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
anthropic:
- name: Claude Haiku 5.5
model: claude-haiku-5-5
description: "Small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-10-07
cost: {input: 0.1, output: 0.5}
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Claude Sonnet 5.5
model: claude-sonnet-5-5
description: "Sonnet-class reasoning model for everyday coding, bug fixes, and document creation"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-28
cost: {input: 2, output: 10}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Claude Opus 5.5
model: claude-opus-5-5
description: "Anthropic's strongest Opus model for coding, agents, and knowledge work"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-22
cost: {input: 4, output: 20}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Claude Fable 5.1
model: claude-fable-5-1
description: "Anthropic model for ambitious, long-running coding, agentic, research, and enterprise workflows"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-01
cost: {input: 10, output: 50}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Claude Opus 5
model: claude-opus-5
description: "Anthropic's flagship model 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: 2026-07-24
cost: {input: 5, output: 25}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Claude Fable 5
model: 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: 2026-06-07
cost: {input: 10, output: 50}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Claude Sonnet 5
model: 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: 2026-06-29
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
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}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Claude Sonnet 4.6
model: claude-sonnet-4-6
description: "Anthropic Sonnet model for coding, agents, and professional work"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-02-17
cost: {input: 3, output: 15}
reasoning_options:
- type: effort
values: [low, medium, high, max]
- type: budget_tokens
min: 1024
limits: {context: 1000000, output: 128000}
- name: Claude Haiku 4.5
model: claude-haiku-4-5
description: "Fast and efficient Claude model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2025-10-15
cost: {input: 1, output: 5}
reasoning_options:
- type: budget_tokens
min: 1024
limits: {context: 200000, output: 64000}
openai:
- name: GPT-6.1 Sol
model: gpt-6.1-sol
description: "Reasoning model for agentic coding, computer use, and document-heavy professional work"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-29
cost: {input: 2, output: 10}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: GPT-6 Luna
model: gpt-6-luna
description: "OpenAI's most efficient model for focused, high-volume tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-22
cost: {input: 0.1, output: 0.5}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: GPT-6 Sol
model: gpt-6-sol
description: "OpenAI reasoning model for demanding tasks that balances capability, latency, and cost"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-22
cost: {input: 2, output: 10}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: Daybreak Blue
model: gpt-daybreak-blue-latest
description: "OpenAI model alias for authorized defensive cybersecurity work with reduced refusals"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-08-07
cost: {input: 4, output: 20}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: Daybreak Red
model: gpt-daybreak-red-latest
description: "OpenAI model alias for advanced authorized cybersecurity work, including penetration testing and exploit validation"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-08-07
cost: {input: 12.5, output: 75}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 400000, output: 128000}
- name: GPT-6 Astra
model: gpt-6-astra
description: "OpenAI model for advanced analysis, software engineering, deep research, scientific work, and document creation"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-04
cost: {input: 10, output: 50}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- 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: 4, output: 20}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- 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: 0.2, output: 1.2}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- 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: 4, output: 20}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- 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, output: 12}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: GPT-5.5
model: gpt-5.5
description: "OpenAI model for complex professional workloads, with stronger reasoning, reliability, and token efficiency than GPT-5.4 on hard tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-04-23
cost: {input: 5, output: 30}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh]
limits: {context: 1050000, output: 128000}
google:
- 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: 32768}
- name: Claude Haiku 5.5
model: claude-haiku-5-5@default
