Best vision

Kimi K2.6

Accounts

Kimi reasoning model for long-horizon research, planning, and tool use

Kimi K2.7 Code

Accounts

Kimi coding model for software agents, refactors, and repository reasoning

MiniMax-M3

Accounts

MiniMax multimodal coding model for long-context reasoning and agent tasks

Qwen 3.7 Plus

Accounts

Qwen vision-language model for visual reasoning, documents, and agent tasks

Kimi K2.6 Fast

Accounts

Kimi reasoning model for long-horizon research, planning, and tool use

Kimi K2.6 Turbo

Accounts

Kimi reasoning model for long-horizon research, planning, and tool use

Kimi K2.7 Code Fast

Accounts

Kimi coding model for software agents, refactors, and repository reasoning

Qwen 3.6 Max Preview

Alibaba

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Qwen3 235B A22B Thinking 2507

Alibaba

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen 3.5 Flash

Alibaba

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen 3.5 Plus

Alibaba

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3.6 27B Thinking

Alibaba

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen 3.6 27B

Alibaba

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3.6 35B-A3B

Alibaba

Open multimodal Qwen MoE for local agents that need vision, audio, and code

Qwen3.6 Flash

Alibaba

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen 3.6 Plus

Alibaba

Earlier Qwen multimodal workhorse for million-token agent and document tasks

Qwen 3.7 Max

Alibaba

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

Qwen 3.7 Plus

Alibaba

Multimodal Qwen workhorse for long-context agents, visual inputs, and coding

Qwen3 VL 235B A22B Instruct

Alibaba

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3 VL Instruct

Alibaba

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3 VL Thinking

Alibaba

Qwen vision-language model for visual reasoning, documents, and agent tasks

Nova 2 Lite

Amazon

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilit

Nova Lite 1.0

Amazon

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...

Nova Lite

Amazon

Efficient model for low-latency assistance, extraction, and routine automation

Nova Premier 1.0

Amazon

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.

Nova Pro 1.0

Amazon

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...

Nova Pro

Amazon

Flagship model for demanding analysis, coding, and production agent workflows

Claude 3.5 Haiku

Anthropic

Fast Claude model for responsive assistance, classification, and lightweight agents

Claude Sonnet 3.5 v2

Anthropic

Balanced Claude model for coding, analysis, agent workflows, and cost control

Claude Sonnet 3.7

Anthropic

Balanced Claude model for coding, analysis, agent workflows, and cost control

Claude 3 Haiku

Anthropic

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark re

Claude Sonnet 3

Anthropic

Balanced Claude model for coding, analysis, agent workflows, and cost control

Claude Fable 5

Anthropic

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning sup

Claude Fable Latest

Anthropic

This model always redirects to the latest model in the Claude Fable family.

Claude Opus 3

Anthropic

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Claude-Haiku-3.5

Anthropic

Fast Claude model for responsive assistance, classification, and lightweight agents

Claude-Haiku-3

Anthropic

Fast Claude model for responsive assistance, classification, and lightweight agents

Anthropic Claude Haiku Latest

Anthropic

This model always redirects to the latest model in the Anthropic Claude Haiku family.

Claude Opus 4.1

Anthropic

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified

Claude Opus 4.5

Anthropic

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal ca

Anthropic: Claude Opus 4.6 (Fast)

Anthropic

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Claude 4.6 Opus Thinking Low

Anthropic

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Claude 4.6 Opus Thinking Max

Anthropic

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Claude 4.6 Opus Thinking Medium

Anthropic

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Claude 4.6 Opus Thinking

Anthropic

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Claude Opus 4.7 (Fast)

Anthropic

Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs: https://platfo

Claude 4.7 Opus Thinking

Anthropic

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Claude Opus 4.7

Anthropic

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stron

Claude Opus 4.8 (Fast)

Anthropic

Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's

Claude Opus 4.8 Thinking

Anthropic

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Claude Opus 4.8

Anthropic

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M

Claude Opus Latest

Anthropic

This model always redirects to the latest model in the Claude Opus family.

