EZ AI ASSIST MODEL DIRECTORY

253 Models.One Interface.

Access every major AI model for chat, image generation, video generation, and music generation from one unified EZ Ai Assist workspace.

Counts include retained reference pages, not just currently selectable app models. Image guides cover 40 app-listed choices, 8 historical entries and 1 snapshot reference. Video guides cover 33 app-listed video choices and 2 retained references. Check each guide for routing and availability notes.

154

Chat Models

Frontier chat, reasoning, coding, research, and agentic models.

51

Image Tools

Prompt-to-image engines for creative and production visual work.

35

Video Models

Text-to-video and cinematic generation models across leading providers.

13

Music Models

Prompt-to-song, sound, voice, and audio generation models.

253 results

Browse the EZ Ai Assist model catalog.

Each card links to a static marketing detail page. The directory does not trigger real model selection or app workflows.

chat

OpenAI

GPT-6.1 Sol

GPT-6.1 Sol is OpenAI’s reasoning model for complex coding and professional work, with image input and a 1.05M-token context window.

ReasoningCoding
New
chat

OpenAI

GPT-6.1 Terra

OpenAI chat model with vision, a 1.05M-token context window, a 128K-token reply limit, and reasoning effort from none to max. Available on all EZ Ai Assist plans.

ReasoningImage input
NewGPT-6
chat

OpenAI

GPT-6 Sol

GPT-6 Sol is an OpenAI model for complex coding and tool-assisted workflows, with image input and configurable reasoning.

ReasoningCoding
NewGPT-6
chat

OpenAI

GPT-6 Luna

GPT-6 Luna is an efficient OpenAI model for focused, high-volume tasks, with image input, structured outputs, and configurable reasoning.

FastEfficient
chat

OpenAI

GPT-6 Astra

GPT-6 Astra is an OpenAI model for complex reasoning, coding, and research, with image input and a 1.05M-token context window.

ReasoningCoding
New
chat

OpenAI

GPT-5.6 Sol

Best for Coding

GPT-5.6 Sol is an OpenAI model for professional reasoning and coding, with image input, configurable reasoning effort, and a 1.05M-token context window.

1M+ contextCoding
New
chat

OpenAI

GPT-5.6 Terra

Best Overall

OpenAI model balancing reasoning and cost for everyday work, with image input, structured outputs, and configurable reasoning effort.

1M+ contextCoding
New
chat

OpenAI

GPT-5.6 Luna

Fastest

OpenAI model for cost-sensitive, high-volume tasks, with image input, structured outputs, and configurable reasoning effort.

1M+ contextCoding
New
chat

OpenAI

GPT-5.5

OpenAI reasoning model for complex professional work and coding, with image input, tool support, and a large context window.

1M+ contextCoding
New
chat

OpenAI

GPT-5.5 Pro

OpenAI reasoning model for demanding analysis, with a 1,050,000-token context window and text/image input.

1M+ contextReasoning
Deprecated
chat

OpenAI

GPT-5.3 Codex

Best for Coding

OpenAI coding specialist for repository work and tools. Deprecated; API shutdown is scheduled for April 1, 2027.

CodingTool use
New
chat

OpenAI

GPT-5.4

OpenAI model for professional work, coding, and tool-assisted tasks, with a 1,050,000-token context window.

1M contextFlagship
New
chat

OpenAI

GPT-5.4 Mini

Best Overall

Efficient OpenAI model for coding, image understanding, and tool-assisted workflows with a 400,000-token context window.

BalancedExtended context
Deprecated
chat

OpenAI

GPT-5.4 Nano

Fastest

OpenAI model for classification, extraction, and ranking. Deprecated; API shutdown is scheduled for April 1, 2027.

FastSimple tasks
New
chat

OpenAI

GPT-5.4 Pro

Best for Research

OpenAI reasoning model for difficult analysis via the Responses API, with a 1,050,000-token context window.

Deep reasoningCritical tasks
Deprecated
chat

OpenAI

GPT-5.1

OpenAI model for coding and configurable reasoning. Deprecated; API shutdown is scheduled for April 1, 2027.

CodingAgentic
chat

OpenAI

GPT-5.2 Thinking

OpenAI model for document analysis, coding, and professional reasoning, available through the API as gpt-5.2.

ReasoningKnowledge work
chat

OpenAI

GPT-5.2 Pro

OpenAI reasoning model for complex professional analysis via the Responses API, with a 400,000-token context window.

ReasoningKnowledge work
Deprecated
chat

OpenAI

o3

OpenAI reasoning model for technical and visual analysis. Its deprecated API snapshot retires December 11, 2026.

Reasoning
Deprecated
chat

OpenAI

o3-pro

OpenAI model for extended reasoning through Responses, without streaming. Its deprecated API snapshot retires December 11, 2026.

ReasoningExtended thinking
Deprecated
chat

OpenAI

GPT-5

OpenAI model for coding and configurable reasoning. Its deprecated API snapshot retires December 11, 2026.

FlagshipMultimodal
Deprecated
chat

OpenAI

GPT-5 Mini

OpenAI GPT-5 variant for well-defined, cost-sensitive tasks. Its deprecated API snapshot retires December 11, 2026.

Lower costGeneral purpose
Deprecated
chat

OpenAI

GPT-5 Nano

OpenAI GPT-5 variant for focused summarization and classification. Its deprecated API snapshot retires December 11, 2026.

FastHigh volume
Deprecated
chat

OpenAI

GPT-5 Pro

OpenAI model with high-only reasoning for complex analysis. Its deprecated API snapshot retires December 11, 2026.

Deep analysisReasoning
chat

OpenAI

GPT-4.1

OpenAI non-reasoning model for instruction following, coding, and long documents, with a 1,047,576-token context window.

