Every model, unmetered

Claude Opus 5 (Fast)

anthropic/claude-opus-5-fast

Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular

Claude Opus 5

anthropic/claude-opus-5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end

MoonshotAI: Kimi K3

moonshotai/kimi-k3

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and lo

Claude Opus 5 (batch)

anthropic/claude-opus-5:batch

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end

Qwen: Qwen3.8 2.4T A95B

qwen/qwen3.8-2.4t-a95b

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max

Qwen: Qwen3.8 Max

qwen/qwen3.8-max

Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multim

SpaceXAI: Grok 4.6

x-ai/grok-4.6

Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

Z.ai: GLM Latest

~z-ai/glm-latest

This model always redirects to the latest GLM model from Z.ai.

Z.ai: GLM 5.3

z-ai/glm-5.3

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text in

Meta: Muse Spark 1.1

meta/muse-spark-1.1

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents

Meta: Muse Spark 1.2

meta/muse-spark-1.2

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents,

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It i

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It i

Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language an

Google: Gemini 3.6 Flash

google/gemini-3.6-flash

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produc

DeepSeek: DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it

Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming t

Qwen: Qwen3.8 27B

qwen/qwen3.8-27b

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal i

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software d

Google: Gemini 3.5 Flash Lite

google/gemini-3.5-flash-lite

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute foc

Google: Gemini 3.6 Flash (batch)

google/gemini-3.6-flash:batch

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produc

Google: Gemini 3.7 Flash

google/gemini-3.7-flash

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for

Meta: Muse Glimmer 30B

meta/muse-glimmer-30b

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for auto

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total

LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for codin

Google: Gemini 3.5 Flash Lite (batch)

google/gemini-3.5-flash-lite:batch

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute foc

Google: Gemini 3.7 Flash (batch)

google/gemini-3.7-flash:batch

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for

DeepSeek: DeepSeek V4 Flash Vision Exp

deepseek/deepseek-v4-flash-vision-exp

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v

KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it

DeepSeek: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-traine

Tencent: Hy-MT2-30B-A3B

tencent/hy-mt2-30b-a3b

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and mino

Tencent: Hy-MT2-7B

tencent/hy-mt2-7b

Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pai

Meta: Muse Spark 1.2 Contributor

meta/muse-spark-1.2-contributor

Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’

NVIDIA: Nemotron 3.5 Lightning

nvidia/nemotron-3.5-lightning

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for

Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B

Tencent: Hy-MT2-1.8B

tencent/hy-mt2-1.8b

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-

Qwen: Qwen3.7 Flash

qwen/qwen3.7-flash

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer int

Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agenti

DeepSeek V4 Flash Latest

~deepseek/deepseek-v4-flash-latest

This model always redirects to the latest model in the DeepSeek V4 Flash family.

Ling-3.0-flash

inclusionai/ling-3.0-flash

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model i

Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the ligh

LiquidAI: LFM2.5-2.6B (free)

liquid/lfm-2.5-2.6b:free

LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing

NVIDIA: Nemotron 3.5 Lightning (free)

nvidia/nemotron-3.5-lightning:free

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for

Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B

Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It i

Auto Router (Beta)

openrouter/auto-beta

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

OpenAI: o1-pro

openai/o1-pro

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

OpenAI: o1-pro (batch)

openai/o1-pro:batch

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

OpenAI: GPT-5.4 Pro

openai/gpt-5.4-pro

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, hi

OpenAI: GPT-5.5 Pro

openai/gpt-5.5-pro

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+

OpenAI: GPT-5.2 Pro

openai/gpt-5.2-pro

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 i

Anthropic: Claude Opus 4.7 (Fast)

anthropic/claude-opus-4.7-fast

Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing. Learn

OpenAI: GPT-5 Pro

openai/gpt-5-pro

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

OpenAI: GPT-5.4 Pro (batch)

openai/gpt-5.4-pro:batch

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, hi

OpenAI: GPT-5.5 Pro (batch)

openai/gpt-5.5-pro:batch

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+

OpenAI: o3 Pro

openai/o3-pro

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

OpenAI: GPT-5.2 Pro (batch)

openai/gpt-5.2-pro:batch

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 i

Anthropic: Claude Opus 4

anthropic/claude-opus-4

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running t

Anthropic: Claude Opus 4.1

anthropic/claude-opus-4.1

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.