Claude-Sonnet-3.5-June

Anthropic

Legacy model retained for compatibility with older integrations

Claude-Sonnet-3.5

Anthropic

Legacy model retained for compatibility with older integrations

Claude-Sonnet-3.7

Anthropic

Balanced Claude model for coding, analysis, agent workflows, and cost control

Claude Sonnet 4.6 Thinking

Anthropic

Balanced Claude model for coding, analysis, agent workflows, and cost control

Claude Sonnet 5 (Free)

Anthropic

Everyday Claude agent model for coding, planning, browsing, and general work

Claude Sonnet 4.6

Anthropic

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex c

Claude Sonnet 5

Anthropic

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reaso

Anthropic Claude Sonnet Latest

Anthropic

This model always redirects to the latest model in the Anthropic Claude Sonnet family.

Multimodal model for analyzing text, images, documents, and rich media

ERNIE-4.5-VL-28B-A3B-Thinking

Baidu

Multimodal reasoning model for visual analysis, planning, and tool use

ERNIE 4.5 VL 28B A3B

Baidu

Multimodal reasoning model for visual analysis, planning, and tool use

ERNIE 4.5 VL 424B A47B

Baidu

ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointl

ERNIE 5.0

Baidu

Multimodal reasoning model for visual analysis, planning, and tool use

Baidu: Qianfan-OCR-Fast

Baidu

OCR model for extracting structured text from documents and screenshots

FLUX.1-Kontext-dev

Black Forest Labs

Image model for prompt-driven generation, editing, and visual design workflows

FLUX.2 Klein 4B

Black Forest Labs

Image model for prompt-driven generation, editing, and visual design workflows

Seed 1.6

Bytedance

Multimodal reasoning model for visual analysis, planning, and tool use

Seed 1.8

Bytedance

Multimodal reasoning model for visual analysis, planning, and tool use

Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate

Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.

Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practi

Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance compar

Seedance 2.0 Fast

Bytedance

Video model for prompt-guided generation, editing, and motion workflows

Seedance 2.0

Bytedance

Video model for prompt-guided generation, editing, and motion workflows

Seedance 2

Bytedance

Video model for prompt-guided generation, editing, and motion workflows

UI-TARS 7B

Bytedance

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, i

GPT-OSS-120B-CS

Cerebras

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Llama-3.1-8B-CS

Cerebras

Open Llama instruction model for multilingual chat, reasoning, and coding

llama-3.3-70b-cs

Cerebras

Legacy model retained for compatibility with older integrations

Legacy model retained for compatibility with older integrations

Legacy model retained for compatibility with older integrations

Gemma 4 26B A4B IT

Cf

Open Gemma instruction model for efficient chat and self-hosted deployments

Llama 3.2 11B Vision Instruct

Cf

Open Llama multimodal model for image understanding and text reasoning

Llama 4 Scout 17B 16E Instruct

Cf

Open Llama with long-context vision for efficient multimodal agents

Kimi K2.6

Cf

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Kimi K2.7 Code

Cf

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Multimodal model for analyzing text, images, documents, and rich media