Long contextCoding
chat

OpenAI

GPT-4.1 Mini

OpenAI non-reasoning model for instruction following and tool-assisted tasks, with a 1,047,576-token context window.

1M contextCompact
chat

OpenAI

GPT-4o Mini

OpenAI small model for focused text and image-input tasks, with structured outputs and a 128,000-token context window.

MultimodalFast
chat

OpenAI

ChatGPT Latest

OpenAI’s rolling chat-latest alias for the latest Instant model used in ChatGPT, with text and image input.

Rolling aliasChatGPT
New
chat

Anthropic

Claude Sonnet 5.5

Anthropic model for coding and everyday professional work, with adaptive thinking, image input, and a 1M-token context window.

Adaptive thinking1M context
New
chat

Anthropic

Claude Opus 5.5

Claude Opus 5.5 is Anthropic’s model for demanding coding and analysis, with always-on adaptive thinking and optional API Fast Mode.

Adaptive thinkingFast Mode
New
chat

Anthropic

Claude Haiku 5.5

Anthropic’s efficiency-oriented model with adaptive thinking, image input, a 1M-token context and medium effort by default.

Adaptive thinking1M context
Legacy
chat

Anthropic

Claude Opus 5

Best for Coding

Anthropic’s active legacy Opus model for complex coding and analysis, with adaptive thinking and a 1M-token context window.

CodingComplex reasoning
Legacy
chat

Anthropic

Claude Sonnet 5

Best Overall

Anthropic’s active legacy Sonnet model for coding and general work, with adaptive thinking and a 1M-token context window.

BalancedGeneral purpose
chat

Anthropic

Claude Fable 5.1

Claude Fable 5.1 is Anthropic’s model for demanding reasoning and long-running agentic work, with always-on adaptive thinking.

Adaptive thinkingLong-horizon work
Legacy
chat

Anthropic

Claude Fable 5

Best for Research

Anthropic’s active legacy Fable model for difficult reasoning and long-running work, with always-on adaptive thinking.

ResearchComplex reasoning
Retired
chat

Anthropic

Claude Opus 4.1

Historical Anthropic model for coding and reasoning. Retired on Anthropic-operated platforms August 5, 2026; partner availability can differ.

ReasoningFlagship
Legacy
chat

Anthropic

Claude Opus 4.8

Best for Research

Anthropic’s active legacy Opus model with optional adaptive thinking, image input, and a 1M-token context.

1M contextAgentic
Legacy
chat

Anthropic

Claude Opus 4.7

Best for Research

Anthropic’s legacy Opus model with adaptive thinking, five effort levels, and a 1M-token context for supplied material.

1M contextAgentic
Legacy
chat

Anthropic

Claude Sonnet 4.6

Best for Coding

Anthropic’s active legacy Sonnet model for coding and analysis, with optional adaptive thinking and a 1M-token context.

1M contextCoding
Legacy
chat

Anthropic

Claude Opus 4.6

Best for Research

Anthropic’s active legacy Opus model with a 1M-token context and adaptive thinking for established coding and analysis workflows.

1M contextDeep reasoning
Deprecated
chat

Anthropic

Claude Sonnet 4.5

Anthropic model with manual extended thinking. Deprecated; retirement on Anthropic-operated platforms is scheduled for November 30, 2026.

Reasoning
Legacy
chat

Anthropic

Claude Opus 4.5

Best for Writing

Anthropic’s active legacy Opus model with manual extended thinking, three effort levels, and a 200K-token context.

WritingAgentic
chat

Anthropic

Claude Haiku 4.5

Anthropic’s efficiency-oriented Haiku model for bounded tasks, with optional extended thinking, image input, and a 200K-token context.

FastNear-frontier
New
chat

Google

Gemini 4 Argon

Google’s flagship reasoning model for complex coding and analysis, with a shared 1M-token context, multimodal understanding and provider long-decode support.

ReasoningImage understanding
New
chat

Google

Gemini 4 Carbon

Google’s newest and most capable Gemini 4 model supports text and images, a 1M-token context window, and adjustable thinking. Available on EZ Ai Assist Pro and Business plans.

Deep reasoningImage input
New
chat

Google

Gemini 3.8 Flash

Google’s Gemini 3.8 Flash supports multimodal understanding, three thinking levels, and tool-assisted workflows with promotional API pricing.

FastMultimodal
chat

Google

Gemini 3.7 Flash

Google’s Gemini 3.7 Flash combines multimodal inputs, configurable thinking, and structured tool workflows for repeatable everyday tasks.

Chat
Preview
chat

Google

Gemini 3.1 Pro

Best for Coding

Google’s Gemini 3.1 Pro Preview supports complex synthesis, coding, and multimodal analysis with a 1M-token input limit.

ReasoningCoding
Retired
chat

Google

Gemini 3 Pro

Historical guide to Google’s retired Gemini 3 Pro Preview API, with specifications, migration checks, and the Gemini 3.1 Pro replacement.

Chat
Preview
chat

Google

Gemini 3.1 Pro (Custom Tools)

Best for Coding

Google’s Gemini 3.1 Pro Preview variant favors custom tools over bash; evaluate tool selection and answer quality for your workflow.

Tool useAgentic
Legacy
chat

Google

Gemini 3.6 Flash

Best Overall

Google’s earlier Gemini 3.6 Flash supports multimodal workflows and four thinking levels; the recommended replacement for Gemini 3 Flash Preview.

1M contextAgentic
Legacy
chat

Google

Gemini 3.5 Flash

Best Overall

Google’s earlier Gemini 3.5 Flash supports multimodal analysis, thinking controls, and tools, with its own model-specific API rates.

