Showing 358 models
Grok
Grok Build 0.1xAI

Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding..

256K$1.00$2.00867ms
codingvision
Google
Gemini 3.5 FlashGoogle

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 proficiency and parallel age

1.0M$1.50$9.002607ms
analysiscodingvision
Anthropic
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.

1.0M$30.00$150.001908ms
vision
PE
Perceptron Mk1Perceptron

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 queries, and produces

33K$0.15$1.501515ms
analysisvision
IN
Ring-2.6-1TInclusion AI

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 capability and operational efficiency. It is optimized for

262K$0.07$0.632089ms
analysiscoding
Google
Gemini 3.1 Flash LiteGoogle

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 is designed for light

1.0M$0.25$1.502268ms
codingvision
Baidu
CoBuddy (free)Baidu

CoBuddy is a code generation model from Baidu, optimized for coding tasks and AI Agent workflows. It features high inference throughput and low end-to-end latency, with native support for tool...

131KFreeFree553ms
coding
OpenAI
GPT Chat LatestOpenAI

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 updates...

400K$5.00$30.001517ms
chatvision
Grok
Grok 4.3xAI

Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

1.0M$1.25$2.50838ms
analysiscodinginstructionvision
IBM
Granite 4.1 8BIBM

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

131K$0.05$0.102553ms
coding
Mistral
Mistral Medium 3.5Mistral

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, and complex...

262K$1.50$7.501447ms
codinginstructionvision
OP
Owl AlphaOpenRouter

Owl Alpha is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in code generation, automated workflows, an

1.0MFreeFree891ms
codinginstruction
Nvidia
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, video, and...

256KFreeFree1968ms
codingvision
PO
Laguna XS.2 (free)Poolside

Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai), their efficient coding agent series. It combines tool calling and reasoning capabilities with a co

131KFreeFree1119ms
analysiscoding
PO
Laguna M.1 (free)Poolside

Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling an

131KFreeFree1831ms
analysiscoding
Anthropic
Anthropic Claude Haiku LatestAnthropic

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

200K$1.00$5.002944ms
vision
OpenAI
OpenAI GPT Mini LatestOpenAI

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

400K$0.75$4.50940ms
vision
Google
Google Gemini Pro LatestGoogle

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

1.0M$2.00$12.002468ms
vision
MoonshotAI
MoonshotAI Kimi LatestMoonshot AI

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

262K$0.73$3.491933ms
vision
Google
Google Gemini Flash LatestGoogle

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

1.0M$1.50$9.002363ms
vision
Anthropic
Anthropic Claude Sonnet LatestAnthropic

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

1.0M$3.00$15.002126ms
vision
OpenAI
OpenAI GPT LatestOpenAI

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

1.1M$5.00$30.002618ms
vision
AlibabaCloud
Qwen3.5 Plus 2026-04-20Alibaba

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. This...

1.0M$0.30$1.802533ms
vision
AlibabaCloud
Qwen3.6 FlashAlibaba

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...

1.0M$0.19$1.13984ms
vision
AlibabaCloud
Qwen3.6 35B A3BAlibaba

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-experts architectur

262K$0.15$1.002732ms
vision
AlibabaCloud
Qwen3.6 Max PreviewAlibaba

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic cod

262K$1.04$6.241937ms
coding
AlibabaCloud
Qwen3.6 27BAlibaba

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, and video inputs..

262K$0.32$3.202300ms
vision
OpenAI
GPT-5.5 ProOpenAI

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 output) with support

1.1M$30.00$180.002372ms
analysisvision
OpenAI
GPT-5.5OpenAI

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 hard tasks. It feature

1.1M$5.00$30.00589ms
analysisvision
DeepSeek
DeepSeek V4 ProDeepSeek

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reaso

1.0M$0.43$0.87608ms
analysiscoding
DeepSeek
DeepSeek V4 Flash (free)DeepSeek

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fa

1.0MFreeFree2573ms
chat
DeepSeek
DeepSeek V4 FlashDeepSeek

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fa

1.0M$0.11$0.222325ms
chat
IN
Ling-2.6-1TInclusion AI

Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It u

262K$0.07$0.63456ms
codinginstruction
Tencent
Hy3 previewTencent

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes

262K$0.07$0.26876ms
analysiscoding
XI
MiMo-V2.5-ProXiaomi

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as C

1.0M$1.00$3.00463ms
coding
XI
MiMo-V2.5Xiaomi

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and v

1.0M$0.40$2.001991ms
codingvision
OpenAI
GPT-5.4 Image 2OpenAI

[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 multimodal workflows, allo

272K$8.00$15.002139ms
analysiscodingvision
IN
Ling-2.6-flashInclusion AI

Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and

262K$0.01$0.032411ms
codinginstruction
Anthropic
Claude Opus LatestAnthropic

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

1.0M$5.00$25.002597ms
vision
OP
Pareto Code RouterOpenRouter

The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the

2.0M$-1000000.0000$-1000000.00002037ms
coding
Baidu
Qianfan-OCR-FastBaidu

Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while preserving versatile multimodal intelligence, it provides a powerf

66K$0.68$2.811772ms
vision
MoonshotAI
Kimi K2.6Moonshot AI

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-to-end coding tasks

262K$0.73$3.49559ms
codingvision
Anthropic
Claude Opus 4.7Anthropic

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 stronger performance on..