DeepSeek OCR

Deepseek Ai

OCR model for extracting structured text from documents and screenshots

deepseek-ai/DeepSeek-OCR

Deepseek Ai

OCR model for extracting structured text from documents and screenshots

deepseek/deepseek-ocr-2

DeepSeek

OCR model for extracting structured text from documents and screenshots

DeepSeek-OCR

DeepSeek

OCR model for extracting structured text from documents and screenshots

DeepSeek Reasoner

DeepSeek

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

DeepSeek V3.2 Speciale

DeepSeek

DeepSeek chat model for instruction following, coding, and analysis

Speech generation model for controllable voice, narration, and audio delivery

Speech generation model for controllable voice, narration, and audio delivery

Speech generation model for controllable voice, narration, and audio delivery

DeepSeek-V4-Pro-EL

Empiriolabs

Flagship DeepSeek model for coding, reasoning, and agentic work

DeepSeek-V4-Flash-EL

Empiriolabs

Fast DeepSeek model for efficient chat, coding help, and agent loops

Multimodal reasoning model for visual analysis, planning, and tool use

Kimi-K2.5-FW

Fireworks Ai

Kimi multimodal agent model for visual understanding, coding, and planning

Gemini 2.5 Flash-Lite

Gemini

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

Gemini 2.5 Flash

Gemini

Fast Gemini workhorse for multimodal apps where latency and price matter

Gemini 2.5 Pro

Gemini

Google's proven reasoning model for coding, math, and multimodal analysis

Gemini 3.1 Pro Preview

Gemini

Reasoning-first Gemini preview for agentic coding and complex problem solving

Gemini 3.5 Flash

Gemini

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Gemini 3 Flash Preview

Gemini

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

Google: Gemini 2.0 Flash

Google

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Google: Gemini 2.0 Flash Lite

Google

Low-latency Gemini model for high-volume multimodal and agent workloads

Gemini-2.0-Flash-Lite

Google

Low-latency Gemini model for high-volume multimodal and agent workloads

Gemini-2.0-Flash

Google

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Nano Banana (Gemini 2.5 Flash Image)

Google

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image gene

Google: Gemini 2.5 Flash Lite Preview 09-2025

Google

Low-latency Gemini model for high-volume multimodal and agent workloads

Gemini 2.5 Pro Preview 05-06

Google

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to

Gemini 2.5 Pro Preview 06-05

Google

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to

Nano Banana 2 (Gemini 3.1 Flash Image Preview)

Google

Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed.

Nano Banana 2 (Gemini 3.1 Flash Image)

Google

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combi

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

Google

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual expl

Gemini 3.1 Flash Lite Preview

Google

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2

Gemini 3.1 Flash Lite

Google

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and i

Gemini 3.1 Pro Preview Custom Tools

Google

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-part

Gemini 3.1 Pro (Preview High)

Google

Advanced Gemini model for complex reasoning, coding, and multimodal analysis

Gemini 3.1 Pro (Preview Low)

Google

Advanced Gemini model for complex reasoning, coding, and multimodal analysis

Gemini 3.1 Pro Preview

Google

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage acro

Gemini 3.5 Flash Thinking

Google

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Gemini 3.5 Flash

Google

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficie

Gemini 3 Flash Thinking

Google

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Gemini 3 Flash Preview

Google

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and t

Nano Banana Pro (Gemini 3 Pro Image Preview)

Google

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reas

Nano Banana Pro (Gemini 3 Pro Image)

Google

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reas

Gemini 3 Pro Preview

Google

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

gemini-deep-research

Google

Legacy model retained for compatibility with older integrations

Gemini 3 Pro Preview

Google

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

Google Gemini Flash Latest

Google

This model always redirects to the latest model in the Google Gemini Flash family.

Gemini Flash-Lite Latest

Google

Low-latency Gemini model for high-volume multimodal and agent workloads

Gemini Omni Flash Preview

Google

Omni-modal model for text, vision, audio, and multimodal agent tasks

Google Gemini Pro Latest

Google

This model always redirects to the latest model in the Google Gemini Pro family.

Gemma 3 12B

Google

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improv

Gemma 3 27B

Google

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improv

Gemma 3 4B

Google

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improv

Gemma 3n E2b It

Google

Open Gemma instruction model for efficient chat and self-hosted deployments

Google Gemma 3

Google

Open Gemma instruction model for efficient chat and self-hosted deployments

Gemma 4 26B A4B (free)

Google

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — deli

Gemma 4 26B A4B Thinking

Google

Open Gemma instruction model for efficient chat and self-hosted deployments

Gemma 4 26B A4B

Google

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — deli

Gemma 4 31B IT FP8

Google

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Gemma 4 31B (free)

Google

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking

Gemma 4 31B Thinking

Google

Open Gemma instruction model for efficient chat and self-hosted deployments

Gemma 4 31B

Google

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking

gemma 4 31B turbo TEE

Google

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Gemma 4 E2B IT

Google

Open Gemma instruction model for efficient chat and self-hosted deployments

Gemma 4 E4B IT

Google

Open Gemma instruction model for efficient chat and self-hosted deployments

paligemma

Google

Gemini multimodal model for text, image, audio, video, and document tasks

Imagen-3-Fast

Google

Image model for prompt-driven generation, editing, and visual design workflows

Imagen-3

Google

Image model for prompt-driven generation, editing, and visual design workflows

Imagen-4-Fast

Google

Image model for prompt-driven generation, editing, and visual design workflows

Imagen-4-Ultra

Google

Image model for prompt-driven generation, editing, and visual design workflows

Imagen-4

Google

Image model for prompt-driven generation, editing, and visual design workflows

Lyria 3 Clip Preview

Google

30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...