FastAgentic
Preview
chat

Google

Gemini 3 Flash

Best Overall

Google’s Gemini 3 Flash Preview supports multimodal inputs and tool workflows, with separate audio rates and a Gemini 3.6 Flash migration path.

FlashValue
New
chat

Google

Gemini 3.5 Flash-Lite

Google’s Gemini 3.5 Flash-Lite supports high-volume multimodal tasks, configurable thinking, and document parsing with a 1M-token input limit.

FastEfficient
New
chat

Google

Gemini 3.1 Flash-Lite

Best Value

Google’s Gemini 3.1 Flash-Lite supports translation, extraction, and lightweight multimodal workflows, with minimal thinking by default.

ValueHigh volume
Legacy
chat

Google

Gemini 2.5 Flash-Lite

Best Value

Google’s stable Gemini 2.5 Flash-Lite supports budget-sensitive multimodal tasks with optional thinking. Direct API access is restricted to prior users.

BudgetMultimodal
Legacy
chat

Google

Gemini 2.5 Pro

Best for Coding

Google’s stable Gemini 2.5 Pro supports complex reasoning and coding with a 1M-token input limit. Direct API access is restricted to prior users.

ReasoningCoding
Legacy
chat

Google

Gemini 2.5 Flash

Best Overall

Google’s stable Gemini 2.5 Flash combines multimodal input and adjustable thinking budgets. Direct API access is restricted to prior users.

FastReasoning
chat

Perplexity

Sonar

Perplexity’s lightweight web-grounded Sonar model for focused questions, with citations and a documented transition to the Agent API.

SearchLightweight
chat

Perplexity

Sonar Pro

Perplexity’s Sonar Pro supports deeper search and a 200K-token context. Explore its reference pricing and Agent API transition.

CitationsReasoning
chat

Perplexity

Sonar Reasoning Pro

Best for Research

Perplexity’s Sonar Reasoning Pro combines multi-step analysis with web retrieval. Distinct from the retired sonar-reasoning API identifier.

ResearchReasoning
chat

Perplexity

Sonar Deep Research

Perplexity’s Sonar Deep Research synthesizes broad web research into reports, with separate search, citation, and reasoning charges.

Deep researchSearch
NewPreview
chat

Meta

Muse Wonder

Meta’s preview reasoning model for demanding coding, analysis and multimodal understanding, with a 1M-token context and six API reasoning-effort levels.

ReasoningCoding
New
chat

Meta

Muse Spark 1.3

Meta’s latest Muse Spark for coding and multi-step tool workflows, with a 1M-token context and max reasoning on the Standard tier.

ReasoningCoding
chat

Meta

Muse Spark 1.2

Meta’s previous Muse Spark version supports text, image, video, audio, and PDF inputs for long-context reasoning and tool-assisted work.

MultimodalReasoning
chat

Meta

Muse Spark 1.1

Meta’s original Muse Spark version supports multimodal understanding and reasoning with a 1M-token context and Standard-tier API pricing.

MultimodalReasoning
New
chat

xAI

Grok 4.7

Coding and knowledge-work model with 500K context, image input, and configurable reasoning effort.

Reasoning controlsReasoning
chat

xAI

Grok 4.6

Coding and agentic model with 500K context, structured outputs, and four reasoning effort levels.

Chat
New
chat

xAI

Grok 4.5

Best Overall

Coding and engineering model with 500K context, image input, tool calling, and configurable reasoning.

CodingAgentic
chat

xAI

Grok 4.3

Best Overall

1M-context model for instruction-driven work and tool calling, with configurable reasoning that can be disabled.

1M contextInstruction following
chat

xAI

Grok Build 0.1

Best for Coding

Coding-focused model with 256K context, image input, function calling, and structured outputs.

CodingAgentic
chat

xAI

Grok 4.20 Reasoning

Best for Research

Reasoning-enabled Grok 4.20 with 1M context, image input, tool calling, and structured outputs.

Reasoning1M context
chat

xAI

Grok 4.20 Non-Reasoning

Fastest

Non-reasoning Grok 4.20 for direct-response workflows, with 1M context, image input, and tool calling.

FastCost-efficient
chat

xAI

Grok 4.20 Multi-Agent

Best for Research

Beta research model coordinating 4 or 16 agents, with 1M context and a leader that synthesizes the answer.

Multi-agentDeep research
New
chat

DeepSeek

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash combines text and vision with thinking controls, long context, and peak/off-peak direct API pricing.

FastTime-aware pricing
New
chat

DeepSeek

DeepSeek V4 Flash

Best Overall

V4 Flash 0731 on OpenRouter, with long-context text workflows and hosting limits distinct from newer direct API aliases.

1M contextVersioned model
New
chat

DeepSeek

DeepSeek V4 Pro

Best for Research

V4 Pro 0423 on OpenRouter for long-context reasoning, with provider-specific pricing and direct API version caveats.

Deep reasoning1M context
New
chat

Groq

GPT-OSS 120B

Best Overall

OpenAI's larger open-weight reasoning model on Groq, with tool use, structured outputs, and a 131K context window.

500 tok/sOpen model
New
chat

Groq

GPT-OSS 20B

Fastest

Compact open-weight reasoning on Groq for focused text tasks, with structured outputs, tool use, and automatic caching.

1000 tok/sLightweight
Retired
chat

Groq

Compound Mini

Historical single-tool Groq system retired September 21, 2026. Explore its former workflow and migration considerations.

Historical systemMigration guide
Retired
chat

Groq

Compound

Historical multi-tool Groq system retired September 21, 2026, with no direct replacement listed in its shutdown notice.

Historical systemMigration guide
Enterprise access
chat

Groq

LLaMA 3.3 70B Versatile

Meta's 70B text model on Groq with 131K context. Free/developer access ended; committed-spend enterprise contracts are exempt.