1.0M$5.00$25.00794ms
codingvision
Anthropic
Claude Opus 4.6 (Fast)Anthropic

Fast-mode variant of [Opus 4.6](/anthropic/claude-opus-4.6) - identical capabilities with higher output speed at premium 6x pricing.

1.0M$30.00$150.002254ms
vision
Zhipu
GLM 5.1Zhipu AI

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work

203KFreeFree1098ms
coding
Google
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 — delivering near-31B qual

262KFreeFree2399ms
instructionvision
Google
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 — delivering near-31B qual

262K$0.06$0.331180ms
instructionvision
Google
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/reasoning mode, nat

262KFreeFree2783ms
analysiscodinginstructionvision
Google
Gemma 4 31BGoogle

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/reasoning mode, nat

262K$0.12$0.372971ms
analysiscodinginstructionvision
AlibabaCloud
Qwen3.6 PlusAlibaba

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

1.0M$0.33$1.95563ms
vision
Zhipu
GLM 5V TurboZhipu AI

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon p

203K$1.20$4.001957ms
codingvision
AR
Trinity Large Thinking (free)Arcee AI

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://you

262KFreeFree1653ms
analysiscoding
AR
Trinity Large ThinkingArcee AI

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://you

262K$0.22$0.85309ms
analysiscoding
Grok
Grok 4.20 Multi-AgentxAI

Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesi

2.0M$2.00$6.002873ms
codingvision
Grok
Grok 4.20xAI

Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, deliver

2.0M$1.25$2.501230ms
analysiscodingvision
Google
Lyria 3 Pro PreviewGoogle

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, 48kHz...

1.0MFreeFree708ms
vision
Google
Lyria 3 Clip PreviewGoogle

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...

1.0MFreeFree750ms
vision
KW
KAT-Coder-Pro V2KwaiPilot

KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding st

256K$0.30$1.201896ms
coding
RE
Reka EdgeReka

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 deliver industry-leadin

16K$0.10$0.101929ms
vision
XI
MiMo-V2-OmniXiaomi

MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability - vis

262K$0.40$2.001132ms
codingvision
XI
MiMo-V2-ProXiaomi

MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total parameters and a 1M context length, deeply optimized for agentic scenarios. It is highly adaptable to general agent framework

1.0M$1.00$3.002911ms
coding
Minimax
MiniMax M2.7MiniMax

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates

205K$0.28$1.202076ms
coding
OpenAI
GPT-5.4 NanoOpenAI

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 designed for low-lat

400K$0.20$1.251969ms
vision
OpenAI
GPT-5.4 MiniOpenAI

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 performance across reasoni

400K$0.75$4.501217ms
analysiscodingvision
Mistral
Mistral Small 4Mistral

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 reasoning from...

262K$0.15$0.60939ms
analysisvision
Zhipu
GLM 5 TurboZhipu AI

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows..

203K$1.20$4.00653ms
coding
Nvidia
Nemotron 3 Super (free)Nvidia

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mam

1.0MFreeFree2515ms
coding
Nvidia
Nemotron 3 SuperNvidia

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mam

1.0M$0.09$0.45382ms
coding
ByteDance
Seed-2.0-LiteByteDance

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 practical default choice f

262K$0.25$2.002252ms
codingvision
AlibabaCloud
Qwen3.5-9BAlibaba

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 architecture. It uses a unified

262K$0.04$0.151829ms
analysiscodingvision
OpenAI
GPT-5.4 ProOpenAI

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 context window (922

1.1M$30.00$180.001229ms
analysisvision
OpenAI
GPT-5.4OpenAI

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...

1.1M$2.50$15.002019ms
codingvision
IN
Mercury 2Inception

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achie

128K$0.25$0.75677ms
analysis
OpenAI
GPT-5.3 ChatOpenAI

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 better contextualizati

128K$1.75$14.00564ms
chatvision
Google
Gemini 3.1 Flash Lite PreviewGoogle

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 2.5 Flash performance

1.0M$0.25$1.501214ms
vision
ByteDance
Seed-2.0-MiniByteDance

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

262K$0.10$0.402799ms
analysisvision
Google
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. It combines...

131K$0.50$3.001590ms
vision
AlibabaCloud
Qwen3.5-35B-A3BAlibaba

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, achieving higher inf

262K$0.14$1.002313ms
vision
AlibabaCloud
Qwen3.5-27BAlibaba

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 overall capabilities a

262K$0.20$1.56440ms
vision
AlibabaCloud
Qwen3.5-122B-A10BAlibaba

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 higher inference eff

262K$0.26$2.081841ms
vision
AlibabaCloud
Qwen3.5-FlashAlibaba

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 higher inference effic

1.0M$0.07$0.26805ms
vision
LI
LFM2-24B-A2BLiquid

LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active paramete

128K$0.03$0.12974ms
chat
Google
Gemini 3.1 Pro Preview Custom ToolsGoogle

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-party...