description: "Small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use, available through Vertex AI only"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-10-07
cost: {input: 0.1, output: 0.5}
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Grok 4.7
model: xai/grok-4.7
description: "Model for coding, agentic tasks, and knowledge work, available through Vertex AI only"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-09-21
cost: {input: 2, output: 6}
reasoning_options:
- type: effort
values: [low, medium, high]
limits: {context: 524288, output: 500000}
- name: Claude Sonnet 5.5
model: claude-sonnet-5-5@default
description: "Sonnet-class reasoning model for everyday coding, bug fixes, and document creation, available through Vertex AI only"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-28
cost: {input: 2, output: 10}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Claude Opus 5.5
model: claude-opus-5-5@default
description: "Anthropic's strongest Opus model for coding, agents, and knowledge work, available through Vertex AI only"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-22
cost: {input: 4, output: 20}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Grok 4.6
model: xai/grok-4.6
description: "xAI frontier model for coding, knowledge work, and STEM"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-08-12
cost: {input: 2, output: 6}
reasoning_options:
- type: effort
values: [low, medium, high]
limits: {context: 524288, output: 500000}
- name: Gemini 3.8 Flash
model: gemini-3.8-flash
description: "Google's most intelligent Flash model, with gains in software engineering, agentic tasks, and multi-step reasoning"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-02
cost: {input: 0.75, output: 3.75}
reasoning_options:
- type: effort
values: [low, medium, high]
limits: {context: 1048576, output: 65536}
- name: Claude Fable 5.1
model: claude-fable-5-1@default
description: "Anthropic model for ambitious, long-running coding, agentic, research, and enterprise workflows, available through Vertex AI only"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-01
cost: {input: 10, output: 50}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Gemini Flash Latest
model: gemini-flash-latest
description: "Alias that points to the latest Gemini Flash release and can change when Google updates the model family"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-08-13
cost: {input: 0.75, output: 3.75}
reasoning_options:
- type: effort
values: [low, medium, high]
limits: {context: 1048576, output: 65536}
- name: Gemini 3.7 Flash
model: gemini-3.7-flash
description: "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-08-13
cost: {input: 0.75, output: 3.75}
reasoning_options:
- type: effort
values: [low, medium, high]
limits: {context: 1048576, output: 65536}
- name: Gemma 4 26B A4B IT
model: gemma-4-26b-a4b-it
description: "Instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-04-02
reasoning_options:
- type: toggle
limits: {context: 262144, output: 32768}
- name: Gemma 4 31B IT
model: gemma-4-31b-it
description: "Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-04-02
reasoning_options:
- type: toggle
limits: {context: 262144, output: 32768}
- name: Claude Opus 5
model: claude-opus-5@default
description: "Anthropic Claude Opus 5 on Google Vertex AI only (not available via the Gemini API)"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-07-24
cost: {input: 5, output: 25}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Claude Sonnet 5
model: claude-sonnet-5@default
description: "Anthropic Claude Sonnet 5 on Google Vertex AI only (not available via the Gemini API)"
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
model: claude-opus-4-8@default
description: "Anthropic Claude Opus 4.8 on Google Vertex AI only (not available via the Gemini API)"
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}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
bedrock:
- name: Claude Haiku 5.5 (Global)
model: global.anthropic.claude-haiku-5-5
description: "Small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-10-07
cost: {input: 0.1, output: 0.5}
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: GPT-6.1 Sol (Global)
model: global.openai.gpt-6.1-sol
description: "Reasoning model for agentic coding, computer use, and document-heavy professional work"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-09-29
cost: {input: 2, output: 10}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: Claude Opus 5.5 (Global)
model: global.anthropic.claude-opus-5-5
description: "Anthropic's strongest Opus model for coding, agents, and knowledge work"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-22
cost: {input: 4, output: 20}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: GPT-6 Luna (Global)
model: global.openai.gpt-6-luna
description: "OpenAI's most efficient model for focused, high-volume tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-09-22
cost: {input: 0.1, output: 0.5}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: GPT-6 Astra (Global)
model: global.openai.gpt-6-astra
description: "OpenAI model for advanced analysis, software engineering, deep research, scientific work, and document creation"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-09-04