Text workflows131K context
Enterprise access
chat

Groq

LLaMA 3.1 8B Instant

Compact LLaMA text model on Groq. Free/developer access ended; eligible enterprise contracts retain access under Groq's exception.

CompactText workflows
Enterprise access
chat

Groq

Qwen3.6 27B

Groq-hosted text and vision model with thinking modes and 131K context. Self-service access ended; an enterprise exception remains.

MultimodalThinking modes
New
chat

Mistral AI

Mistral Medium 3.5

Best Overall

Text-and-vision model for coding and agent workflows, with 256K context and configurable reasoning.

AgenticCoding
Preview
chat

Mistral AI

Mistral Large 4

Mistral’s newest flagship is an open-weight multimodal model in v26.10 preview, with 1M context, vision, function calling, and structured output.

1M contextVision
New
chat

Mistral AI

Mistral Small 4

Fastest

Hybrid text-and-vision model combining instruction following, reasoning and coding with 256K context.

HybridCoding
New
chat

Mistral AI

Ministral 3 8B

Fastest

Compact 8B text-and-vision model for extraction and constrained workflows, with 256K context.

TextVision
New
chat

Mistral AI

Ministral 3 3B

Best Value

Small 3B text-and-vision model for narrow classification and extraction tasks, with 256K context.

EfficientVision
Flagship
chat

Mistral AI

Mistral Large 3

Best for Research

Open-weight mixture-of-experts model for text, vision and tool-assisted work, with 256K context.

Open-weightMultimodal
Vision
chat

Mistral AI

Ministral 3 14B

14B text-and-vision model for document and image workflows, with 256K context and open weights.

TextVision
New
chat

MiniMax

MiniMax M3

Best Overall

Multimodal coding model with text, image and video input and up to 1M context, subject to endpoint capacity.

1M contextMultimodal
chat

MiniMax

MiniMax M2.7

Best Overall

Text-focused coding and office-work model with 204,800 context, tool calling and always-on thinking.

CodingReasoning
Fast
chat

MiniMax

MiniMax M2.7 Highspeed

Fastest

Faster-serving M2.7 endpoint with 204,800 context, always-on thinking and separate API rates.

FastCoding
Legacy
chat

MiniMax

MiniMax M2-her

Best Overall

Legacy dialogue and role-play model with published 64K context and dedicated conversation settings.

DialogueRole-play
Legacy
chat

MiniMax

MiniMax M2.5

Legacy coding and tool-workflow model with 204,800 context and always-on thinking.

CodingReasoning
Legacy
chat

MiniMax

MiniMax M2.5 Highspeed

Legacy faster-serving M2.5 variant with 204,800 context and distinct input/output API rates.

FastCoding
Legacy
chat

MiniMax

MiniMax M2.1

Best for Coding

Legacy multilingual programming and refactoring model with 204,800 context and always-on thinking.

CodingMultilingual
Legacy
chat

MiniMax

MiniMax M2.1 Highspeed

Legacy faster-serving M2.1 endpoint for multilingual code workflows, with 204,800 context.

FastMultilingual
Legacy
chat

MiniMax

MiniMax M2

Original legacy M2 for text, reasoning and tool workflows, with 204,800 context and qualified output limits.

AgenticReasoning
New
chat

Kimi

Kimi K3.1 Pro

Best for Coding

Kimi’s reasoning model for sustained coding, visual analysis and knowledge work, with 1M context and configurable thinking effort.

1M contextReasoning
New
chat

Kimi

Kimi K3.1 Pro High Speed

Best for Coding

Faster-serving K3.1 Pro variant with the same provider-described intelligence, 1M context and separate API pricing.

1M contextHigh speed
New
chat

Kimi

Kimi K3

Best for Coding

Multimodal Kimi with 1M context, always-on thinking and adjustable reasoning effort for coding and knowledge work.

1M contextCoding
New
chat

Kimi

Kimi K2.7 Code

Best for Coding

Coding-focused Kimi with 256K context, visual inputs and always-on thinking for multi-step software work.

256K contextCoding
chat

Kimi

Kimi K2.7 Code HighSpeed

Best for Coding

Faster-serving K2.7 Code endpoint with the same model behavior, 256K context and separately priced API usage.

High speedCoding
chat

Kimi

Kimi K2.6

Best Overall

Multimodal Kimi with 256K context and optional thinking for coding, document analysis and visual review.

256K contextOptional thinking
Retired
chat

Kimi

Kimi K2.5

Historical multimodal Kimi with 256K context, retired on the Kimi platform August 31, 2026. Migration reference for K3.

Historical256K context
New
chat

Cohere

Command A+

Best for Research

Multimodal Cohere MoE with hybrid reasoning, 48-language support and a 128K context window.

Vision48 languages
chat

Cohere

Command A

Best for Research

Text-focused Cohere model for grounded answers and tool workflows, with 256K context and 8K output.

RAG256K context
chat

Cohere

Command A Reasoning

Best for Research

Hybrid text reasoning with optional thinking budgets, 256K context and 32K output for evidence-heavy workflows.

ReasoningResearch
chat

Cohere

Command A Vision

Best for Research

Text and image understanding for documents, tables and charts, with up to 20 images per request and no tool use.

VisionDocuments
chat

Cohere

Command A Translate

Best Overall

Specialized text translation across 23 languages, with separate 8K input and 8K output limits.

Translation23 languages
chat

Cohere

Command R7B

Best Overall

Compact 7B text model for grounded answers and tool workflows, with 128K context and low API token rates.

RAGTool use
chat

Cohere

Command R+

Best for Research

Dated August 2024 model for grounded answers and multi-step tools; distinct from deprecated Command R+ aliases.