OpenAI: GPT-4

openai/gpt-4

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than p

OpenAI: o1

openai/o1

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trai

OpenAI: GPT-5 Pro (batch)

openai/gpt-5-pro:batch

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

Anthropic: Claude Fable Latest

~anthropic/claude-fable-latest

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

Anthropic: Claude Fable 5

anthropic/claude-fable-5

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

Anthropic: Claude Opus 4.8 (Fast)

anthropic/claude-opus-4.8-fast

Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regu

OpenAI: o3 Pro (batch)

openai/o3-pro:batch

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

Anthropic: Claude Opus 4.1 (batch)

anthropic/claude-opus-4.1:batch

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.

OpenAI: GPT-4 Turbo

openai/gpt-4-turbo

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

OpenAI: GPT-4 Turbo Preview

openai/gpt-4-turbo-preview

The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training

OpenAI: o1 (batch)

openai/o1:batch

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trai

OpenAI: GPT-5.5

openai/gpt-5.5

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliabil

OpenAI: GPT Chat Latest

openai/gpt-chat-latest

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

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

Anthropic: Claude Opus Latest

~anthropic/claude-opus-latest

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

Anthropic: Claude Fable 5 (batch)

anthropic/claude-fable-5:batch

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

Anthropic: Claude Opus 4.5

anthropic/claude-opus-4.5

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon comp

Anthropic: Claude Opus 4.6

anthropic/claude-opus-4.6

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire wo

Anthropic: Claude Opus 4.7

anthropic/claude-opus-4.7

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

Anthropic: Claude Opus 4.8

anthropic/claude-opus-4.8

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

OpenAI: GPT-5.4 Image 2

openai/gpt-5.4-image-2

[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

OpenAI: GPT-4 Turbo (batch)

openai/gpt-4-turbo:batch

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

OpenAI: GPT-4o (2024-05-13)

openai/gpt-4o-2024-05-13

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence

OpenAI: GPT-5 Image

openai/gpt-5-image

[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offe

Anthropic: Claude Sonnet 4

anthropic/claude-sonnet-4

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with im

Anthropic: Claude Sonnet 4.5

anthropic/claude-sonnet-4.5

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state

Anthropic: Claude Sonnet 4.6

anthropic/claude-sonnet-4.6

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It ex

Perplexity: Sonar Pro

perplexity/sonar-pro

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-br

Perplexity: Sonar Pro Search

perplexity/sonar-pro-search

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is desi

OpenAI: GPT-5.4

openai/gpt-5.4

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 (92

OpenAI: GPT-5.5 (batch)

openai/gpt-5.5:batch

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliabil

OpenAI: GPT-5.2

openai/gpt-5.2

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. I

OpenAI: GPT-5.2 Chat

openai/gpt-5.2-chat

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

OpenAI: GPT-5.2-Codex

openai/gpt-5.2-codex

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 inter

OpenAI: GPT-5.3-Codex

openai/gpt-5.3-codex

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

MoonshotAI Kimi Latest

~moonshotai/kimi-latest

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

Amazon: Nova Premier 1.0

amazon/nova-premier-v1

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

Anthropic: Claude Opus 4.5 (batch)

anthropic/claude-opus-4.5:batch

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon comp

Anthropic: Claude Opus 4.6 (batch)

anthropic/claude-opus-4.6:batch

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire wo

Anthropic: Claude Opus 4.7 (batch)

anthropic/claude-opus-4.7:batch

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

Anthropic: Claude Opus 4.8 (batch)

anthropic/claude-opus-4.8:batch

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

Google Gemini Pro Latest

~google/gemini-pro-latest

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

Google: Nano Banana Pro (Gemini 3 Pro Image)

google/gemini-3-pro-image

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

Google: Nano Banana Pro (Gemini 3 Pro Image Preview)