cost: {input: 10, output: 50}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: Grok 4.6 (Global)
model: global.xai.grok-4.6
description: "xAI frontier model for coding, knowledge work, and STEM"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-08-12
cost: {input: 2, output: 6}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh]
limits: {context: 500000, output: 500000}
- name: Claude Fable 5.1 (Global)
model: global.anthropic.claude-fable-5-1
description: "Anthropic model for ambitious, long-running coding, agentic, research, and enterprise workflows"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-01
cost: {input: 10, output: 50}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Grok 4.6
model: xai.grok-4.6
description: "xAI's frontier model for coding, agentic tasks, knowledge work, and visual reasoning"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-08-12
cost: {input: 2.2, output: 6.6}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh]
limits: {context: 500000, output: 500000}
- name: GPT-5.6 Luna (Global)
model: global.openai.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]
output_types: [text]
release_date: 2026-07-09
cost: {input: 0.2, output: 1.2}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: GPT-5.6 Sol (Global)
model: global.openai.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]
output_types: [text]
release_date: 2026-07-09
cost: {input: 4, output: 20}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: Claude Opus 5 (Global)
model: global.anthropic.claude-opus-5
description: "Anthropic's flagship model 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: 2026-07-24
cost: {input: 5, output: 25}
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: GPT-5.6 Luna
model: openai.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: 0.22, output: 1.32}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: GPT-5.6 Sol
model: openai.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: 4.4, output: 22}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: GPT-5.6 Terra
model: openai.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: 2.2, output: 13.2}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, 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"
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}
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: GLM-5
model: zai.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: 2026-02-12
cost: {input: 1, output: 3.2}
reasoning_options:
- type: toggle
limits: {context: 202752, output: 131072}
- name: NVIDIA Nemotron 3 Super 120B A12B
model: nvidia.nemotron-super-3-120b
description: "120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-03-11
cost: {input: 0.15, output: 0.65}
reasoning_options: []
limits: {context: 262144, output: 131072}
- name: Claude Sonnet 4.6
model: anthropic.claude-sonnet-4-6
description: "Anthropic Sonnet model for coding, agents, and professional work"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-02-17
cost: {input: 3.3, output: 16.5}
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, high, max]
- type: budget_tokens
min: 1024
limits: {context: 1000000, output: 128000}
azure:
- name: Claude Haiku 5.5
model: claude-haiku-5-5
description: "Small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-10-07
cost: {input: 0.1, output: 0.5}
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: GPT-6.1 Sol
model: gpt-6.1-sol
description: "Reasoning model for agentic coding, computer use, and document-heavy professional work"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-29
cost: {input: 2, output: 10}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: Claude Sonnet 5.5
model: claude-sonnet-5-5
description: "Sonnet-class reasoning model for everyday coding, bug fixes, and document creation"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-28
cost: {input: 2, output: 10}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Claude Opus 5.5
model: claude-opus-5-5
description: "Anthropic's strongest Opus model for coding, agents, and knowledge work"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-22
cost: {input: 4, output: 20}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: GPT-6 Luna
model: gpt-6-luna
description: "OpenAI's most efficient model for focused, high-volume tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-22
cost: {input: 0.1, output: 0.5}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: GPT-6 Sol
model: gpt-6-sol
description: "OpenAI reasoning model for demanding tasks that balances capability, latency, and cost"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-22
cost: {input: 2, output: 10}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: GPT-6 Astra
model: gpt-6-astra
description: "OpenAI model for advanced analysis, software engineering, deep research, scientific work, and document creation"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-04
cost: {input: 10, output: 50}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: Claude Fable 5.1
model: claude-fable-5-1