RAGCitations
chat

Cohere

Command R

Dated August 2024 text model for cost-conscious grounded answers, citations and tool workflows with 128K context.

RAGTool use
New
chat

Z.ai

GLM-5.3

Best for Coding

Text-only flagship for complex coding and agent workflows with 1M context and always-on reasoning.

1M contextReasoning
New
chat

Z.ai

GLM-5.3-Flash

Best Value

Native multimodal GLM-5 model for images, video, files and text with 1M context and low API token rates.

Multimodal1M context
New
chat

Z.ai

GLM-5.3-FlashX

Fastest

Faster-serving GLM-5.3-Flash tier with native multimodal inputs, 1M context and separately priced API access.

Fast servingMultimodal
New
chat

Z.ai

GLM-5.2

Best Overall

Text model for long-horizon engineering with 1M context, 128K output and configurable thinking.

1M contextLong horizon
New
chat

Z.ai

GLM-5.1

Best Overall

Text model for sustained engineering and iterative agent workflows with 200K context and optional thinking.

200K contextAgentic
chat

Z.ai

GLM-5-Turbo

Fastest

OpenClaw-oriented text model with 200K context; confirm current Turbo endpoint access and API pricing.

FastCoding
chat

Z.ai

GLM-5V-Turbo

Best Overall

Multimodal coding model with 200K context for screenshots and visual workflows; current API rates remain unverified.

VisionFast
chat

Z.ai

GLM-5

Best Overall

Text reasoning and coding model with 200K context, 128K output and optional thinking.

200K contextReasoning
chat

Z.ai

GLM-4.6V

Best Value

Vision model for images, video and documents with 128K context, 32K output and native function calling.

VisionDocuments
chat

Z.ai

GLM-4.7

Best Overall

Previous-generation text model with 200K context, turn-level thinking and coding-oriented tool workflows.

ReasoningFlagship
chat

Z.ai

GLM-4.6

Best for Coding

Text model with 200K context, hybrid thinking and explicitly enabled streaming tool-call arguments.

200K contextCoding
chat

Z.ai

GLM-4.5

Best Overall

General-purpose text model with 128K context, 96K output and hybrid thinking for coding and analysis.

BalancedGeneral purpose
chat

Z.ai

GLM-4.5-Air

Fastest

Lightweight GLM-4.5 text tier with 128K context, hybrid thinking and lower API token rates.

128K contextLightweight
chat

Z.ai

GLM-4.7-FlashX

Best Value

Paid lightweight GLM-4.7 tier for fast text and coding workflows with 200K context and 128K output.

High throughputLow cost
chat

Z.ai

GLM-4.7-Flash

Best Value

Lightweight text model with 200K context and currently free direct API token rates, subject to provider limits.

Free tierLightweight
chat

Z.ai

GLM-4.5-X

Premium high-speed GLM-4.5 text tier with 128K context, hybrid thinking and separate API rates.

Fast serving128K context
chat

Z.ai

GLM-4.5-AirX

Faster-serving lightweight GLM-4.5 tier with 128K context and higher API rates than standard Air.

LightweightFast serving
chat

Z.ai

GLM-4.5V

Visual reasoning model for images, video and documents with 64K context, 16K output and switchable thinking.

Vision64K context
chat

Z.ai

GLM-4.6V-FlashX

Best Value

Paid lightweight vision tier with 128K context, 32K output and native function calling at low API token rates.

VisionLow cost
chat

Z.ai

GLM-4-32B-0414-128K

Best Value

Older 32B text model with 128K context, 16K output and low direct API rates for instruction-following tasks.

Text128K context
Retiring
chat

Xiaomi MiMo

MiMo-V2.5-Pro

Best Overall

Text-focused Xiaomi model with 1M context and deep thinking. Provider-service retirement is scheduled for October 21, 2026; app availability is separate.

1M contextWeb search
Retiring
chat

Xiaomi MiMo

MiMo-V2.5

Xiaomi model for text, images, video and audio understanding. Provider-service retirement is scheduled for October 21, 2026; app availability is separate.

1M contextOmni
New
chat

Alibaba Qwen

Qwen3.7-Max

Best Overall

Text-only Qwen model for coding and complex workflows, with 1M context, thinking support and region-specific API capabilities.

1M contextAgentic coding
New
chat

Alibaba Qwen

Qwen3.7-Plus

Best Overall

Vision-language Qwen model with image and video input, 1M context and hybrid thinking enabled by default.

1M contextMultimodal
chat

Alibaba Qwen

Qwen3.6-Plus

Best Overall

Hosted Qwen Plus model with image and video input, 1M context and configurable thinking; tools depend on the integration and region.

1M contextVision
chat

Alibaba Qwen

Qwen3.6-Flash

Fastest

Qwen vision-language Flash model with 1M context, hybrid thinking and region-specific tool support for bounded workflows.

1M contextTool support
New
chat

Alibaba Qwen

Qwen3 Max

Best Overall

Text-focused Qwen model with 262K context, optional thinking and mode-specific output limits; hosted features vary by region.

262K contextText
chat

Alibaba Qwen

Qwen3 Coder Plus

Best for Coding

Coding-focused Qwen model with 1M context and 65K output; tool availability and token prices depend on the deployment region.

CodingRepo reasoning
chat

Alibaba Qwen

Qwen3 VL Plus

Best for Writing

Qwen vision-language model for images and video, with 262K context, 32K output and region-specific integration limits.

VisionVideo analysis
New
chat

Alibaba Qwen

Qwen3 Next 80B

Fastest

80B MoE with 3B active parameters and 262K native context. This guide distinguishes the confirmed Instruct and Thinking variants.

80B MoEFast
New
chat

Alibaba Qwen

Qwen 3.6

Best Overall

The app’s Qwen 3.6 label maps to qwen3.6-plus: a hosted vision-language model with 1M context and hybrid thinking.