google/gemini-3-pro-image-preview

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

Google: Gemini 3.1 Pro Preview

google/gemini-3.1-pro-preview

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliabil

Google: Gemini 3.1 Pro Preview Custom Tools

google/gemini-3.1-pro-preview-customtools

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

OpenAI: GPT-5.6 Terra

openai/gpt-5.6-terra

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

OpenAI: GPT-5.6 Terra Pro

openai/gpt-5.6-terra-pro

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`

Cohere: Command A

cohere/command-a

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multili

Cohere: Command R+ (08-2024)

cohere/command-r-plus-08-2024

command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower late

OpenAI: GPT-4o

openai/gpt-4o

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence

OpenAI: GPT-4o (2024-08-06)

openai/gpt-4o-2024-08-06

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_

OpenAI: GPT-4o (2024-11-20)

openai/gpt-4o-2024-11-20

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve r

OpenAI: GPT Audio

openai/gpt-audio

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural soundi

Anthropic Claude Sonnet Latest

~anthropic/claude-sonnet-latest

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

OpenAI GPT Latest

~openai/gpt-latest

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

Anthropic: Claude Sonnet 5

anthropic/claude-sonnet-5

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

OpenAI: GPT-5.6 Sol

openai/gpt-5.6-sol

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 part

OpenAI: GPT-5.6 Sol Pro

openai/gpt-5.6-sol-pro

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

Google: Gemini 2.5 Pro

google/gemini-2.5-pro

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs

Google: Gemini 2.5 Pro Preview 06-05

google/gemini-2.5-pro-preview

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs

Google: Gemini 2.5 Pro Preview 05-06

google/gemini-2.5-pro-preview-05-06

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs

OpenAI: GPT-5

openai/gpt-5

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for comp

OpenAI: GPT-5.1

openai/gpt-5.1

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence,

OpenAI: GPT-5.1-Codex

openai/gpt-5.1-codex

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interacti

OpenAI: GPT-5.1-Codex-Max

openai/gpt-5.1-codex-max

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based o

Google: Gemini 3.5 Flash

google/gemini-3.5-flash

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

OpenAI: GPT-4.1

openai/gpt-4.1

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context r

OpenAI: o3

openai/o3

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It als

Perplexity: Sonar Deep Research

perplexity/sonar-deep-research

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autono

Perplexity: Sonar Reasoning Pro

perplexity/sonar-reasoning-pro

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-br

Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative gene

Anthropic: Claude Sonnet 4.5 (batch)

anthropic/claude-sonnet-4.5:batch

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state

Anthropic: Claude Sonnet 4.6 (batch)

anthropic/claude-sonnet-4.6:batch

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It ex

Mistral: Mistral Medium 3.5

mistralai/mistral-medium-3-5

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 d

OpenAI: GPT-5.4 (batch)

openai/gpt-5.4:batch

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 (92

xAI: Grok Latest

~x-ai/grok-latest

This model always redirects to the latest Grok model from xAI.

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthrop

Mistral Large

mistralai/mistral-large

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels a

Mistral Large 2407

mistralai/mistral-large-2407

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at

Mistral: Mixtral 8x22B Instruct

mistralai/mixtral-8x22b-instruct

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141

SpaceXAI: Grok 4.5

x-ai/grok-4.5

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

OpenAI: GPT-5.2 (batch)

openai/gpt-5.2:batch

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. I

Qwen: Qwen3.6 Max Preview

qwen/qwen3.6-max-preview

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately

Google: Gemini 3.1 Pro Preview (batch)

google/gemini-3.1-pro-preview:batch

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliabil

OpenAI: GPT-3.5 Turbo 16k

openai/gpt-3.5-turbo-16k

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request

OpenAI: GPT-5.6 Terra Pro (batch)

openai/gpt-5.6-terra-pro:batch

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`

OpenAI: GPT-5.6 Terra (batch)

openai/gpt-5.6-terra:batch

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

Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-lea

OpenAI: GPT-4o (batch)