description: "Anthropic model for ambitious, long-running coding, agentic, research, and enterprise workflows"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-01
cost: {input: 10, output: 50}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh]
limits: {context: 1000000, output: 128000}
- name: Grok 4.6
model: grok-4.6
description: "xAI frontier model for coding, knowledge work, and STEM"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-08-12
reasoning_options:
- type: effort
values: [low, medium, high, xhigh]
limits: {context: 200000, output: 128000}
cost: {input: 2, output: 6}
- name: Claude Opus 5
model: claude-opus-5
description: "Anthropic's flagship model 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: 2026-07-24
cost: {input: 5, output: 25}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- 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: 0.2, output: 1.2}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- 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: 4, output: 20}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- 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, output: 12}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: GPT Chat Latest
model: gpt-chat-latest
description: "OpenAI's stable chat-latest alias that always resolves to the latest Instant chat model used in ChatGPT"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-05-05
cost: {input: 5, output: 30}
reasoning_options:
- type: effort
values: [medium]
limits: {context: 400000, output: 128000}
- name: Claude Fable 5
model: 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]
limits: {context: 1000000, output: 128000}
- name: Claude Sonnet 5
model: 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: GPT-5.5
model: gpt-5.5
description: "OpenAI model for complex professional workloads, with stronger reasoning, reliability, and token efficiency than GPT-5.4 on hard tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-04-24
cost: {input: 5, output: 30}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh]
limits: {context: 1050000, output: 128000}
- name: Grok 4.20 (Non-Reasoning)
model: grok-4-20-non-reasoning
description: "Reasoning model from xAI with industry-leading speed and agentic tool calling capabilities"
roles: [chat, edit]
capabilities: [tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-04-08
cost: {input: 2, output: 6}
limits: {context: 262000, output: 8192}
- name: Grok 4.20 (Reasoning)
model: grok-4-20-reasoning
description: "Reasoning model from xAI with industry-leading speed and agentic tool calling capabilities"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-04-08
cost: {input: 2, output: 6}
reasoning_options: []
limits: {context: 262000, output: 8192}
- 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}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: Claude Sonnet 4.6
model: claude-sonnet-4-6
description: "Anthropic Sonnet model for coding, agents, and professional work"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-02-17
cost: {input: 3, output: 15}
reasoning_options:
- type: effort
values: [low, medium, high, max]
- type: budget_tokens
min: 1024
limits: {context: 1000000, output: 64000}
- 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, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-04-24
cost: {input: 0.19, output: 0.51}
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, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-04-24
cost: {input: 1.74, output: 3.48}
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"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-10-17
cost: {input: 0.15, output: 0.6}
reasoning_options:
- type: toggle
- type: effort
values: [low, high, max]
limits: {context: 1048576, output: 384000}
- name: Muse Spark Open
model: muse-spark-open
description: "Open-weight model optimized for agentic coding, reliable tool calling, and codebase understanding"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-10-15
cost: {input: 1.25, output: 4.25}
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, high, max]
limits: {context: 1048576, output: 131072}
- name: Mistral Large 4
model: mistral-large-4
description: "Multimodal model from Mistral AI for reasoning, coding, and agentic workloads"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-10-06
cost: {input: 0.68, output: 2.09}
reasoning_options:
- type: effort
values: [none, high]
limits: {context: 1048576, output: 262144}
- name: DeepSeek V4.1 Flash
model: deepseek-v4.1-flash
description: "Sparse Mixture-of-Experts model from DeepSeek built on a Causal Encoder-Decoder architecture"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-09-10
reasoning_options:
- type: toggle
- type: effort
values: [low, high, max]
limits: {context: 1048576, output: 384000}
cost: {input: 0.15, output: 0.6}
- name: DeepSeek V4 Pro 0813
model: deepseek-v4-pro:0813
description: "Large-scale Mixture-of-Experts model and generally available release of DeepSeek V4 Pro"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-08-13
reasoning_options:
- type: toggle
- type: effort
values: [low, high, max]
limits: {context: 1048576, output: 1048576}
cost: {input: 0.66, output: 1.98}
- name: GLM-5.3-Flash
