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.

fix(ai): remove unavailable models (#10025)

Shahmir Varqha31015fd37451
diff --git a/packages/llm-info/data/models.yml b/packages/llm-info/data/models.yml
index cbe2753acb..36fd33acf5 100644
--- a/packages/llm-info/data/models.yml
+++ b/packages/llm-info/data/models.yml
@@ -1,15 +1,5 @@
anthropic:
- - name: Claude Fable 5
- model: claude-fable-5
- description: ""
- 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}
-
- name: Claude Opus 4.8
model: claude-opus-4-8
description: "Modest but tangible improvement over Claude Opus 4.7"
@@ -81,16 +71,6 @@ anthropic:
cost: {input: 3, output: 15}
openai:
- - name: gpt-image-2
- model: gpt-image-2
- description: ""
- roles: [chat, edit]
- capabilities: []
- input_types: [text, image]
- output_types: [image]
- release_date: 2026-04-21
- cost: {input: 5, output: 30}
-
- name: GPT-5.5
model: gpt-5.5
description: "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"
@@ -161,26 +141,6 @@ openai:
release_date: 2025-12-16
google:
- - name: Claude Opus 4.8
- model: claude-opus-4-8@default
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image, pdf]
- output_types: [text]
- release_date: 2026-05-28
- cost: {input: 5, output: 25}
-
- - name: Claude Opus 4.7
- model: claude-opus-4-7@default
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image, pdf]
- output_types: [text]
- release_date: 2026-04-16
- cost: {input: 5, output: 25}
-
- name: Gemini 3.5 Flash
model: gemini-3.5-flash
description: "Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed"
@@ -250,57 +210,6 @@ google:
cost: {input: 2, output: 12}
bedrock:
-
- - name: Claude Fable 5 (EU)
- model: eu.anthropic.claude-fable-5
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image]
- output_types: [text]
- release_date: 2026-06-09
- cost: {input: 11, output: 55}
-
- - name: Claude Fable 5 (Global)
- model: global.anthropic.claude-fable-5
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image]
- output_types: [text]
- release_date: 2026-06-09
- cost: {input: 10, output: 50}
-
- - name: Claude Fable 5 (US)
- model: us.anthropic.claude-fable-5
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image]
- output_types: [text]
- release_date: 2026-06-09
- cost: {input: 10, output: 50}
-
- - name: Claude Opus 4.8
- model: anthropic.claude-opus-4-8
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image, pdf]
- output_types: [text]
- release_date: 2026-05-28
- cost: {input: 5, output: 25}
-
- - name: Claude Opus 4.8 (AU)
- model: au.anthropic.claude-opus-4-8
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image, pdf]
- output_types: [text]
- release_date: 2026-05-28
- cost: {input: 5, output: 25}
-
- name: Claude Opus 4.8 (Global)
model: global.anthropic.claude-opus-4-8
description: "Modest but tangible improvement over Claude Opus 4.7"
@@ -372,46 +281,6 @@ bedrock:
cost: {input: 3, output: 15}
azure:
- - name: Claude Fable 5
- model: claude-fable-5
- description: ""
- 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}
-
- - name: Claude Opus 4.8
- model: claude-opus-4-8
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image, pdf]
- output_types: [text]
- release_date: 2026-05-28
- cost: {input: 5, output: 25}
-
- - name: DeepSeek-V4-Flash
- model: deepseek-v4-flash
- description: ""
- roles: [chat, edit]
- capabilities: [thinking]
- input_types: [text]
- output_types: [text]
- release_date: 2026-04-24
- cost: {input: 0.19, output: 0.51}
-
- - name: DeepSeek-V4-Pro
- model: deepseek-v4-pro
- description: ""
- roles: [chat, edit]
- capabilities: [thinking]
- input_types: [text]
- output_types: [text]
- release_date: 2026-04-24
- cost: {input: 1.74, output: 3.48}
-
- name: GPT-5.5
model: gpt-5.5
description: "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"
@@ -502,9 +371,19 @@ azure:
release_date: 2026-02-24
cost: {input: 1.75, output: 14}
+ - name: Claude Opus 4.8
+ model: claude-opus-4-8
+ description: "Modest but tangible improvement over Claude Opus 4.7"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text, image, pdf]
+ output_types: [text]
+ release_date: 2026-05-28
+ cost: {input: 5, output: 25}
+
- name: Claude Sonnet 4.6
model: claude-sonnet-4-6
- description: ""
+ description: "Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
@@ -512,6 +391,26 @@ azure:
release_date: 2026-02-17
cost: {input: 3, output: 15}
+ - name: DeepSeek-V4-Flash