openai/gpt-4o:batch

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence

Anthropic Claude Haiku Latest

~anthropic/claude-haiku-latest

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

Anthropic: Claude Haiku 4.5

anthropic/claude-haiku-4.5

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latenc

Anthropic: Claude Sonnet 5 (batch)

anthropic/claude-sonnet-5:batch

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

OpenAI: GPT-5.6 Sol Pro (batch)

openai/gpt-5.6-sol-pro:batch

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

OpenAI: GPT-5.6 Sol (batch)

openai/gpt-5.6-sol:batch

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 part

Qwen: Qwen3.7 Max

qwen/qwen3.7-max

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads

Z.ai: GLM 5.2 (batch)

z-ai/glm-5.2:batch

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long

Google: Gemini 2.5 Pro (batch)

google/gemini-2.5-pro:batch

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs

OpenAI: GPT-5 Codex (batch)

openai/gpt-5-codex:batch

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive d

OpenAI: GPT-5 (batch)

openai/gpt-5:batch

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for comp

OpenAI: GPT-5.1 (batch)

openai/gpt-5.1:batch

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence,

OpenAI: o3 Mini

openai/o3-mini

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and co

OpenAI: o3 Mini High

openai/o3-mini-high

OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language

OpenAI: o4 Mini

openai/o4-mini

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimoda

OpenAI: o4 Mini High

openai/o4-mini-high

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

OpenAI GPT Mini Latest

~openai/gpt-mini-latest

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

Google: Gemini 3.5 Flash (batch)

google/gemini-3.5-flash:batch

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

OpenAI: GPT-5.4 Mini

openai/gpt-5.4-mini

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

Z.ai: GLM 5 Turbo

z-ai/glm-5-turbo

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenar

Z.ai: GLM 5V Turbo

z-ai/glm-5v-turbo

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively han

OpenAI: GPT-4.1 (batch)

openai/gpt-4.1:batch

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context r

OpenAI: o3 (batch)

openai/o3:batch

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It als

MoonshotAI: Kimi K2.6

moonshotai/kimi-k2.6

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-age

MoonshotAI: Kimi K2.7 Code (batch)

moonshotai/kimi-k2.7-code:batch

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 reliabl

Qwen: Qwen3 Max

qwen/qwen3-max

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual sup

Qwen: Qwen3 Max Thinking

qwen/qwen3-max-thinking

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-st

OpenAI: GPT-5 Image Mini

openai/gpt-5-image-mini

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

Qwen: Qwen3 VL 235B A22B Thinking

qwen/qwen3-vl-235b-a22b-thinking

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

NVIDIA: Nemotron 3 Ultra

nvidia/nemotron-3-ultra-550b-a55b

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE

NVIDIA: Nemotron 3 Ultra (batch)

nvidia/nemotron-3-ultra-550b-a55b:batch

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE

Qwen: Qwen3.5 397B A17B

qwen/qwen3.5-397b-a17b

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism wit

MoonshotAI: Kimi K2.7 Code

moonshotai/kimi-k2.7-code

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 reliabl

Z.ai: GLM 5.1

z-ai/glm-5.1

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous mode

Z.ai: GLM 5.2

z-ai/glm-5.2

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long

Nous: Hermes 4 405B

nousresearch/hermes-4-405b

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode,

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user reque

Amazon: Nova Pro 1.0

amazon/nova-pro-v1

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 ran

Qwen: Qwen3 Coder Plus

qwen/qwen3-coder-plus

Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing

SpaceXAI: Grok 4.20

x-ai/grok-4.20

Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallu

SpaceXAI: Grok 4.20 Multi-Agent

x-ai/grok-4.20-multi-agent

Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in par

SpaceXAI: Grok 4.3

x-ai/grok-4.3

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruc

Qwen: Qwen3.6 27B

qwen/qwen3.6-27b

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimo

Google: Gemini 3 Flash Preview

google/gemini-3-flash-preview

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

Google: Nano Banana 2 (Gemini 3.1 Flash Image)

google/gemini-3.1-flash-image

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

Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)

google/gemini-3.1-flash-image-preview

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 P

OpenAI: GPT-3.5 Turbo Instruct

openai/gpt-3.5-turbo-instruct

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2

DeepSeek: R1

deepseek/deepseek-r1

DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B param

MoonshotAI: Kimi K2 0905

moonshotai/kimi-k2-0905

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model deve

MoonshotAI: Kimi K2 Thinking

moonshotai/kimi-k2-thinking

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.