model: glm-5.3-flash
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]
output_types: [text]
release_date: 2026-08-26
reasoning_options:
- type: effort
values: [low, high, max]
limits: {context: 1000000, output: 131072}
cost: {input: 0.15, output: 0.5}
- name: GLM-5.3
model: glm-5.3
description: "Large-scale reasoning model from Z.ai built for complex software engineering and long-horizon agent tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-08-14
reasoning_options:
- type: effort
values: [low, high, max]
limits: {context: 1048576, output: 131072}
cost: {input: 1.4, output: 4.4}
- 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
reasoning_options:
- type: toggle
- type: effort
values: [high, max]
limits: {context: 1048576, output: 1048576}
cost: {input: 0.22, output: 0.66}
- 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"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-07-16
reasoning_options:
- type: toggle
- type: effort
values: [low, high, max]
limits: {context: 1048576, output: 131072}
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, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-04-24
reasoning_options:
- type: toggle
- type: effort
values: [high, max]
limits: {context: 1048576, output: 1048576}
cost: {input: 0.22, output: 0.66}
- 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, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-04-24
reasoning_options:
- type: toggle
- type: effort
values: [low, high, max]
limits: {context: 1048576, output: 1048576}
cost: {input: 0.66, output: 1.98}
- name: Gemma 4 31B
model: gemma4:31b
description: "Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-04-02
reasoning_options:
- type: toggle
limits: {context: 262144, output: 262144}
cost: {input: 0.14, output: 0.4}
- 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
reasoning_options:
- type: toggle
- type: effort
values: [high, max]
limits: {context: 976000, output: 131072}
cost: {input: 1.4, output: 4.4}
- 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: 2026-06-01
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, high, max]
limits: {context: 512000, output: 131072}
cost: {input: 0.6, output: 2.4}
- name: MiniMax M2.7
model: minimax-m2.7
description: "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
reasoning_options: []
limits: {context: 196608, output: 196608}
cost: {input: 0.3, output: 1.2}
- name: NVIDIA Nemotron 3 Ultra
model: nemotron-3-ultra
description: "Open 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
reasoning_options:
- type: toggle
limits: {context: 262144, output: 128000}
cost: {input: 0.1, output: 3}
- 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"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-03-11
reasoning_options:
- type: toggle
limits: {context: 262144, output: 65536}
cost: {input: 0.015, output: 0.6}
- name: Qwen 3.5 397B
model: qwen3.5:397b
description: "Built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-02-15
reasoning_options:
- type: toggle
limits: {context: 262144, output: 65536}
cost: {input: 0.6, output: 3.6}
wandb:
- name: Beam 1.0
model: reflection/Beam-1.0-501B-A23B
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
cost: {input: 0.3, output: 1}
reasoning_options:
- type: effort
values: [minimal, low, medium, high, xhigh, max]
limits: {context: 1048576, output: 1048576}
- name: Nemotron 3.5 Super VL
model: nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B
description: "Open multimodal Mixture-of-Experts model with 12B active parameters out of 120B for reasoning, coding, tool use, and document understanding"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-10-15
cost: {input: 0.15, output: 0.5}
reasoning_options:
- type: toggle
limits: {context: 1048576, output: 1048576}
- name: DeepSeek V4.1 Flash
model: deepseek-ai/DeepSeek-V4.1-Flash
description: "Sparse Mixture-of-Experts model from DeepSeek built on a Causal Encoder-Decoder architecture"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-09-10
cost: {input: 0.15, output: 0.65}
reasoning_options:
- type: toggle
limits: {context: 1048576, output: 1048576}
- name: GLM 5.3 Flash
model: zai-org/GLM-5.3-Flash
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]
output_types: [text]
release_date: 2026-08-26
cost: {input: 0.15, output: 0.5}
reasoning_options: []
limits: {context: 1048576, output: 1048576}
- name: Granite 4.2 8B
model: ibm-granite/granite-4.2-8b
description: "Dense reasoning model from IBM for mathematics, code generation, multilingual dialogue, and multi-step agentic workflows"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-08-25
cost: {input: 0.1, output: 0.15}
reasoning_options:
- type: toggle
limits: {context: 131072, output: 131072}
- name: DeepSeek V4 Pro 0813
model: deepseek-ai/DeepSeek-V4-Pro-0813
description: "Large-scale Mixture-of-Experts model and generally available release of DeepSeek V4 Pro"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-08-13
cost: {input: 1.31, output: 3.96}
reasoning_options:
- type: toggle
limits: {context: 1048576, output: 1048576}
- name: Qwen3.8 27B
model: Qwen/Qwen3.8-27B