1.0M$2.00$12.00777ms
codingvision
OpenAI
GPT-5.3-CodexOpenAI

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 knowledge capabilitie

400K$1.75$14.002813ms
analysiscodingvision
AI
Aion-2.0Aion Labs

Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel

131K$0.80$1.60500ms
creative
Google
Gemini 3.1 Pro PreviewGoogle

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

1.0M$2.00$12.00709ms
analysiscodingvision
Anthropic
Claude Sonnet 4.6Anthropic

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 codebase navigation,

1.0M$3.00$15.001752ms
codingvision
AlibabaCloud
Qwen3.5 Plus 2026-02-15Alibaba

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, achieving higher inference e

1.0M$0.26$1.56981ms
vision
AlibabaCloud
Qwen3.5 397B A17BAlibaba

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, achieving higher infere

262K$0.39$2.34359ms
vision
Minimax
MiniMax M2.5 (free)MiniMax

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise o

205KFreeFree1194ms
coding
Minimax
MiniMax M2.5MiniMax

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise o

205K$0.15$1.151904ms
coding
Zhipu
GLM 5Zhipu AI

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on l

203K$0.60$1.92646ms
coding
AlibabaCloud
Qwen3 Max ThinkingAlibaba

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and re

262K$0.78$3.901158ms
analysis
Anthropic
Claude Opus 4.6Anthropic

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially eff

1.0M$5.00$25.001817ms
codingvision
AlibabaCloud
Qwen3 Coder NextAlibaba

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

262K$0.11$0.802759ms
coding
OP
Free Models RouterOpenRouter

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 models that...

200KFreeFree2848ms
vision
ST
Step 3.5 FlashStepFun

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

262K$0.09$0.302765ms
chat
AR
Trinity Large PreviewArcee AI

Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing.

131K$0.15$0.452307ms
creative
MoonshotAI
Kimi K2.5Moonshot AI

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 pretraining over appr

262K$0.40$1.90728ms
codingvision
Upsate
Solar Pro 3Upstage

Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining

128K$0.15$0.60780ms
chat
Minimax
MiniMax M2-herMiniMax

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personalit

66K$0.30$1.201676ms
chat
WR
Palmyra X5Writer

Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million

1.0M$0.60$6.002712ms
coding
LI
LFM2.5-1.2B-Thinking (free)Liquid

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K

33KFreeFree1383ms
analysiscoding
LI
LFM2.5-1.2B-Instruct (free)Liquid

LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference an

33KFreeFree1119ms
chatinstruction
OpenAI
GPT AudioOpenAI

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is p

128K$2.50$10.00689ms
coding
OpenAI
GPT Audio MiniOpenAI

A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...

128K$0.60$2.402597ms
coding
Zhipu
GLM 4.7 FlashZhipu AI

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 coding use cases, strengthening coding capabilities, long-hor

203K$0.06$0.40932ms
coding
OpenAI
GPT-5.2-CodexOpenAI

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, independent execution

400K$1.75$14.002607ms
codingvision
ByteDance
Seed 1.6 FlashByteDance

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 outputs of...

262K$0.07$0.301933ms
analysisvision
ByteDance
Seed 1.6ByteDance

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.

262K$0.25$2.00380ms
analysisvision
Minimax
MiniMax M2.1MiniMax

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers

205K$0.29$0.95760ms
coding
Zhipu
GLM 4.7Zhipu AI

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements

203K$0.40$1.752471ms
analysiscoding
Google
Gemini 3 Flash PreviewGoogle

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 tool...

1.0M$0.50$3.001249ms
analysischatcodingvision
XI
MiMo-V2-FlashXiaomi

MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architec

262K$0.10$0.302801ms
chat
Nvidia
Nemotron 3 Nano 30B A3B (free)Nvidia

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

256KFreeFree347ms
coding
Nvidia
Nemotron 3 Nano 30B A3BNvidia

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

262K$0.05$0.202755ms
coding
OpenAI
GPT-5.2 ChatOpenAI

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 to selectively “thi

128K$1.75$14.00844ms
analysischatvision
OpenAI
GPT-5.2 ProOpenAI

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 require step-by-step reas

400K$21.00$168.00703ms
analysiscodingvision
OpenAI
GPT-5.2OpenAI

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 computation dynamicall

400K$1.75$14.002538ms
analysiscodingvision
Mistral
Devstral 2 2512Mistral

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports ex

262K$0.40$2.002676ms
coding
RE
Relace SearchRelace

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 request. In contrast to RAG, relace-search performs agentic...

256K$1.00$3.00574ms
coding
Zhipu
GLM 4.6VZhipu AI

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes comp

131K$0.30$0.902741ms
analysisvision
NE
DeepSeek V3.1 Nex N1Nex AGI

DeepSeek V3.1 Nex-N1 is the flagship release of the Nex-N1 series — a post-trained model designed to highlight agent autonomy, tool use, and real-world productivity. Nex-N1 demonstrates competitive pe

131K$0.14$0.501968ms
coding
ES
Rnj 1 InstructEssential AI

Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focus on programming, math, and scientific reasoning. The model demonstrates strong

33K$0.15$0.152017ms
analysiscodinginstructionmath
OP
Body Builder (beta)OpenRouter

Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls.

128K$-1000000.0000$-1000000.0000353ms
chat
OpenAI
GPT-5.1-Codex-MaxOpenAI

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 reasoning stack and trained

400K$1.25$10.001406ms
analysiscodingvision
AWS
Nova 2 LiteAmazon

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 capabilities in processing...

1.0M$0.30$2.50974ms
analysisvision
Mistral
Ministral 3 14B 2512Mistral

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 efficient language.