Anthropic: Claude Haiku 4.5 (batch)

anthropic/claude-haiku-4.5:batch

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latenc

OpenAI: GPT-3.5 Turbo (older v0613)

openai/gpt-3.5-turbo-0613

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional

OpenAI: GPT Audio Mini

openai/gpt-audio-mini

A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better v

SpaceXAI: Grok Build 0.1

x-ai/grok-build-0.1

Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image i

MoonshotAI: Kimi K2 0711

moonshotai/kimi-k2

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters wi

Z.ai: GLM 4.5

z-ai/glm-4.5

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) archite

Amazon: Nova 2 Lite

amazon/nova-2-lite-v1

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

Google: Gemini 2.5 Flash

google/gemini-2.5-flash

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scient

Google: Nano Banana (Gemini 2.5 Flash Image)

google/gemini-2.5-flash-image

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 un

Morph: Morph V3 Large

morph/morph-v3-large

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model re

MiniMax: MiniMax M1

minimax/minimax-m1

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid

OpenAI: o3 Mini High (batch)

openai/o3-mini-high:batch

OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language

OpenAI: o3 Mini (batch)

openai/o3-mini:batch

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and co

OpenAI: o4 Mini High (batch)

openai/o4-mini-high:batch

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

OpenAI: o4 Mini (batch)

openai/o4-mini:batch

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimoda

MoonshotAI: Kimi K2.5

moonshotai/kimi-k2.5

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

DeepSeek: R1 0528

deepseek/deepseek-r1-0528

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and w

OpenAI: GPT-5.4 Mini (batch)