Hybrid thinking1M context
chat

Alibaba Qwen

Qwen 2.5 Coder

Best for Coding

Confirmed Qwen2.5-Coder-32B-Instruct mapping for code generation, repair and review, with long-context support dependent on serving setup.

Coding32B
chat

Alibaba Qwen

Qwen 2.5 72B

Confirmed Qwen2.5-72B-Instruct mapping for multilingual text work, with 131K full context and an 8K generation limit.

General purpose72B
chat

Alibaba Qwen

QwQ 32B

Best for Research

Open-weight Qwen reasoning model with 32.5B parameters and 131K full context; usable limits and API costs depend on the host.

Reasoning32B
New
chat

NVIDIA

Nemotron 3.5 Super VL

NVIDIA’s vision-language reasoner for text, images and visual documents. The app uses paid OpenRouter hosting; context limits vary by serving host.

Vision-languageReasoning
New
chat

NVIDIA

Nemotron 3 Ultra

NVIDIA’s flagship Nemotron reasoner for complex text, code and multi-step analysis, using a paid 256K OpenRouter route.

Reasoning256K context
New
chat

NVIDIA

Nemotron 3 Super

Balanced Nemotron workhorse for text, coding and tool-assisted workflows, using a paid 256K OpenRouter route.

BalancedTool use
New
chat

NVIDIA

Nemotron 3.5 Lightning

Efficiency-focused Nemotron model for low-cost text workflows and rapid iteration, using a paid 256K OpenRouter route.

Efficient256K context
New
chat

NVIDIA

Nemotron 3 Nano

Compact Nemotron model for short replies, extraction and bounded reasoning, using a paid 256K OpenRouter route.

CompactReasoning
New
image

Meta

Muse Image 1.0

Meta image generation and editing through the Responses API, with WebP output in the audited app integration.

Image generationEditing
New
image

Google

Nano Banana 2.1

Google image generation with app controls for aspect ratio and 1K, 2K or 4K output; fallback routing can use another model.

Image generationResolution controls
image

Google

Nano Banana

Original Nano Banana image generation through Lovable AI Gateway; confirm gateway availability separately from Google's lifecycle.

Fast imageCreative
Migration planned
image

Google

Nano Banana 2

Google preview image route with a scheduled app migration on October 29, 2026; provider lifecycle and current routing require verification.

GeminiFast
New
image

Google

Nano Banana 2 Lite

Nano Banana 2 Lite is a lighter, faster Google image model for creative work in the Nano Banana family.

FastImage generation
image

Google

Nano Banana Pro

Google's professional image-generation family; the app audit still names a preview endpoint that requires runtime verification.

ProHigh fidelity
Historical
image

Google

Imagen 4 Fast

Historical Imagen 4 speed tier, removed from the app picker. Read the provider retirement and replacement guide.

FastImagen
Historical
image

Google

Imagen 4

Historical Imagen 4 generation route, retained with lifecycle context and a link to its app replacement.

FlagshipImage
Historical
image

Google

Imagen 4 Ultra

Historical premium Imagen 4 route, retained for comparison and migration rather than current app selection.

UltraHigh quality
New
image

OpenAI

GPT Image 2.6 Sunburst

OpenAI’s newest image generation supports adjustable detail complexity, transparent backgrounds, animated GIF output, and photo editing.

Image generationPhoto editing
New
image

OpenAI

GPT Image 2.6 Flare

OpenAI’s newest image generation supports photo editing, low to high detail complexity, transparent backgrounds, and animated GIFs with adjustable speed.

Image generationPhoto editing
New
image

OpenAI

GPT Image 2.5 Sunburst

GPT Image 2.5 Sunburst is an OpenAI image generation model for turning creative ideas into visuals.

Image generationCreative
New
image

OpenAI

GPT Image 2.5 Flare

GPT Image 2.5 Flare offers another OpenAI image generation option for exploring visual concepts and creative directions.

Image generationCreative
Historical
image

OpenAI

ChatGPT Image Latest

Historical app entry for OpenAI's rolling image alias, with provider deprecation and replacement guidance.

Image
New
image

OpenAI

GPT Image 2

OpenAI image generation and editing pinned to the April 21, 2026 snapshot in the audited app.

FlagshipImage
Snapshot
image

OpenAI

GPT Image 2 (2026-04-21)

Snapshot reference for the same endpoint used by the GPT Image 2 app choice, not an additional picker model.

Image
Historical
image

OpenAI

GPT Image 1.5

Previous-generation OpenAI image model removed from the app picker; provider shutdown is scheduled for December 1, 2026.

FlagshipCreative
Historical
image

OpenAI

GPT Image 1

Historical OpenAI image route with an October 23, 2026 provider shutdown and an app alias to GPT Image 2.5 Flare.

ImageCreative
Historical
image

OpenAI

GPT Image 1 Mini

Older lower-cost OpenAI image model removed from the app picker; provider shutdown is scheduled for December 1, 2026.

Cost-efficientMultimodal
Retired
image

OpenAI

DALL-E 3

Retired OpenAI generation model, retained as a historical reference with migration guidance to current GPT Image routes.

ReliableCreative
New
image

xAI

Grok Imagine 2.0

xAI generation and single-reference editing with app controls for resolution, aspect ratio, quality and image count.

Image generationEditing
New
image

xAI

Grok Imagine Quality

The grok-imagine-image-quality route, formerly labeled Pro on the website, with explicit resolution-based API pricing.

QualityCreative
image

xAI

Grok Imagine

The original Grok Imagine image route, with lower reference output pricing and single-reference editing in the audited app.