262K$0.20$0.202096ms
vision
Mistral
Ministral 3 8B 2512Mistral

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

262K$0.15$0.152860ms
vision
Mistral
Ministral 3 3B 2512Mistral

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

131K$0.10$0.101995ms
vision
Mistral
Mistral Large 3 2512Mistral

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 Apache 2.0 license.

262K$0.50$1.502749ms
vision
AR
Trinity MiniArcee AI

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with ro

131K$0.04$0.151927ms
analysiscoding
DeepSeek
DeepSeek V3.2 SpecialeDeepSeek

DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context proce

164K$0.29$0.431875ms
analysiscoding
DeepSeek
DeepSeek V3.2DeepSeek

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fin

131K$0.25$0.382302ms
analysiscoding
PR
INTELLECT-3Prime Intellect

INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offe

131K$0.20$1.10500ms
math
Anthropic
Claude Opus 4.5Anthropic

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 capabilities, competit

200K$5.00$25.001859ms
analysiscodingvision
AL
Olmo 3 32B ThinkAllen AI

Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performan

66K$0.15$0.502927ms
analysisinstruction
Google
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 reasoning, real-world gr

66K$2.00$12.002742ms
analysisvision
DE
Cogito v2.1 671BDeepCogito

Cogito v2.1 671B MoE represents one of the strongest open models globally, matching performance of frontier closed and open models. This model is trained using self play with reinforcement learning...

128K$1.25$1.251332ms
chat
OpenAI
GPT-5.1OpenAI

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 compared to GPT-5.

400K$1.25$10.002316ms
analysischatinstructionvision
OpenAI
GPT-5.1 ChatOpenAI

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 to selectively “thin

128K$1.25$10.001543ms
analysischatvision
OpenAI
GPT-5.1-CodexOpenAI

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, independent execution of c

400K$1.25$10.002662ms
codingvision
OpenAI
GPT-5.1-Codex-MiniOpenAI

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

400K$0.25$2.002620ms
codingvision
MoonshotAI
Kimi K2 ThinkingMoonshot AI

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) arc

262K$0.60$2.502060ms
analysiscoding
AWS
Nova Premier 1.0Amazon

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.

1.0M$2.50$12.50685ms
analysisvision
Perplexity
Sonar Pro SearchPerplexity

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. Pricing is based...

200K$3.00$15.002483ms
analysiscodingvision
Mistral
Voxtral Small 24B 2507Mistral

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translati

32K$0.10$0.302890ms
chat
OpenAI
gpt-oss-safeguard-20bOpenAI

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content

131K$0.07$0.30652ms
analysis
Nvidia
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-Mamba architecture, c

128KFreeFree862ms
analysisvision
Minimax
MiniMax M2MiniMax

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier

205K$0.26$1.002393ms
analysiscoding
AlibabaCloud
Qwen3 VL 32B InstructAlibaba

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 parameters, it combines

262K$0.10$0.42594ms
analysisinstructionvision
IBM
Granite 4.0 MicroIBM

Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...

131K$0.02$0.11476ms
chat
Azure
Phi 4 Mini InstructMicrosoft

Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4.

131K$0.08$0.35658ms
analysisinstruction
OpenAI
GPT-5 Image MiniOpenAI

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 generation. This natively

400K$2.50$2.002253ms
instructionvision
Anthropic
Claude Haiku 4.5Anthropic

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s perfor

200K$1.00$5.002950ms
vision
AlibabaCloud
Qwen3 VL 8B ThinkingAlibaba

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, and temporal sequences

256K$0.12$1.36395ms
analysisvision
AlibabaCloud
Qwen3 VL 8B InstructAlibaba

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 improved multimodal

256K$0.08$0.501896ms
analysisinstructionvision
OpenAI
GPT-5 ImageOpenAI

[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 quality, and user e

400K$10.00$10.001730ms
analysiscodinginstructionvision
OpenAI
o3 Deep ResearchOpenAI

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks.

200K$10.00$40.001061ms
codingvision
OpenAI
o4 Mini Deep ResearchOpenAI

o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks.

200K$2.00$8.001097ms
codingvision
Nvidia
Llama 3.3 Nemotron Super 49B V1.5Nvidia

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG,

131K$0.10$0.401282ms
analysischatcodinginstruction
Baidu
ERNIE 4.5 21B A3B ThinkingBaidu

ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, math, science, coding, text generation,

131K$0.07$0.281768ms
analysiscodingmath
Google
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 generation,...

33K$0.30$2.501485ms
vision
AlibabaCloud
Qwen3 VL 30B A3B ThinkingAlibaba

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, math, and complex

131K$0.13$1.561165ms
analysismathvision
AlibabaCloud
Qwen3 VL 30B A3B InstructAlibaba

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-following for general mu

262K$0.13$0.521893ms
instructionvision
OpenAI
GPT-5 ProOpenAI

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 reasoning, instructi

400K$15.00$120.001189ms
analysiscodinginstructionvision
Zhipu
GLM 4.6Zhipu AI

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex.

203K$0.43$1.741648ms
chat
Anthropic
Claude Sonnet 4.5Anthropic

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-ben

1.0M$3.00$15.001363ms
codingvision
DeepSeek
DeepSeek V3.2 ExpDeepSeek

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grai

164K$0.27$0.412022ms
chat
TH
Cydonia 24B V4.1The Drummer

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

131K$0.30$0.501354ms
creative
RE
Relace Apply 3Relace

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...