+ 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]
+ input_types: [text]
+ output_types: [text]
+ release_date: 2026-04-24
+ cost: {input: 0.19, output: 0.51}
+
+ - 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]
+ input_types: [text]
+ output_types: [text]
+ release_date: 2026-04-24
+ cost: {input: 1.74, output: 3.48}
+
github:
- name: DeepSeek-R1-0528
model: deepseek/deepseek-r1-0528
@@ -614,42 +513,6 @@ github:
cost: {input: 0, output: 0}
ollama:
- - name: GLM-5.2
- model: glm-5.2
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text]
- output_types: [text]
- release_date: 2026-06-13
-
- - name: kimi-k2.7-code
- model: kimi-k2.7-code
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image]
- output_types: [text]
- release_date: 2026-06-12
-
- - name: nemotron-3-ultra
- model: nemotron-3-ultra
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text]
- output_types: [text]
- release_date: 2026-06-04
-
- - name: minimax-m3
- model: minimax-m3
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image]
- output_types: [text]
- release_date: 2026-05-31
-
- name: DeepSeek V4 Flash
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"
@@ -668,6 +531,15 @@ ollama:
output_types: [text]
release_date: 2026-04-24
+ - name: Kimi K2.7 Code
+ model: kimi-k2.7-code
+ description: "Coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text, image]
+ output_types: [text]
+ release_date: 2026-06-12
+
- name: Kimi K2.6
model: kimi-k2.6
description: "Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration"
@@ -686,6 +558,15 @@ ollama:
output_types: [text]
release_date: 2026-04-02
+ - name: GLM 5.2
+ model: glm-5.2
+ description: "Large-scale reasoning model from Z.ai with a 1M-token context window, suited for long-horizon agent workflows and project-level software engineering"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text]
+ output_types: [text]
+ release_date: 2026-06-13
+
- name: GLM 5.1
model: glm-5.1
description: "GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks"
@@ -695,6 +576,15 @@ ollama:
output_types: [text]
release_date: 2026-03-27
+ - name: MiniMax M3
+ model: minimax-m3
+ description: "Multimodal foundation model from MiniMax with a 1M-token context window, suited for long-horizon agentic work and coding"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text, image]
+ output_types: [text]
+ release_date: 2026-05-31
+
- name: MiniMax M2.7
model: minimax-m2.7
description: "Next-generation large language model designed for autonomous, real-world productivity and continuous improvement"
@@ -704,6 +594,15 @@ ollama:
output_types: [text]
release_date: 2026-03-18
+ - name: NVIDIA Nemotron 3 Ultra
+ model: nemotron-3-ultra
+ 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
+
- name: NVIDIA Nemotron 3 Super 120B
model: nemotron-3-super
description: "120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications"
@@ -722,24 +621,6 @@ ollama:
output_types: [text]
release_date: 2026-02-15
- - name: MiniMax M2.5
- model: minimax-m2.5
- description: "SOTA large language model designed for real-world productivity"
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text]
- output_types: [text]
- release_date: 2026-02-12
-
- - name: GLM 5
- model: glm-5
- description: "Z.ai's flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows"
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text]
- output_types: [text]
- release_date: 2026-02-11
-
wandb:
- name: GLM-5.1
model: zai-org/GLM-5.1
@@ -842,57 +723,6 @@ wandb:
cost: {input: 0.1, output: 0.1}
opencode-go:
-
- - name: GLM-5.2
- model: glm-5.2
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text]
- output_types: [text]
- release_date: 2026-06-13
- cost: {input: 1.4, output: 4.4}
-
- - name: Kimi K2.7 Code
- model: kimi-k2.7-code
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image]
- output_types: [text]
- release_date: 2026-06-12
- cost: {input: 0.95, output: 4}
-
- - name: Qwen3.7 Plus
- model: qwen3.7-plus
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image]
- output_types: [text]
- release_date: 2026-06-02
- cost: {input: 0.4, output: 1.6}
-
- - name: MiniMax M3 (3x usage)
- model: minimax-m3
- description: ""
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text, image]
- output_types: [text]
- release_date: 2026-05-31
- cost: {input: 0.1, output: 0.4}
-
- - name: Qwen3.7 Max
- model: qwen3.7-max