Lyria 3 Pro Preview

Google

Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality

Lyria

Google

Speech generation model for controllable voice, narration, and audio delivery

Nano-Banana-Pro

Google

Image model for prompt-driven generation, editing, and visual design workflows

Nano-Banana

Google

Image model for prompt-driven generation, editing, and visual design workflows

Veo-2

Google

Video model for prompt-guided generation, editing, and motion workflows

Veo-3.1-Fast

Google

Video model for prompt-guided generation, editing, and motion workflows

Veo-3-Fast

Google

Video model for prompt-guided generation, editing, and motion workflows

Veo-3.1

Google

Video model for prompt-guided generation, editing, and motion workflows

Veo-3

Google

Video model for prompt-guided generation, editing, and motion workflows

Veo 3.1 Fast

Google

Video model for prompt-guided generation, editing, and motion workflows

Veo 3.1 Lite

Google

Video model for prompt-guided generation, editing, and motion workflows

Veo 3.1

Google

Video model for prompt-guided generation, editing, and motion workflows

Grok 4.3

Grok

xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk

MiniMax-M3

Hf Minimaxai

MiniMax multimodal model for long-context coding, perception, and agent planning

Kimi K2.7 Code

Hf Moonshotai

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Qwen vision-language model for visual reasoning, documents, and agent tasks

Image model for prompt-driven generation, editing, and visual design workflows

Image model for prompt-driven generation, editing, and visual design workflows

Image model for prompt-driven generation, editing, and visual design workflows

Image model for prompt-driven generation, editing, and visual design workflows

Multimodal reasoning model for visual analysis, planning, and tool use

Automatic model router for matching prompts to suitable backends and budgets

Automatic model router for matching prompts to suitable backends and budgets

kimi/kimi-k2.5

Kimi

Kimi multimodal agent model for visual understanding, coding, and planning

Kimi K2.6

Kimi

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Image model for prompt-driven generation, editing, and visual design workflows

Image model for prompt-driven generation, editing, and visual design workflows

Video model for prompt-guided generation, editing, and motion workflows

Llama-3.2-11B-Vision-Instruct

Meta

Open Llama multimodal model for image understanding and text reasoning

Llama 3.2 11B Vision Instruct

Meta

Open Llama multimodal model for image understanding and text reasoning

Llama-3.2-90B-Vision-Instruct

Meta

Open Llama multimodal model for image understanding and text reasoning

Llama 3.2 90B Vision Instruct

Meta

Open Llama multimodal model for image understanding and text reasoning

Llama-3.3-70B-Instruct

Meta

Open Llama instruction model for multilingual chat, reasoning, and coding

Llama 4 Maverick 17B 128E Instruct FP8

Meta

Open multimodal Llama model for strong reasoning and fast responses

Llama 4 Maverick 17B 128E Instruct

Meta

Open multimodal Llama model for strong reasoning and fast responses

Llama-4-Maverick-17B-128E-Instruct-FP8

Meta

Open multimodal Llama model for strong reasoning and fast responses

Llama 4 Maverick 17b 128e Instruct

Meta

Open multimodal Llama model for strong reasoning and fast responses

Llama 4 Scout 17B 16E Instruct

Meta

Open multimodal Llama model for long-context analysis and efficient agents

Llama-4-Scout-17B-16E-Instruct-FP8

Meta

Open multimodal Llama model for long-context analysis and efficient agents

Llama Guard 4 12B

Meta

Safety model for policy screening, moderation, and risk-aware routing workflows

Llama 3.2 11B Vision Instruct

Meta

Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and..