256K$0.85$1.251308ms
coding
Google
Gemini 2.5 Flash Lite Preview 09-2025Google

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 offers improved throughput, faster token generation, and better

1.0M$0.10$0.402393ms
analysisvision
AlibabaCloud
Qwen3 VL 235B A22B ThinkingAlibaba

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 multimodal reasoning in STE

131K$0.26$2.60794ms
analysismathvision
AlibabaCloud
Qwen3 VL 235B A22B InstructAlibaba

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 general vision-language

262K$0.20$0.881958ms
instructionvision
AlibabaCloud
Qwen3 MaxAlibaba

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the Janua

262K$0.78$3.901836ms
analysisinstructiontranslation
AlibabaCloud
Qwen3 Coder PlusAlibaba

Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...

1.0M$0.65$3.252969ms
coding
OpenAI
GPT-5 CodexOpenAI

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, independent execution of compl

400K$1.25$10.002867ms
codingvision
DeepSeek
DeepSeek V3.1 TerminusDeepSeek

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language cons

164K$0.27$0.95843ms
chatcoding
AlibabaCloud
Tongyi DeepResearch 30B A3BAlibaba

Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-

131K$0.09$0.451223ms
coding
AlibabaCloud
Qwen3 Coder FlashAlibaba

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...

1.0M$0.20$0.97351ms
coding
AlibabaCloud
Qwen3 Next 80B A3B ThinkingAlibaba

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code s

262K$0.10$0.781148ms
analysischatcodingmath
AlibabaCloud
Qwen3 Next 80B A3B Instruct (free)Alibaba

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code

262KFreeFree1516ms
analysischatcodinginstruction
AlibabaCloud
Qwen3 Next 80B A3B InstructAlibaba

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code

262K$0.09$1.102952ms
analysischatcodinginstruction
AlibabaCloud
Qwen Plus 0728 (thinking)Alibaba

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

1.0M$0.26$0.781253ms
analysis
AlibabaCloud
Qwen Plus 0728Alibaba

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

1.0M$0.26$0.781255ms
analysis
Nvidia
Nemotron Nano 9B V2 (free)Nvidia

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and..

128KFreeFree2384ms
analysis
Nvidia
Nemotron Nano 9B V2Nvidia

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and..

131K$0.04$0.162287ms
analysis
MoonshotAI
Kimi K2 0905Moonshot AI

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 developed by Moonshot AI, featuring 1 trillion total parameters

262K$0.60$2.50785ms
chat
AlibabaCloud
Qwen3 30B A3B Thinking 2507Alibaba

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking m

131K$0.08$0.40319ms
analysis
NO
Hermes 4 70BNous Research

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 405B release, allowing the model to either...

131K$0.13$0.40545ms
analysis
NO
Hermes 4 405BNous Research

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, where the model can choose to deliberate internally with...

131K$1.00$3.002675ms
analysis
DeepSeek
DeepSeek V3.1DeepSeek

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase

164K$0.21$0.79797ms
analysis
OpenAI
GPT-4o AudioOpenAI

The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio

128K$2.50$10.001589ms
chat
Mistral
Mistral Medium 3.1Mistral

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 significantly reduced opera

131K$0.40$2.001308ms
vision
Baidu
ERNIE 4.5 21B A3BBaidu

A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneo

131K$0.07$0.282113ms
vision
Baidu
ERNIE 4.5 VL 28B A3BBaidu

A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneou

131K$0.14$0.561645ms
chatvision
Zhipu
GLM 4.5VZhipu AI

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-

66K$0.60$1.801264ms
codingvision
AI21
Jamba Large 1.7AI21

Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 2

256K$2.00$8.002633ms
instruction
OpenAI
GPT-5 ChatOpenAI

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

128K$1.25$10.002821ms
chatvision
OpenAI
GPT-5OpenAI

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 reasoning, instruction f

400K$1.25$10.002233ms
analysiscodinginstructionvision
OpenAI
GPT-5 MiniOpenAI

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 with reduced latency an

400K$0.25$2.001148ms
analysisinstructionvision
OpenAI
GPT-5 NanoOpenAI

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 reasoning depth compared to

400K$0.05$0.40656ms
analysiscodingvision
OpenAI
gpt-oss-120b (free)OpenAI

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B par

131KFreeFree397ms
analysiscoding
OpenAI
gpt-oss-120bOpenAI

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B par

131K$0.04$0.182439ms
analysiscoding
OpenAI
gpt-oss-20b (free)OpenAI

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) architecture with 3.6B active parameters per forward pass, optimiz

131KFreeFree451ms
chat
OpenAI
gpt-oss-20bOpenAI

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) architecture with 3.6B active parameters per forward pass, optimiz

131K$0.03$0.141011ms
chat
Anthropic
Claude Opus 4.1Anthropic

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 and shows notable ga

200K$15.00$75.00425ms
analysiscodingvision
Mistral
Codestral 2508Mistral

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test genera

256K$0.30$0.90961ms
coding
AlibabaCloud
Qwen3 Coder 30B A3B InstructAlibaba

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 advanced code generation, repository-scale understanding, an

160K$0.07$0.27450ms
codinginstruction
AlibabaCloud
Qwen3 30B A3B Instruct 2507Alibaba