description: "Alibaba's 27B dense multimodal model for coding, professional work, research, and long-horizon agentic tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-08-14
cost: {input: 0.4, output: 3}
reasoning_options:
- type: toggle
limits: {context: 262144, output: 262144}
- name: Nemotron 3.5 Lightning
model: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
description: "MoE model built for fast, reliable agentic tasks across financial services, cybersecurity, telecom, and retail"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-08-11
cost: {input: 0.07, output: 0.2}
reasoning_options:
- type: toggle
limits: {context: 262144, output: 262144}
- 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}
reasoning_options:
- type: toggle
limits: {context: 262144, output: 262144}
- name: MiniMax M3
model: MiniMaxAI/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: 2026-06-01
cost: {input: 0.23, output: 0.96}
reasoning_options: []
limits: {context: 262144, output: 262144}
- name: DeepSeek V4-Flash
model: deepseek-ai/DeepSeek-V4-Flash
description: "DeepSeek V4-Flash is an MoE model with 1M context length great for coding, reasoning, and agentic workloads"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-04-24
cost: {input: 0.14, output: 0.28}
reasoning_options:
- type: toggle
limits: {context: 1048576, output: 1048576}
- name: DeepSeek V4 Pro
model: deepseek-ai/DeepSeek-V4-Pro
description: "DeepSeek V4-Pro is a 1.6T-parameter MoE model with 49B active parameters excelling at advanced reasoning, coding, and complex agentic workloads"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-04-24
cost: {input: 1.15, output: 2.55}
reasoning_options:
- type: toggle
limits: {context: 1048576, output: 1048576}
- name: GLM 5.2
model: zai-org/GLM-5.2
description: "GLM-5.2 is a Mixture-of-Experts language model featuring 40 billion activated parameters and a total of 744 billion parameters"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-06-13
cost: {input: 0.62, output: 2.42}
reasoning_options:
- type: toggle
limits: {context: 1048576, output: 1048576}
- name: Nemotron 3 Ultra
model: nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
description: "Open 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: 0.5, output: 2.15}
reasoning_options:
- type: toggle
limits: {context: 262144, output: 262144}
- name: NVIDIA Nemotron 3 Super 120B
model: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
description: "120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-03-11
cost: {input: 0.2, output: 0.8}
- name: gpt-oss-120b
model: openai/gpt-oss-120b
description: "Open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2025-08-05
cost: {input: 0.03, output: 0.17}
reasoning_options: []
limits: {context: 131072, output: 131072}
- name: gpt-oss-20b
model: openai/gpt-oss-20b
description: "Open-weight 21B parameter model released by OpenAI under the Apache 2.0 license"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2025-08-05
cost: {input: 0.03, output: 0.13}
reasoning_options: []
limits: {context: 131072, output: 131072}
- name: Mellum2 12B A2.5B
model: JetBrains/Mellum2-12B-A2.5B-Instruct
description: "Mellum2-12B-A2.5B-Instruct is a fast MoE model with 131K context built for coding, tool use, and low-latency AI workflows"
roles: [chat, edit]
capabilities: [tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-06-01
cost: {input: 0.05, output: 0.1}
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"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-10-05
cost: {input: 0, output: 0}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1048576, output: 131072}
- name: Gemini 4 Argon Contributor
model: gemini-4-argon-contributor
description: "Contributor tier of Gemini 4 Argon for reasoning, coding, and agents, with prompts and completions eligible for model training"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-10-13
cost: {input: 4, output: 20}
reasoning_options:
- type: effort
values: [low, medium, high]
limits: {context: 1048576, output: 65536}
- name: Claude Haiku 5.5
model: claude-haiku-5-5
description: "Small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-10-07
cost: {input: 0.1, output: 0.5}
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1000000, output: 128000}
- name: LongCat 2.5 Preview Free
model: longcat-2.5-preview-free
description: "Multimodal reasoning model from Meituan for coding and agentic workflows, with a one-million-token context window"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-09-25
cost: {input: 0, output: 0}
reasoning_options:
- type: toggle
limits: {context: 1000000, output: 131072}
- name: Space Bunny Free
model: space-bunny-free
description: "Anonymous model with fast inference, strong coding capabilities, native multimodal input, and adjustable reasoning effort"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-09-23
cost: {input: 0, output: 0}
reasoning_options:
- type: effort
values: [low, medium, high, xhigh, max]
limits: {context: 1048576, output: 524288}
- name: GPT-6 Luna
model: gpt-6-luna
description: "OpenAI's most efficient model for focused, high-volume tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-22