CreativeImage
Latest
image

FLUX

FLUX.2 Pro

Black Forest Labs image generation hosted by WaveSpeed for detailed product and editorial visuals.

Image generationDetail
image

FLUX

FLUX.2 Flex

Typography specialist for flexible, prompt-aware image generation.

TypographyFlexible
Latest
image

FLUX

FLUX.2 Turbo

Ultra-fast FLUX.2 generation for rapid creative output.

FastFLUX.2
image

FLUX

FLUX.1 Schnell

Ultra-fast generation model for speed-focused image workflows.

FastSchnell
image

Stability AI

Stable Image Ultra

Flagship model for highest-quality Stable image generation.

FlagshipHigh quality
image

Stability AI

Stable Image Core

Balanced quality and speed for everyday image generation.

BalancedSpeed
image

Stability AI

SD 3.5 Large

8B parameter flagship Stable Diffusion model for image generation.

8BFlagship
image

Stability AI

SD 3.5 Large Turbo

4-step distilled model for high-speed Stable Diffusion generation.

TurboFast
image

Stability AI

SD 3.5 Medium

2.5B parameter model balancing quality and efficiency.

2.5BBalanced
New
image

ByteDance

Seedream 4.5

Next-generation text-to-image model optimized for high-quality output.

Text-to-imageQuality
New
image

ByteDance

Seedream 5.0 Lite

State-of-the-art text-to-image model in a lighter configuration.

LiteText-to-image
New
image

ByteDance

Seedream 4.5 Sequential

A sequential hosting route for consistent visuals; the audited app returns only the first image, not a multi-image set.

SequentialMulti-image
New
image

ByteDance

Seedream 5.0 Lite Sequential

A sequential image route whose host supports sets; app mapping and size compatibility need verification, and only the first image is returned.

SequentialLite
image

ByteDance

Seedream 4.0

ByteDance flagship image generation model for creative production.

FlagshipImage
image

ByteDance

Seedream 4.0 Sequential

Sequential image generation through WaveSpeed; the app sends no image-count control and returns only the first image.

SequentialMulti-image
New
image

Ideogram

Ideogram V3 Quality

Highest-quality V3 model for realistic, detailed image generation.

QualityRealistic
New
image

Ideogram

Ideogram V3 Balanced

Balanced V3 model for realistic output with practical speed.

BalancedRealistic
New
image

Ideogram

Ideogram V3 Turbo

Fastest V3 model for photorealistic image generation.

TurboPhotorealistic
New
image

Ideogram

Ideogram V3 Transparent

Transparent-background PNG generation for production design assets.

TransparentPNG
image

Ideogram

Ideogram V2

WaveSpeed-hosted Ideogram V2 for prompt-led design and lettering; editing features are not exposed by the app route.

TypographyPrompt adherence
image

Ideogram

Ideogram V2 Turbo

A faster hosted Ideogram V2 option for typography and design; the app integration is text-to-image only.

TurboTypography
image

Ideogram

Ideogram V2A

Precise prompt-following model for high-fidelity image generation.

Prompt fidelityImage
image

Ideogram

Ideogram V2A Turbo

Fastest V2A model for high-fidelity text and image output.

TurboText
New
image

Alibaba Qwen

Qwen Image Max

Flagship Qwen image model for highest-quality visual generation.

FlagshipQuality
New
image

Alibaba Qwen

Qwen Image 2512

The dated Qwen Image 2512 endpoint hosted by WaveSpeed for prompt-led image generation and lettering.

Dated variantPrompt adherence
image

Alibaba Qwen

Qwen Image

20B MMDiT next-generation text-to-image model.

20BText-to-image
image

Alibaba Qwen

Jib Mix Qwen Image

A community Qwen-image derivative hosted by WaveSpeed, grouped by its base family rather than an official Alibaba release.

QwenCreative
New
image
HI

Higgsfield

Marketing Studio

Higgsfield's marketing-image workflow with presets and enhancement controls, distinct from a standalone foundation model.

MarketingCreative production
New
video

Google

Gemini Omni 1.2 Flash

Google video generation creates 3–15 second clips with sound from text, a photo, or up to 6 reference images, with resolutions up to 4K.

Text-to-videoPhoto-to-video
New
video

Google

Gemini Omni Flash

Gemini Omni Flash brings fast, multimodal video generation to Google's creative model lineup.

Video generationMultimodal
Latest
video

Google

VEO 3.1

Google's flagship video model with native 1080p generation.

1080pFlagship
Fast
video

Google

VEO 3.1 Fast

Faster VEO 3.1 model for native 1080p video workflows.

Fast1080p
Budget
video

Google

VEO 3.1 Lite

Affordable VEO 3.1 model for 720p and 1080p video generation.

BudgetVideo
video

Google

VEO 3

Google's previous flagship video generation model.

VideoFlagship
video

Google

VEO 3 Fast

Faster VEO 3 model for synchronized video generation.

FastVideo
video

Google

VEO 2

High-quality image-to-video and text-to-video generation.

Image-to-videoText-to-video
video

Runway

Gen-4 Aleph

Source-video editing through AI/ML API, with input requirements and host duration limits explained in the guide.

Video editingSource video
video

Runway

Gen-4 Turbo

Runway image-to-video through AI/ML API; a starting image is required by the audited app workflow.

Image-to-videoTurbo
Legacy alias
video

Runway

Gen-4.5 Turbo

Retained legacy website alias mapping to Gen-4 Turbo in the app; a separate Gen-4.5 Turbo provider model is unverified.

Alias referenceSee Gen-4 Turbo
Reference
video

Runway

Gen-4.5

Runway provider reference. The app's older Gen-4.5 alias routes to Gen-4 Turbo, not a separate Gen-4.5 choice.

Provider referenceVideo
video

Runway

Gen-3a Turbo

Budget-friendly fast video generation model.

