning_options:
- type: toggle
- type: effort
- values: [high, max]
+ values: [low, high, max]
limits: {context: 1048576, output: 1048576}
cost: {input: 0.66, output: 1.98}
@@ -1324,6 +1327,7 @@ ollama:
output_types: [text]
release_date: 2026-06-13
reasoning_options:
+ - type: toggle
- type: effort
values: [high, max]
limits: {context: 976000, output: 131072}
@@ -1336,7 +1340,7 @@ ollama:
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
- release_date: 2026-05-31
+ release_date: 2026-06-01
reasoning_options:
- type: toggle
- type: effort
@@ -1352,8 +1356,7 @@ ollama:
input_types: [text]
output_types: [text]
release_date: 2026-03-18
- reasoning_options:
- - type: toggle
+ reasoning_options: []
limits: {context: 196608, output: 196608}
cost: {input: 0.3, output: 1.2}
@@ -1404,8 +1407,8 @@ wandb:
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
- release_date: 2026-10-16
- cost: {input: 1, output: 3}
+ release_date: 2026-10-05
+ cost: {input: 0.3, output: 1}
reasoning_options:
- type: effort
values: [minimal, low, medium, high, xhigh, max]
@@ -1456,7 +1459,7 @@ wandb:
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
- release_date: 2026-08-24
+ release_date: 2026-08-25
cost: {input: 0.1, output: 0.15}
reasoning_options:
- type: toggle
@@ -1521,7 +1524,7 @@ wandb:
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
- release_date: 2026-06-12
+ release_date: 2026-06-01
cost: {input: 0.23, output: 0.96}
reasoning_options: []
limits: {context: 262144, output: 262144}
@@ -1559,7 +1562,7 @@ wandb:
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
- release_date: 2026-06-16
+ release_date: 2026-06-13
cost: {input: 0.62, output: 2.42}
reasoning_options:
- type: toggle
@@ -1624,6 +1627,48 @@ wandb:
limits: {context: 131072, output: 131072}
opencode-go:
+ - name: Kimi K3.1 Pro
+ model: kimi-k3.1-pro
+ description: "Open-weight multimodal reasoning model from Moonshot AI for long-horizon coding, financial research, and agentic knowledge work"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text, image]
+ output_types: [text]
+ release_date: 2026-10-23
+ cost: {input: 2, output: 10}
+ reasoning_options:
+ - type: effort
+ values: [low, high, max]
+ limits: {context: 1048576, output: 131072}
+
+ - name: MiniMax M3.1 Flash
+ model: minimax-m3.1-flash
+ description: "Multimodal model from MiniMax for coding, computer use, and complex multi-step agent workflows"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text, image]
+ output_types: [text]
+ release_date: 2026-10-19
+ cost: {input: 0.15, output: 0.6}
+ reasoning_options:
+ - type: effort
+ values: [low, medium, high, xhigh, max]
+ limits: {context: 1000000, output: 512000}
+
+ - name: Gemini 4 Argon
+ model: gemini-4-argon
+ description: "Reasoning model for complex software engineering, mathematical and scientific problem solving, and autonomous multi-step agents"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text, image, pdf]
+ output_types: [text]
+ release_date: 2026-10-13
+ cost: {input: 2, output: 10}
+ reasoning_options:
+ - type: effort
+ values: [low, medium, high]
+ limits: {context: 1048576, output: 65536}
+
- name: Beam Free
model: beam-free
description: "Free access to Reflection's Beam model for coding, reasoning, and long-running agent workflows, available for a limited time in supported regions"
@@ -1779,7 +1824,7 @@ opencode-go:
description: "Native multimodal model from Z.ai optimized for efficient coding and long-horizon agent tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
- input_types: [text, image, pdf]
+ input_types: [text, image]
output_types: [text]
release_date: 2026-08-26
cost: {input: 0.15, output: 0.5}
@@ -1957,7 +2002,7 @@ opencode-go:
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
- release_date: 2026-05-31
+ release_date: 2026-06-01
cost: {input: 0.3, output: 1.2}
reasoning_options:
- type: toggle