- description: "Capable of writing and debugging code, and sustaining autonomous execution across hundreds or thousands of steps"
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text]
- output_types: [text]
- release_date: 2026-05-21
- cost: {input: 2.5, output: 7.5}
-
- name: DeepSeek V4 Flash
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"
@@ -913,25 +743,15 @@ opencode-go:
release_date: 2026-04-24
cost: {input: 1.74, output: 3.48}
- - name: MiMo V2.5
- model: mimo-v2.5
- description: "Native omnimodal model from Xiaomi delivering Pro-level agentic performance at roughly half the inference cost"
+ - name: Kimi K2.7 Code
+ model: kimi-k2.7-code
+ description: "Coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
- release_date: 2026-04-22
- cost: {input: 0.4, output: 2}
-
- - name: MiMo V2.5 Pro
- model: mimo-v2.5-pro
- description: "Xiaomi's flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal,…"
- roles: [chat, edit]
- capabilities: [thinking, tool_calling]
- input_types: [text]
- output_types: [text]
- release_date: 2026-04-22
- cost: {input: 1, output: 3}
+ release_date: 2026-06-12
+ cost: {input: 0.95, output: 4}
- name: Kimi K2.6
model: kimi-k2.6
@@ -943,6 +763,16 @@ opencode-go:
release_date: 2026-04-21
cost: {input: 0.95, output: 4}
+ - name: GLM 5.2
+ model: glm-5.2
+ description: "Large-scale reasoning model from Z.ai with a 1M-token context window, suited for long-horizon agent workflows and project-level software engineering"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text]
+ output_types: [text]
+ release_date: 2026-06-13
+ cost: {input: 1.4, output: 4.4}
+
- name: GLM-5.1
model: glm-5.1
description: "GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks"
@@ -953,6 +783,26 @@ opencode-go:
release_date: 2026-04-07
cost: {input: 1.4, output: 4.4}
+ - name: Qwen3.7 Plus
+ model: qwen3.7-plus
+ description: "Cost-effective model in Alibaba's Qwen3.7 series supporting text and image input with upgraded text capabilities"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text, image]
+ output_types: [text]
+ release_date: 2026-06-02
+ cost: {input: 0.4, output: 1.6}
+
+ - name: Qwen3.7 Max
+ model: qwen3.7-max
+ description: "Capable of writing and debugging code, and sustaining autonomous execution across hundreds or thousands of steps"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text]
+ output_types: [text]
+ release_date: 2026-05-21
+ cost: {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"
@@ -963,32 +813,42 @@ opencode-go:
release_date: 2026-04-02
cost: {input: 0.5, output: 3}
- - name: MiMo V2 Omni
- model: mimo-v2-omni
- description: "Frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture"
+ - name: MiniMax M3 (3x usage)
+ model: minimax-m3
+ description: "Multimodal foundation model from MiniMax with a 1M-token context window, suited for long-horizon agentic work and coding"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
- input_types: [text, image, pdf]
+ input_types: [text, image]
output_types: [text]
- release_date: 2026-03-18
- cost: {input: 0.4, output: 2}
+ release_date: 2026-05-31
+ cost: {input: 0.1, output: 0.4}
- - name: MiMo V2 Pro
- model: mimo-v2-pro
- description: "Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply optimized for agentic scenarios"
+ - name: MiniMax M2.7
+ model: minimax-m2.7
+ description: "Next-generation large language model designed for autonomous, real-world productivity and continuous improvement"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-03-18
- cost: {input: 1, output: 3}
+ cost: {input: 0.3, output: 1.2}
- - name: MiniMax M2.7
- model: minimax-m2.7
- description: "Next-generation large language model designed for autonomous, real-world productivity and continuous improvement"
+ - name: MiMo V2.5
+ model: mimo-v2.5
+ description: "Native omnimodal model from Xiaomi delivering Pro-level agentic performance at roughly half the inference cost"
+ roles: [chat, edit]
+ capabilities: [thinking, tool_calling]
+ input_types: [text, image]
+ output_types: [text]
+ release_date: 2026-04-22
+ cost: {input: 0.4, output: 2}
+
+ - name: MiMo V2.5 Pro
+ model: mimo-v2.5-pro
+ description: "Xiaomi's flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal,…"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
- release_date: 2026-03-18
- cost: {input: 0.3, output: 1.2}
+ release_date: 2026-04-22
+ cost: {input: 1, output: 3}