cost: {input: 0.1, output: 0.5}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: MiMo-V2.6-Flash
model: mimo-v2.6-flash
description: "Open-source Mixture-of-Experts foundation model from Xiaomi with 309B total parameters and 15B activated per token"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-09-22
cost: {input: 0.14, output: 0.28}
reasoning_options: []
limits: {context: 1048576, output: 131072}
- name: MiMo-V2.6-Pro
model: mimo-v2.6-pro
description: "Xiaomi's flagship foundation model with over one trillion parameters, designed for demanding coding and agentic tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-09-22
cost: {input: 0.435, output: 0.87}
reasoning_options: []
limits: {context: 1048576, output: 131072}
- name: DeepSeek V4.1 Flash
model: deepseek-v4.1-flash
description: "Sparse Mixture-of-Experts model from DeepSeek built on a Causal Encoder-Decoder architecture"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-09-10
cost: {input: 0.15, output: 0.6}
reasoning_options:
- type: effort
values: [low, high, max]
limits: {context: 1000000, output: 384000}
- name: Muse Spark 1.3 Contributor
model: muse-spark-1.3-contributor
description: "Cost-efficient contributor tier of Meta's multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image, pdf]
output_types: [text]
release_date: 2026-09-02
cost: {input: 0.1, output: 0.2}
reasoning_options:
- type: effort
values: [minimal, low, medium, high, xhigh]
limits: {context: 1048576, output: 131072}
- name: Hy4 preview
model: hy4-preview
description: "Mixture-of-Experts model from Tencent designed for coding agents, complex tool use, and productivity tasks"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-08-28
cost: {input: 0.834, output: 2.501}
reasoning_options:
- type: effort
values: [none, high]
limits: {context: 1024000, output: 64000}
- name: GLM-5.3-Flash (2x usage)
model: glm-5.3-flash
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]
output_types: [text]
release_date: 2026-08-26
cost: {input: 0.15, output: 0.5}
reasoning_options:
- type: effort
values: [low, high, max]
limits: {context: 1000000, output: 131072}
- name: Qwen3.8 Flash
model: qwen3.8-flash
description: "Multimodal reasoning model from Alibaba for coding, agentic workflows, visual understanding, document and codebase analysis, and desktop interaction"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-08-26
cost: {input: 0.15, output: 0.47}
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, xhigh]
- type: budget_tokens
limits: {context: 1000000, output: 131072}
- name: DeepSeek V4 Flash Vision Exp
model: deepseek-v4-flash-vision-exp
description: "Experimental multimodal variant of DeepSeek V4 Flash that adds image understanding while retaining its text and agent capabilities"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-08-21
cost: {input: 0.15, output: 0.6}
reasoning_options:
- type: toggle
- type: effort
values: [low, high, max]
limits: {context: 1000000, output: 384000}
- name: GLM-5.3
model: glm-5.3
description: "Flagship GLM model for long-horizon coding, agents, and complex project delivery"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-08-14
cost: {input: 1.4, output: 4.4}
reasoning_options:
- type: effort
values: [low, high, max]
limits: {context: 1000000, output: 131072}
- 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}
reasoning_options:
- type: toggle
- type: effort
values: [low, medium, xhigh]
- type: budget_tokens
max: 262144
limits: {context: 1000000, output: 131072}
- 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: 0.2, output: 1.2}
reasoning_options:
- type: effort
values: [none, low, medium, high, xhigh, max]
limits: {context: 1050000, output: 128000}
- name: Kimi K3 (2x usage)
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"
roles: [chat, edit]
capabilities: [thinking, tool_calling]
input_types: [text, image]
output_types: [text]
release_date: 2026-07-16
cost: {input: 3, output: 15}
reasoning_options:
- type: effort
values: [max]
limits: {context: 1048576, output: 131072}
- 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, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-07-31
cost: {input: 0.15, output: 0.6}
reasoning_options:
- type: effort
values: [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, tool_calling]
input_types: [text]
output_types: [text]
release_date: 2026-04-24
cost: {input: 0.66, output: 1.98}
reasoning_options:
- type: effort
values: [high, max]
limits: {context: 1000000, output: 384000}
- 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}
reasoning_options:
- type: effort
values: [high, max]
limits: {context: 1000000, output: 131072}
- 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}
reasoning_options:
- type: toggle
- type: budget_tokens
max: 262144
limits: {context: 1000000, output: 65536}
- 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}
reasoning_options:
- type: toggle
- type: budget_tokens
max: 262144
limits: {context: 1000000, output: 65536}
- 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]
output_types: [text]
release_date: 2026-06-01
cost: {input: 0.3, output: 1.2}
reasoning_options:
- type: toggle
limits: {context: 1000000, output: 131072}