BudgetFast
video

Runway

Runway Act Two

Performance transfer using character and driving footage; the full app input flow still needs verification.

Performance transferSource media
video

Pika

Pika 2.2

App-listed Pika video choice with a five-second card label; hosting and version-specific controls remain unverified.

CreativeVideo
video

Pika

Pika 1.5

Older app-listed Pika video choice with a three-second card label; exact proxy capabilities and pricing need confirmation.

VideoApp mapping
video

Luma AI

Ray 2

Luma video generation with provider keyframe and extension workflows; app control support is documented separately.

CinematicVideo
video

Luma AI

Ray 1.5

Retained app label with an unresolved ray2 mapping. Read the routing notice before assuming a distinct Ray 1.5 endpoint.

Mapping unresolvedVideo
New
video

Kling

Kling 4.0

Cinematic video generation through AIML API, with text and image workflow references, a real example and copyable prompts.

CinematicAIML API
New
video

Kling

Kling 2.5 Turbo Pro

Kling 2.5 Turbo Pro for fast, high-quality video generation.

TurboHigh quality
video

Kling

Kling V3 Pro

Kling 3.0 Pro for fast, high-quality video generation.

ProHigh quality
video

Kling

Kling V3 Standard

Kling 3.0 Standard for reliable video generation.

StandardVideo
Latest
video

MiniMax

Hailuo 2.3

MiniMax flagship cinematic video generation.

CinematicFlagship
Fast
video

MiniMax

Hailuo 2.3 Fast

App choice using the Hailuo 2.3 upstream ID with a Fast request flag; separate serving speed and pricing are unverified.

FastCinematic
video

MiniMax

Hailuo 0.2

Hailuo 0.2 is a MiniMax video model in the EZ Ai Assist catalog.

Video
New
video

xAI

Grok Imagine Video 1.5

xAI’s newest video model delivers sharper motion, native 1080p, and sound. Animate a photo or use up to 14 reference images in clips up to 15 seconds.

Native 1080pPhoto animation
New
video

xAI

Grok Imagine Video 1.5 Lite

Lower-priced xAI video generation with text or starting-image input; 1080p output is upscaled from 720p.

Text-to-videoLite
video

xAI

Grok Imagine Video

xAI's original text-to-video generation model.

Text-to-videoCreative
New
video

ByteDance

Seedance 2.0

Seedance 2.0 is a ByteDance video generation model for motion-led creative work.

Video generationMotion
New
video

ByteDance

Seedance 2.5

Seedance 2.5 is the newer Seedance generation in the ByteDance catalog for video creation and motion workflows.

Video generationMotion
New
video

ByteDance

Seedance 1 Pro

ByteDance flagship video model for cinematic generation.

FlagshipCinematic
New
video

ByteDance

Seedance 1.5 Pro

Seedance 1.5 Pro for cinematic, lively video generation.

CinematicPro
New
video

ByteDance

Seedance 1.5 Pro Fast

Faster Seedance 1.5 Pro for quicker video workflows.

FastPro
New
video

ByteDance

Seedance V1 Pro Fast

Coherent multi-shot text-to-video generation with faster output.

Multi-shotFast
New
video

ByteDance

Seedance V1 Pro 480p

Budget 480p text-to-video generation for lightweight workflows.

480pBudget
New
music

Suno

Suno v5.5

Vocal and instrumental songs through aivideoapi, with Suno custom-mode controls and documented integration caveats.

Custom modeaivideoapi
music

Suno

Suno v5

Suno song generation through aivideoapi, with vocal, instrumental and custom-mode guidance.

Custom modeaivideoapi
New
music

MiniMax

MiniMax Music 2.6

Vocal-song generation via WaveSpeed. The audited app sends the main prompt as lyrics, without a separate lyrics input.

Prompt as lyricsWaveSpeed
music

MiniMax

MiniMax Music 2.5

Vocal songs and accompaniment via Replicate, with the app's shared prompt-and-lyrics behavior explained.

Prompt as lyricsReplicate
music

MiniMax

MiniMax Music 1.5

Vocal music via Replicate, with model-specific input limits and prompt-as-lyrics integration caveats.

Prompt as lyricsReplicate
New
music
GL

Google Lyria

Lyria 3.5

Vocal and instrumental music via WaveSpeed, with provider capabilities separated from prompt-only app controls.

Prompt-only controlsWaveSpeed
Legacy
music
GL

Google Lyria

Lyria 002

Legacy instrumental model retained as a distinct app choice. Its reported WaveSpeed route remains unverified.

Instrumental referenceRoute unverified
New
music
GL

Google Lyria

Lyria 3 Pro

Lyria music via WaveSpeed, with documented vocal capabilities and clear limits on the app's exposed controls.

Prompt-only controlsWaveSpeed
New
music
GL

Google Lyria

Lyria 3 Clip

Short-form Lyria music via WaveSpeed. The app's 60-second client request does not establish a 60-second clip.

Prompt-only controlsWaveSpeed
New
music

Stability AI

Stable Audio 3

Stable Audio 3 provider reference with the app's reported prompt-only integration. The exact WaveSpeed music route is unverified.

Music referenceRoute unverified
music

Stability AI

Stable Audio 2.5

Music and sound via Replicate, with an explicit caveat about the audited app's duration parameter.

Timing caveatReplicate
New
music
SO

Sonilo

Sonilo Text-to-Music

Prompt-driven music via WaveSpeed. The app requests 60 seconds; the documented provider range is not an app control.

60s requestedWaveSpeed
music

ElevenLabs

ElevenLabs Music

Music via AIML, with a reported MiniMax Music 2.5 fallback. Provider features and app controls are documented separately.

AIML gatewayFallback disclosed