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 operates in non-thinking mode and is designed for high-quali

262K$0.09$0.301656ms
analysisinstructiontranslation
Zhipu
GLM 4.5Zhipu AI

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GL

131K$0.60$2.201837ms
coding
Zhipu
GLM 4.5 Air (free)Zhipu AI

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, it adopts the Mixture-of-Experts (MoE) architecture but wit

131KFreeFree2011ms
coding
Zhipu
GLM 4.5 AirZhipu AI

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, it adopts the Mixture-of-Experts (MoE) architecture but wit

131K$0.13$0.851188ms
coding
AlibabaCloud
Qwen3 235B A22B Thinking 2507Alibaba

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass

262K$0.15$1.50401ms
analysis
Zhipu
GLM 4 32B Zhipu AI

GLM 4 32B is a cost-effective foundation language model. It can efficiently perform complex tasks and has significantly enhanced capabilities in tool use, online search, and code-related intelligent t

128K$0.10$0.101343ms
coding
AlibabaCloud
Qwen3 Coder 480B A35B (free)Alibaba

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-con

1.0MFreeFree1912ms
analysiscodinginstruction
AlibabaCloud
Qwen3 Coder 480B A35BAlibaba

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-con

1.0M$0.22$1.802778ms
analysiscodinginstruction
ByteDance
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, it builds upon the UI

128K$0.10$0.202105ms
codingvision
Google
Gemini 2.5 Flash LiteGoogle

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 offers improved throughput, faster token generation, and better

1.0M$0.10$0.40620ms
analysisvision
AlibabaCloud
Qwen3 235B A22B Instruct 2507Alibaba

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized

262K$0.07$0.101865ms
instructiontranslation
SW
Switchpoint RouterSwitchPoint

Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an ever-evolving library. As the world of LLMs advances, our router gets smarter, ensuring you...

131K$0.85$3.40905ms
chat
MoonshotAI
Kimi K2 0711Moonshot AI

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for..

131K$0.57$2.30346ms
instruction
Mistral
Devstral MediumMistral

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves...

131K$0.40$2.001586ms
analysiscoding
Mistral
Devstral Small 1.1Mistral

Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and...

131K$0.10$0.301675ms
coding
CO
Uncensored (free)Cognitive Computations

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “unc

33KFreeFree2025ms
instruction
Tencent
Hunyuan A13B InstructTencent

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers compe

131K$0.14$0.572511ms
analysisinstruction
MO
Morph V3 LargeMorph

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instructio

262K$0.90$1.902357ms
codinginstruction
MO
Morph V3 FastMorph

Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}

82K$0.80$1.202001ms
codinginstruction
Baidu
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 jointly on text and image

131K$0.42$1.252122ms
vision
Baidu
ERNIE 4.5 300B A47B Baidu

ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu as part of the ERNIE 4.5 series. It activates 47B parameters per token and supports text generation i

131K$0.28$1.102186ms
chat
Mistral
Mistral Small 3.2 24BMistral

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release

128K$0.07$0.201611ms
codinginstructionvision
Minimax
MiniMax M1MiniMax

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "

1.0M$0.40$2.201857ms
analysis
Google
Gemini 2.5 FlashGoogle

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, en

1.0M$0.30$2.502306ms
analysiscodingmathvision
Google
Gemini 2.5 ProGoogle

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 reason through respo

1.0M$1.25$10.001091ms
analysiscodingmathvision
OpenAI
o3 ProOpenAI

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 provide consistently...

200K$20.00$80.002739ms
analysisvision
Google
Gemini 2.5 Pro Preview 06-05Google

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 reason through respo

1.0M$1.25$10.002274ms
analysiscodingmathvision
DeepSeek
R1 0528DeepSeek

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in siz

164K$0.50$2.15904ms
analysis
Anthropic
Claude Opus 4Anthropic

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...

200K$15.00$75.001737ms
codingvision
Anthropic
Claude Sonnet 4Anthropic

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the

1.0M$3.00$15.001716ms
analysiscodingvision
Google
Gemma 3n 4BGoogle

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enab

33K$0.06$0.122029ms
vision
Mistral
Mistral Medium 3Mistral

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-of-the-art reasoning

131K$0.40$2.001125ms
analysisvision
Google
Gemini 2.5 Pro Preview 05-06Google

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 reason through respo

1.0M$1.25$10.001511ms
analysiscodingmathvision
AR
SpotlightArcee AI

Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich

131K$0.18$0.181093ms
vision
AR
Maestro ReasoningArcee AI

Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the earlier 7 B...

131K$0.90$3.302320ms
analysis
AR
Virtuoso LargeArcee AI

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...

131K$0.75$1.20575ms
analysiscreative
AR
Coder LargeArcee AI

Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context win

33K$0.50$0.802393ms
codinginstruction
Meta
Llama Guard 4 12BMeta

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 in both LLM...