openai/gpt-5.4-mini:batch

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

Qwen: Qwen3 30B A3B Thinking 2507

qwen/qwen3-30b-a3b-thinking-2507

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step

Qwen: Qwen3 VL 30B A3B Thinking

qwen/qwen3-vl-30b-a3b-thinking

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

Qwen: Qwen3 235B A22B Thinking 2507

qwen/qwen3-235b-a22b-thinking-2507

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tas

Z.ai: GLM 5

z-ai/glm-5

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expe

Z.ai: GLM 4.6

z-ai/glm-4.6

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128

Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tensio

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of

Mistral: Mistral Medium 3

mistralai/mistral-medium-3

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly redu

Mistral: Mistral Medium 3.1

mistralai/mistral-medium-3.1

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to delive

Z.ai: GLM 4.5V

z-ai/glm-4.5v

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B

Qwen: Qwen3.5-122B-A10B

qwen/qwen3.5-122b-a10b

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a spa

Qwen: Qwen3 VL 8B Thinking

qwen/qwen3-vl-8b-thinking

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reason

Qwen: Qwen3 235B A22B

qwen/qwen3-235b-a22b

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It support

Qwen: Qwen3.6 Plus

qwen/qwen3.6-plus

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling stro

Google Gemini Flash Latest

~google/gemini-flash-latest

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

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

Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noti

OpenAI: GPT-5 Mini

openai/gpt-5-mini

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

OpenAI: GPT-5.1-Codex-Mini

openai/gpt-5.1-codex-mini

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

DeepSeek: DeepSeek V3.1

deepseek/deepseek-chat-v3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt

Z.ai: GLM 4.7

z-ai/glm-4.7

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step r

Qwen: Qwen3 VL 235B A22B Instruct

qwen/qwen3-vl-235b-a22b-instruct

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images a

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from

Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collabor

Qwen: Qwen3.5 Plus 2026-04-20

qwen/qwen3.5-plus-20260420

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text

Mistral: Mistral Large 3 2512

mistralai/mistral-large-2512

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters

Morph: Morph V3 Fast

morph/morph-v3-fast

Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prom

Nous: Hermes 3 405B Instruct

nousresearch/hermes-3-llama-3.1-405b

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplayi

OpenAI: GPT-3.5 Turbo

openai/gpt-3.5-turbo

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional

Perplexity: Sonar

perplexity/sonar

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

OpenAI: GPT-4.1 Mini

openai/gpt-4.1-mini

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 mil

Arcee AI: Virtuoso Large

arcee-ai/virtuoso-large

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and ente

Qwen: Qwen3.5 Plus 2026-02-15

qwen/qwen3.5-plus-02-15

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sp

Qwen: Qwen2.5 VL 72B Instruct

qwen/qwen2.5-vl-72b-instruct

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

Qwen: Qwen3.5-27B

qwen/qwen3.5-27b

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

Google: Gemini 3 Flash Preview (batch)

google/gemini-3-flash-preview:batch

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

Google: Gemini 3.1 Flash Lite

google/gemini-3.1-flash-lite

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, im

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

google/gemini-3.1-flash-lite-image

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity develo

Google: Gemini 3.1 Flash Lite Preview

google/gemini-3.1-flash-lite-preview

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

Sao10K: Llama 3.1 Euryale 70B v2.2

sao10k/l3.1-euryale-70b

Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70

Baidu: ERNIE 4.5 VL 424B A47B

baidu/ernie-4.5-vl-424b-a47b

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 47

Qwen2.5 Coder 32B Instruct

qwen/qwen-2.5-coder-32b-instruct

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the follow

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

Qwen: Qwen3.7 Plus

qwen/qwen3.7-plus

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 serie

DeepSeek: R1 Distill Llama 70B

deepseek/deepseek-r1-distill-llama-70b

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), usi

DeepSeek: DeepSeek V4 Pro 0423

deepseek/deepseek-v4-pro

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting

Anthropic: Claude 3 Haiku

anthropic/claude-3-haiku

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

KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineer

MiniMax: MiniMax M2-her

minimax/minimax-m2-her

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conve

MiniMax: MiniMax M2.1

minimax/minimax-m2.1

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application develop

MiniMax: MiniMax M3

minimax/minimax-m3

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context win

MiniMax: MiniMax M3 (batch)

minimax/minimax-m3:batch

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context win

Qwen: Qwen3.5-35B-A3B

qwen/qwen3.5-35b-a3b

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

OpenAI: GPT-5.4 Nano

openai/gpt-5.4-nano

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. I

Google: Gemini 2.5 Flash (batch)

google/gemini-2.5-flash:batch

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scient

Nous: Hermes 3 70B Instruct

nousresearch/hermes-3-llama-3.1-70b

Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including

OpenAI: GPT-5.6 Luna

openai/gpt-5.6-luna

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,

OpenAI: GPT-5.6 Luna Pro

openai/gpt-5.6-luna-pro

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

Sao10K: Llama 3.3 Euryale 70B

sao10k/l3.3-euryale-70b

Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.