Llama 3.2 90B Vision Instruct

Meta

Open Llama multimodal model for image understanding and text reasoning

Llama 4 Maverick Instruct

Meta

Open multimodal Llama model for strong reasoning and fast responses

Llama 4 Scout 17B 16E

Meta

Open multimodal Llama model for long-context analysis and efficient agents

Llama Guard 4 12B

Meta

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content

Muse Spark 1.1

Meta

Open Llama instruction model for multilingual chat, reasoning, and coding

Phi-3.5-vision instruct (128k)

Microsoft

Multimodal reasoning model for visual analysis, planning, and tool use

Phi-4-multimodal-instruct

Microsoft

Multimodal reasoning model for visual analysis, planning, and tool use

MiniMax-01

Minimax

MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per in

MiniMax Latest

Minimax

MiniMax multimodal coding model for long-context reasoning and agent tasks

MiniMax M3 Thinking

Minimax

MiniMax multimodal coding model for long-context reasoning and agent tasks

MiniMax M3

Minimax

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agen

MiniMax-M3

Minimaxai

MiniMax multimodal model for long-context coding, perception, and agent planning

Mistral Medium 3 (25.05)

Mistral Ai

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Mistral Small 3.1

Mistral Ai

Efficient Mistral model for fast chat, extraction, and production assistants

Devstral Small 2

Mistral

Mistral coding agent model for repository tasks and software engineering workflows

Ministral 14B

Mistral

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Mistral Large 3

Mistral

Mistral's largest general model for enterprise agents, coding, and multilingual reasoning

Mistral Large 3

Mistral

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Mistral Large (latest)

Mistral

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Mistral Medium 3

Mistral

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Mistral Medium 3.5 Thinking

Mistral

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Mistral Medium Latest

Mistral

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Mistral Medium (latest)

Mistral

Balanced Mistral model for enterprise assistants, multilingual work, and tools

Mistral Medium 3.1

Mistral

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Mistral Small (latest)

Mistral

Efficient Mistral model for fast chat, extraction, and production assistants

Mistral Small (latest)

Mistral

Efficient Mistral model for fast chat, extraction, and production assistants

Pixtral 12B

Mistral

Mistral vision-language model for image understanding and multimodal chat

Pixtral Large (latest)

Mistral

Mistral's larger vision model for document-heavy image understanding and chat

Pixtral Large (latest)

Mistral

Mistral's larger vision model for document-heavy image understanding and chat

Ministral 3 14B Reasoning 2512

Mistral

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Ministral 3 3B Reasoning 2512

Mistral

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Ministral 3 14B 2512

Mistral

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and

Ministral 3 14B

Mistral

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Ministral 3 3B 2512

Mistral

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

Ministral 3 8B 2512

Mistral

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

Mistral Large 3 675B Instruct 2512

Mistral

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Mistral Large Instruct 2411

Mistral

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Mistral Large 3 2512

Mistral

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apa

Mistral Medium 3.1

Mistral

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at signifi

Mistral Medium 3.5 128B

Mistral

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Mistral Medium 3.5

Mistral

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, a

Mistral Medium 3

Mistral

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-

Mistral Small 4

Mistral

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoni

Mistral Small 3.1 24B

Mistral

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art

Mistral Small 4 119B Thinking

Mistral

Efficient Mistral model for fast chat, extraction, and production assistants

mistral-small-4-119b-2603

Mistral

Efficient Mistral model for fast chat, extraction, and production assistants

Mistral: Pixtral Large 2411

Mistral

Mistral vision-language model for image understanding and multimodal chat

Kimi K2.5

Moonshot

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Kimi K2.6

Moonshot

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Kimi K2.7 Code

Moonshot

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Kimi-K2.5-fast

Moonshotai

Legacy model retained for compatibility with older integrations

Kimi K2.5 TEE

Moonshotai

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Kimi K2.5 Thinking

Moonshotai

Kimi reasoning model for long-horizon research, planning, and tool use

Kimi K2.5

Moonshotai

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued p

Kimi K2.6 Fast

Moonshotai

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Kimi K2.6 TEE

Moonshotai

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Kimi K2.6

Moonshotai

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end

Kimi K2.6 Thinking

Moonshotai

Kimi reasoning model for long-horizon research, planning, and tool use

Kimi K2.7 Code (Free)