164K$0.18$0.182365ms
vision
AlibabaCloud
Qwen3 30B A3BAlibaba

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tas

131K$0.09$0.451125ms
analysiscodingtranslation
AlibabaCloud
Qwen3 8BAlibaba

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode f

131K$0.05$0.40826ms
analysismath
AlibabaCloud
Qwen3 14BAlibaba

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode f

132K$0.10$0.242516ms
analysis
AlibabaCloud
Qwen3 32BAlibaba

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode

131K$0.08$0.282366ms
analysis
AlibabaCloud
Qwen3 235B A22BAlibaba

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex r

131K$0.46$1.821174ms
analysismath
OpenAI
o4 Mini HighOpenAI

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 fast, cost-efficient p

200K$1.10$4.402868ms
analysisvision
OpenAI
o3OpenAI

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

200K$2.00$8.00677ms
analysiscodingcreativeinstruction
OpenAI
o4 MiniOpenAI

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 tool use and demonst

200K$1.10$4.402339ms
analysiscodingvision
OpenAI
GPT-4.1OpenAI

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 context window and o

1.0M$2.00$8.00509ms
analysisinstructionvision
OpenAI
GPT-4.1 MiniOpenAI

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 45.1% on hard...

1.0M$0.40$1.602319ms
vision
OpenAI
GPT-4.1 NanoOpenAI

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...

1.0M$0.10$0.40549ms
vision
AL
CodeLLaMa 7B Instruct SolidityAlfred Pros

A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library.

4K$0.80$1.201709ms
codinginstruction
Meta
Llama 4 MaverickMeta

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forw

1.0M$0.15$0.60996ms
instructionvision
Meta
Llama 4 ScoutMeta

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

10.0M$0.08$0.30431ms
instructionvision
DeepSeek
DeepSeek V3 0324DeepSeek

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) mod

164K$0.20$0.771777ms
chat
OpenAI
o1-proOpenAI

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 provide...

200K$150.00$600.002322ms
analysisvision
Mistral
Mistral Small 3.1 24BMistral

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 performance in text

128K$0.35$0.561607ms
analysisinstructionvision
Google
Gemma 3 4BGoogle

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 improved math, reasoning,

131K$0.04$0.081386ms
analysischatmathvision
Google
Gemma 3 12BGoogle

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 improved math, reasoning,

131K$0.04$0.131649ms
analysischatmathvision
Cohere
Command ACohere

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading propr

256K$2.50$10.00706ms
codingtranslation
OpenAI
GPT-4o-mini Search PreviewOpenAI

GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

128K$0.15$0.601278ms
chat
OpenAI
GPT-4o Search PreviewOpenAI

GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

128K$2.50$10.00900ms
chat
RE
Reka Flash 3Reka

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function ca

66K$0.10$0.201840ms
chatcodinginstruction
Google
Gemma 3 27BGoogle

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 improved math, reasoning,

131K$0.08$0.162273ms
analysischatmathvision
TH
Skyfall 36B V2The Drummer

Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.

33K$0.55$0.80959ms
creative
Perplexity
Sonar Reasoning ProPerplexity

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-sonar-pro) Sonar Reasoni

128K$2.00$8.00969ms
analysisvision
Perplexity
Sonar ProPerplexity

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-sonar-pro) For enterpris

200K$3.00$15.001481ms
analysisvision
Perplexity
Sonar Deep ResearchPerplexity

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its

128K$2.00$8.001172ms
analysis
Google
Gemini 2.0 Flash LiteGoogle

Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemin

1.0M$0.07$0.301867ms
vision
Mistral
SabaMistral

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance

33K$0.20$0.60591ms
chat
Meta
Llama Guard 3 8BMeta

Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classificati

131K$0.48$0.031977ms
chat
OpenAI
o3 Mini HighOpenAI

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 model optimized for STEM reasoning tasks, particularly excel

200K$1.10$4.402490ms
analysismath
Google
Gemini 2.0 FlashGoogle

Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro

1.0M$0.10$0.401933ms
vision
AI
Aion-1.0Aion Labs

Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as

131K$4.00$8.001040ms
analysiscoding
AI
Aion-1.0-MiniAion Labs

Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant

131K$0.70$1.401822ms
analysiscodingmath
AI
Aion-RP 1.0 (8B)Aion Labs

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses.

33K$0.80$1.602649ms
chat
AlibabaCloud
Qwen2.5 VL 72B InstructAlibaba

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 within images.

131K$0.25$0.75626ms
instructionvision
AlibabaCloud
Qwen-PlusAlibaba

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

1.0M$0.26$0.781588ms
chat
OpenAI
o3 MiniOpenAI

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter,

200K$1.10$4.40920ms
analysiscodingmath
Mistral
Mistral Small 3Mistral

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tune

33K$0.05$0.081661ms
instruction
DeepSeek
R1 Distill Qwen 32BDeepSeek

DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperfor

128K$0.29$0.292970ms
chat
Perplexity
SonarPerplexity

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 lightweight question-and-ans

127K$1.00$1.00535ms
vision
DeepSeek
R1 Distill Llama 70BDeepSeek

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), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The mo

131K$0.70$0.802644ms
instruction
DeepSeek
R1DeepSeek

DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....

164K$0.70$2.50895ms
analysis
Minimax
MiniMax-01MiniMax

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 inference, and can han

1.0M$0.20$1.10824ms
vision
Azure
Phi 4Microsoft

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 b

16K$0.07$0.142843ms
analysis
SA
Llama 3.1 70B Hanami x1Sao10k

This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b).

16K$3.00$3.001229ms
chat
DeepSeek
DeepSeek V3DeepSeek

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported ev

164K$0.32$0.89692ms
codinginstruction
SA
Llama 3.3 Euryale 70BSao10k

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 v2.2](/models/sao10k/l3-euryale-70b).