MiniMax: MiniMax M2.5

minimax/minimax-m2.5

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital w

Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playin

Qwen: Qwen3 Next 80B A3B Thinking

qwen/qwen3-next-80b-a3b-thinking

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a v

Qwen: Qwen3.6 Flash

qwen/qwen3.6-flash

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 c

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and l

Google: Gemma 2 27B

google/gemma-2-27b-it

Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gem

MiniMax: MiniMax-01

minimax/minimax-01

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

Qwen: Qwen3 Coder 480B A35B

qwen/qwen3-coder

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic c

DeepSeek: DeepSeek V3

deepseek/deepseek-chat

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous version

MiniMax: MiniMax M2

minimax/minimax-m2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activat

DeepSeek: DeepSeek V3.1 Terminus

deepseek/deepseek-v3.1-terminus

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while

DeepSeek: DeepSeek V3 0324

deepseek/deepseek-chat-v3-0324

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. I

An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative s

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 architect

WizardLM-2 8x22B

microsoft/wizardlm-2-8x22b

WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietar

Qwen: Qwen3 Next 80B A3B Instruct

qwen/qwen3-next-80b-a3b-instruct

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinki

MiniMax: MiniMax M2.7

minimax/minimax-m2.7

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to

Mistral: Codestral 2508

mistralai/codestral-2508

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such

Z.ai: GLM 4.6V

z-ai/glm-4.6v

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, an

Qwen: Qwen3 Coder Flash

qwen/qwen3-coder-flash

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model sp

Qwen: Qwen3.6 35B A3B

qwen/qwen3.6-35b-a3b

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t

OpenAI: GPT-5 Mini (batch)

openai/gpt-5-mini:batch

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

ReMM SLERP 13B

undi95/remm-slerp-l2-13b

A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge

Venice: Uncensored

cognitivecomputations/dolphin-mistral-24b-venice-edition

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in col

Arcee AI: Trinity Large Thinking

arcee-ai/trinity-large-thinking

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agent

Qwen: Qwen-Plus

qwen/qwen-plus

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

Qwen: Qwen Plus 0728

qwen/qwen-plus-2025-07-28

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and c

Qwen: Qwen Plus 0728 (thinking)

qwen/qwen-plus-2025-07-28:thinking

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and c

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercu

OpenAI: GPT-3.5 Turbo (batch)

openai/gpt-3.5-turbo:batch

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional

Meta: Llama 4 Maverick

meta-llama/llama-4-maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architectur

OpenAI: GPT-4.1 Mini (batch)

openai/gpt-4.1-mini:batch

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 mil

Z.ai: GLM 4.5 Air

z-ai/glm-4.5-air

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5,

Qwen: Qwen3 Coder Next

qwen/qwen3-coder-next

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE d

Mistral: Mistral Small 3.1 24B

mistralai/mistral-small-3.1-24b-instruct

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal ca

Google: Gemini 3.1 Flash Lite (batch)

google/gemini-3.1-flash-lite:batch

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, im

Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.

Meta: Llama 3.1 70B Instruct

meta-llama/llama-3.1-70b-instruct

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high q

Mistral: Saba

mistralai/mistral-saba

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextuall

UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.

Tencent: Hy3 preview

tencent/hy3-preview

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports config

Qwen2.5 72B Instruct

qwen/qwen-2.5-72b-instruct

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more k

Cohere: Command R (08-2024)

cohere/command-r-08-2024

command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented g

Mistral: Mistral Small 4

mistralai/mistral-small-2603

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a s

OpenAI: GPT-4o-mini

openai/gpt-4o-mini

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

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

openai/gpt-4o-mini-2024-07-18

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

Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expre

Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward

OpenAI: GPT-5.4 Nano (batch)

openai/gpt-5.4-nano:batch

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. I

Tencent: Hunyuan A13B Instruct

tencent/hunyuan-a13b-instruct

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and

inclusionAI: Ling-2.6-1T

inclusionai/ling-2.6-1t

Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents th

inclusionAI: Ring-2.6-1T

inclusionai/ring-2.6-1t

Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong

OpenAI: GPT-5.6 Luna Pro (batch)

openai/gpt-5.6-luna-pro:batch

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

OpenAI: GPT-5.6 Luna (batch)

openai/gpt-5.6-luna:batch

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,

DeepSeek: DeepSeek V3.2 Exp

deepseek/deepseek-v3.2-exp

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures

Tencent: Hy3

tencent/hy3

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic work

AllenAI: Olmo 3 32B Think

allenai/olmo-3-32b-think

Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instructio

Qwen: Qwen3 VL 30B A3B Instruct

qwen/qwen3-vl-30b-a3b-instruct

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

DeepSeek: DeepSeek V3.2

deepseek/deepseek-v3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use perfo