Moonshotai

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Kimi K2.7 Code Highspeed

Moonshotai

Lower-latency Kimi Code variant for interactive edits and coding-agent loops

Kimi K2.7 Code

Moonshotai

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native m

Kimi K3

Moonshotai

Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and i

MoonshotAI Kimi Latest

Moonshotai

This model always redirects to the latest model in the MoonshotAI Kimi family.

Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool

Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and

DeepSeek-V3.2

Novita

DeepSeek chat model for instruction following, coding, and analysis

GLM-4.6

Novita

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

glm-4.6v

Novita

GLM vision model for visual reasoning, documents, and multimodal agents

glm-4.7-flash

Novita

Efficient GLM model for fast reasoning, coding, and agent workflows

glm-4.7-n

Novita

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

glm-4.7

Novita

Legacy model retained for compatibility with older integrations

GLM-5

Novita

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

Kimi-K2.5

Novita

Kimi multimodal agent model for visual understanding, coding, and planning

Kimi-K2.6

Novita

Kimi multimodal agent model for visual understanding, coding, and planning

kimi-k2-thinking

Novita

Kimi reasoning model for long-horizon research, planning, and tool use

minimax-m2.1

Novita

MiniMax model for chat, coding, office work, and agentic tasks

Active Speaker Detection

NVIDIA

Nemotron multimodal model for visual reasoning and agentic AI workflows

bevformer

NVIDIA

Nemotron multimodal model for visual reasoning and agentic AI workflows

cosmos-predict1-5b

NVIDIA

Video model for prompt-guided generation, editing, and motion workflows

cosmos-transfer1-7b

NVIDIA

Video model for prompt-guided generation, editing, and motion workflows

cosmos-transfer2.5-2b

NVIDIA

Video model for prompt-guided generation, editing, and motion workflows

Llama-3.3-70B-Instruct

NVIDIA

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

llama-nemotron-embed-vl-1b-v2

NVIDIA

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

llama-nemotron-rerank-vl-1b-v2

NVIDIA

Reranking model for improving retrieval quality in search and recommendation systems

magpie-tts-zeroshot

NVIDIA

Speech generation model for controllable voice, narration, and audio delivery

Nemotron 3.5 Content Safety (free)

NVIDIA

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses fr

Nemotron 3 Nano Omni (free)

NVIDIA

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, vide

Nemotron 3 Nano Omni 30B A3B Reasoning

NVIDIA

Open Nemotron omni model combining reasoning with text, vision, and audio

Nemotron Nano 12B 2 VL (free)

NVIDIA

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-M

Nvidia Nemotron Nano 12B V2 VL

NVIDIA

Nemotron multimodal model for visual reasoning and agentic AI workflows

nemotron-voicechat

NVIDIA

Nemotron multimodal model for visual reasoning and agentic AI workflows

sparsedrive

NVIDIA

Nemotron multimodal model for visual reasoning and agentic AI workflows

streampetr

NVIDIA

Nemotron multimodal model for visual reasoning and agentic AI workflows

synthetic-video-detector

NVIDIA

Video model for prompt-guided generation, editing, and motion workflows

DALL-E-3

OpenAI

Image model for prompt-driven generation, editing, and visual design workflows

ChatGPT-4o-Latest

OpenAI

Legacy model retained for compatibility with older integrations

GPT-3.5-Turbo-Raw

OpenAI

Compact GPT model for low-latency assistance and high-volume workloads

GPT-4.1 Mini

OpenAI

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.

GPT-4.1 Nano

OpenAI

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

GPT-4.1

OpenAI

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token

GPT-4-Classic

OpenAI

Legacy model retained for compatibility with older integrations

GPT-4-Classic-0314

OpenAI

Legacy model retained for compatibility with older integrations

GPT-4 Turbo

OpenAI

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

GPT-4o (2024-05-13)

OpenAI

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gp

GPT-4o (2024-08-06)

OpenAI

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.

GPT-4o (2024-11-20)

OpenAI

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better

GPT-4o-Aug

OpenAI

GPT model for general reasoning, writing, coding, and tool-assisted tasks

GPT-4o-mini (2024-07-18)

OpenAI

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is m

GPT-5.1 Chat

OpenAI

GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning

GPT-5.1-Codex-Max

OpenAI

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasonin

GPT-5.1-Codex-Mini

OpenAI

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

GPT-5.1-Codex

OpenAI

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, indepe

GPT-5.1 Instant

OpenAI

Compact GPT model for low-latency assistance and high-volume workloads

GPT 5.1 Thinking

OpenAI

Image model for prompt-driven generation, editing, and visual design workflows

GPT-5.1

OpenAI

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style

GPT-5.2 Chat

OpenAI

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning

GPT-5.2-Codex

OpenAI

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, in

GPT-5.2-Instant

OpenAI

Compact GPT model for low-latency assistance and high-volume workloads

GPT-5.2 Pro

OpenAI

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that requi

GPT-5.3 Chat (latest)

OpenAI

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

GPT-5.2

OpenAI

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate co

GPT-5.3 Chat

OpenAI

GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with be

GPT-5.3-Codex-Spark

OpenAI

Coding-optimized GPT model for repository edits, reviews, and agentic software work

GPT-5.3-Instant

OpenAI

Compact GPT model for low-latency assistance and high-volume workloads

GPT-5.3-Codex

OpenAI

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional k

GPT-5.4 Image 2

OpenAI

[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multim

GPT-5.4 Mini

OpenAI

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong perfor

GPT-5.4 Nano

OpenAI

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is

GPT-5.4 Pro

OpenAI

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token

GPT-5.4

OpenAI

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for.

GPT-5.5 Instant

OpenAI

Compact GPT model for low-latency assistance and high-volume workloads

GPT-5.5 Pro

OpenAI

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K

GPT-5.5

OpenAI

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on ha

GPT-5.6 Luna Pro

OpenAI

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses o

GPT-5.6 Luna

OpenAI

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic

GPT-5.6 Sol Pro

OpenAI

GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on c

GPT-5.6 Sol

OpenAI

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and mult

GPT-5.6 Terra Pro

OpenAI

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality response

GPT-5.6 Terra

OpenAI

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning

GPT-5 Chat (latest)

OpenAI

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

GPT-5 Chat

OpenAI

GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.

GPT-5 Codex

OpenAI

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independen

GPT-5 Image Mini

OpenAI

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image gener

GPT-5 Image

OpenAI

[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code

GPT-5 Mini

OpenAI

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but wit

GPT-5 Nano

OpenAI

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasonin

GPT-5 Pro

OpenAI

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step

GPT-5

OpenAI

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reas

GPT Chat Latest

OpenAI

GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updat

OpenAI GPT Latest

OpenAI

This model always redirects to the latest model in the OpenAI GPT family.

OpenAI GPT Mini Latest

OpenAI

This model always redirects to the latest model in the OpenAI GPT Mini family.

o1-pro

OpenAI

The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and pr

o3 Deep Research

OpenAI

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds

o1

OpenAI

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learn

o3 Pro

OpenAI

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and pro

o4 Mini Deep Research

OpenAI

o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks. Note: This model always uses the 'web_search'

o4 Mini

OpenAI

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports

o4 Mini High

OpenAI

OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fa

Sora-2-Pro

OpenAI

Video model for prompt-guided generation, editing, and motion workflows

Sora-2

OpenAI

Video model for prompt-guided generation, editing, and motion workflows

Auto Router (Beta) is a task-aware router from OpenRouter. It classifies each request, then routes it the [most popular model](/rankings#task-spend) for that task based on aggregat

Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output. To see which model was used,...

The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for model

Automatic model router for matching prompts to suitable backends and budgets

Multimodal model for analyzing text, images, documents, and rich media

Multimodal model for analyzing text, images, documents, and rich media

Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language q

Sonar Pro

Perplexity

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sona

Sonar Pro Search

Perplexity

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis.