Qwen: Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-2507

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, w

Qwen: Qwen3 30B A3B

qwen/qwen3-30b-a3b

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to exce

Qwen: Qwen3 8B

qwen/qwen3-8b

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialog

Qwen: Qwen3 VL 8B Instruct

qwen/qwen3-vl-8b-instruct

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning acr

Nous: Hermes 4 70B

nousresearch/hermes-4-70b

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 4

Google: Gemma 3 27B

google/gemma-3-27b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understan

Qwen: Qwen3 VL 32B Instruct

qwen/qwen3-vl-32b-instruct

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

Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference de

Google: Gemini 2.5 Flash Lite

google/gemini-2.5-flash-lite

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It off

OpenAI: GPT-4.1 Nano

openai/gpt-4.1-nano

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

NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accurac

Z.ai: GLM 4.7 Flash

z-ai/glm-4.7-flash

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic c

OpenAI: GPT-5 Nano

openai/gpt-5-nano

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

Google: Gemma 4 31B

google/gemma-4-31b-it

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K tok

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpass

Meta: Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).

Google: Gemma 4 26B A4B

google/gemma-4-26b-a4b-it

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 ac

Meta: Llama 4 Scout

meta-llama/llama-4-scout

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a t

Mistral: Ministral 3 14B 2512

mistralai/ministral-14b-2512

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral S

Mistral: Voxtral Small 24B 2507

mistralai/voxtral-small-24b-2507

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class te

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selective

Meta: Llama 3.2 3B Instruct

meta-llama/llama-3.2-3b-instruct

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialo

Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features

OpenAI: GPT-4o-mini (batch)

openai/gpt-4o-mini:batch

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

OpenAI: gpt-oss-safeguard-20b

openai/gpt-oss-safeguard-20b

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (Mo

Qwen: Qwen3 32B

qwen/qwen3-32b

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogu

Meta: Llama Guard 4 12B

meta-llama/llama-guard-4-12b

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous vers

Qwen: Qwen3 14B

qwen/qwen3-14b

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue

Qwen: Qwen3 Coder 30B A3B Instruct

qwen/qwen3-coder-30b-a3b-instruct

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for

Qwen: Qwen3.5-Flash

qwen/qwen3.5-flash-02-23

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a spars

Amazon: Nova Lite 1.0

amazon/nova-lite-v1

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 gen

ByteDance: UI-TARS 7B

bytedance/ui-tars-1.5-7b

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile s

Mistral: Ministral 3 8B 2512

mistralai/ministral-8b-2512

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

Qwen: Qwen2.5 7B Instruct

qwen/qwen-2.5-7b-instruct

Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more kn

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at genera

Mistral: Mistral Small 3.2 24B

mistralai/mistral-small-3.2-24b-instruct

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction

Qwen: Qwen3.5-9B

qwen/qwen3.5-9b

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

Google: Gemini 2.5 Flash Lite (batch)

google/gemini-2.5-flash-lite:batch

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It off

NVIDIA: Nemotron 3 Nano 30B A3B

nvidia/nemotron-3-nano-30b-a3b

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialize

OpenAI: GPT-4.1 Nano (batch)

openai/gpt-4.1-nano:batch

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

Qwen: Qwen3 30B A3B Instruct 2507

qwen/qwen3-30b-a3b-instruct-2507

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It

Meta: Llama 3.2 1B Instruct

meta-llama/llama-3.2-1b-instruct

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialog

OpenAI: GPT-5 Nano (batch)

openai/gpt-5-nano:batch

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

Mistral: Ministral 8B

mistralai/ministral-8b

Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference

Microsoft: Phi 4

microsoft/phi-4

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with

OpenAI: gpt-oss-120b

openai/gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and

Google: Gemma 3 12B

google/gemma-3-12b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understan

Mistral: Ministral 3 3B 2512

mistralai/ministral-3b-2512

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

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

Cohere: Command R7B (12-2024)

cohere/command-r7b-12-2024

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and s

Google: Gemma 3n 4B

google/gemma-3n-e4b-it

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports m

Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their L

Amazon: Nova Micro 1.0

amazon/nova-micro-v1

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost

DeepSeek: DeepSeek V4 Flash 0423

deepseek/deepseek-v4-flash

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters,

OpenAI: gpt-oss-20b

openai/gpt-oss-20b

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) archit