Sonar Reasoning Pro

Perplexity

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sona

Sonar

Perplexity

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightwei

Automatic model router for matching prompts to suitable backends and budgets

claude-code

Poetools

Claude model for careful reasoning, writing, coding, and tool use

Pro/moonshotai/Kimi-K2.5

Pro

Kimi multimodal agent model for visual understanding, coding, and planning

Pro/moonshotai/Kimi-K2.6

Pro

Kimi multimodal agent model for visual understanding, coding, and planning

Qwen 2.5 7B Vision Instruct

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen Image Edit

Qwen

Image model for prompt-driven generation, editing, and visual design workflows

Qwen Image

Qwen

Image model for prompt-driven generation, editing, and visual design workflows

Qwen 2.5 VL 32B Instruct

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen2.5 VL 72B Instruct

Qwen

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts

Qwen3.5 122B A10B NVFP4

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3.5-122B-A10B

Qwen

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving

Qwen3.5-27B

Qwen

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its ov

Qwen3.5-35B-A3B

Qwen

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model,

Qwen3.5 397B A17B TEE

Qwen

Large open Qwen multimodal MoE for visual agents and long technical tasks

Qwen3.5 397B A17B Thinking

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3.5 397B A17B

Qwen

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, ach

Qwen/Qwen3.5-4B

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3.5-9B

Qwen

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architectur

Qwen3.5-Flash

Qwen

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving hi

Qwen3.5 Plus 2026-02-15

Qwen

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achievin

Qwen3.5 Plus 2026-04-20

Qwen

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window.

Qwen3.5 Plus Thinking

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3.5 Plus

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3.6 27B FP8

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3.6 27B TEE

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3.6 27B

Qwen

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image

Qwen 3.6 35B A3B FP8

Qwen

Open multimodal Qwen MoE for local agents that need vision, audio, and code

Qwen3.6 35B A3B

Qwen

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of

Qwen3.6 35B A3B Thinking

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3.6 Flash

Qwen

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in..

Qwen3.6 Plus

Qwen

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance infe

Qwen3.7 Plus

Qwen

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensiv

Qwen3 Omni 30B A3B Instruct

Qwen

Qwen omni model for text, vision, audio, and multimodal agent tasks

Qwen3 Omni 30B A3B Thinking

Qwen

Qwen omni model for text, vision, audio, and multimodal agent tasks

Qwen3-VL 235B

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3 VL 235B A22B Instruct

Qwen

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets gen

Qwen3 VL 235B A22B Thinking

Qwen

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimo

Qwen3 VL 30B A3B Instruct

Qwen

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-foll

Qwen3 VL 32B Instruct

Qwen

Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion para

Qwen3 VL 30B A3B Thinking

Qwen

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM

Qwen3 VL 8B Instruct

Qwen

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features

Qwen/Qwen3-VL-32B-Thinking

Qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen3 VL 8B Thinking

Qwen

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, an

Qwen3-VL Embedding 8B

Qwen

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to del

Video model for prompt-guided generation, editing, and motion workflows

Video model for prompt-guided generation, editing, and motion workflows

Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model t

Efficient model for low-latency assistance, extraction, and routine automation

Image model for prompt-driven generation, editing, and visual design workflows

Stealth: Claude Opus 4.7 (20% off)

Stealth

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Stealth: Claude Sonnet 4.6 (20% off)

Stealth

Balanced Claude model for coding, analysis, agent workflows, and cost control

Stealth: Claude Opus 4.6 (20% off)

Stealth

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Stepfun-Ai/Gelab Zero 4b Preview

Stepfun Ai

StepFun flash model for efficient multimodal reasoning, coding, and tool use

Newer StepFun flash model for faster agents, coding, and multimodal prompts

Step 3.7 Flash (Free)

Stepfun

Newer StepFun flash model for faster agents, coding, and multimodal prompts

Step 3.7 Flash Thinking

Stepfun

StepFun flash model for efficient multimodal reasoning, coding, and tool use