131K$0.65$0.751165ms
creative
OpenAI
o1OpenAI

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 learning to reason...

200K$15.00$60.002479ms
analysisvision
Cohere
Command R7B (12-2024)Cohere

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 similar tasks requiring complex reasoning...

128K$0.04$0.152987ms
analysiscoding
Meta
Llama 3.3 70B Instruct (free)Meta

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

131KFreeFree2734ms
instructiontranslation
Meta
Llama 3.3 70B InstructMeta

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

131K$0.10$0.32438ms
instructiontranslation
AWS
Nova Lite 1.0Amazon

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...

300K$0.06$0.242778ms
vision
AWS
Nova Micro 1.0Amazon

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. With a context length...

128K$0.04$0.142570ms
chat
AWS
Nova Pro 1.0Amazon

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...

300K$0.80$3.202976ms
vision
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 at working with upl

128K$2.50$10.001108ms
creativevision
Mistral
Mistral Large 2411Mistral

Mistral Large 2 2411 is an update of [Mistral Large 2](/mistralai/mistral-large) released together with [Pixtral Large 2411](/mistralai/pixtral-large-2411) It provides a significant upgrade on the pre

131K$2.00$6.001553ms
chat
Mistral
Mistral Large 2407Mistral

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch annou

131K$2.00$6.002577ms
analysischatcoding
Mistral
Pixtral Large 2411Mistral

Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural images.

131K$2.00$6.00725ms
vision
AlibabaCloud
Qwen2.5 Coder 32B InstructAlibaba

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improveme

128K$0.66$1.00693ms
analysiscodinginstruction
TH
UnslopNemo 12BThe Drummer

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

33K$0.40$0.40981ms
creative
Anthropic
Claude 3.5 HaikuAnthropic

Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for d

200K$0.80$4.002506ms
codingvision
AN
Magnum v4 72BAnthracite

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthrop

33K$3.00$5.001766ms
instruction
AlibabaCloud
Qwen2.5 7B InstructAlibaba

Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and.

131K$0.04$0.101836ms
codinginstruction
Inflection
Inflection 3 ProductivityInflection

Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news. For emotional

8K$2.50$10.002881ms
instruction
Inflection
Inflection 3 PiInflection

Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like custo

8K$2.50$10.002038ms
chatcreative
TH
Rocinante 12BThe Drummer

Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narrative

33K$0.17$0.432152ms
creative
Meta
Llama 3.2 11B Vision InstructMeta

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...

131K$0.24$0.242685ms
instructionvision
Meta
Llama 3.2 1B InstructMeta

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows

131K$0.03$0.20329ms
instructionsummarizationtranslation
Meta
Llama 3.2 3B Instruct (free)Meta

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with

131KFreeFree937ms
analysisinstructionsummarizationtranslation
Meta
Llama 3.2 3B InstructMeta

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with

131K$0.05$0.342945ms
analysisinstructionsummarizationtranslation
AlibabaCloud
Qwen2.5 72B InstructAlibaba

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and

131K$0.36$0.402603ms
codinginstruction
Cohere
Command R (08-2024)Cohere

command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at

128K$0.15$0.602189ms
analysiscodingmathtranslation
Cohere
Command R+ (08-2024)Cohere

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 latencies as compared to the previous Command R+ version, while

128K$2.50$10.00402ms
chat
SA
Llama 3.1 Euryale 70B v2.2Sao10k

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 70B v2.1](/models/sao10k/l3-euryale-70b).

131K$0.85$0.85652ms
creative
NO
Hermes 3 70B InstructNous Research

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

131K$0.30$0.302252ms
analysischatcodinginstruction
NO
Hermes 3 405B Instruct (free)Nous Research

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coheren

131KFreeFree594ms
analysischatcodinginstruction
NO
Hermes 3 405B InstructNous Research

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coheren

131K$1.00$1.001586ms
analysischatcodinginstruction
SA
Llama 3 8B LunarisSao10k

Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....

8K$0.04$0.051596ms
analysis
OpenAI
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.com/index/introducin

128K$2.50$10.002317ms
vision
Meta
Llama 3.1 70B InstructMeta

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 quality dialogue usecases. It has demonstrated strong...

131K$0.40$0.40876ms
instruction
Meta
Llama 3.1 8B InstructMeta

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...

131K$0.02$0.05820ms
instruction
Mistral
Mistral NemoMistral

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chine

131K$0.02$0.03537ms
translation
OpenAI
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 many multiples more a

128K$0.15$0.601552ms
vision
OpenAI
GPT-4o-miniOpenAI

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 many multiples more a

128K$0.15$0.601712ms
vision
Google
Gemma 2 27BGoogle

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). Gemma models are well-suited for a variety of...

8K$0.65$0.651303ms
chat
SA
Llama 3 Euryale 70B v2.1Sao10k

Euryale 70B v2.1 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). - Better prompt adherence. - Better anatomy / spatial awareness. - Adapts much better to unique and cu

8K$1.48$1.48313ms
creative
NO
Hermes 2 Pro - Llama-3 8BNous Research

Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced...

8K$0.14$0.14852ms
chat
OpenAI
GPT-4oOpenAI

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/gpt-4-turbo) while bei

128K$2.50$10.001990ms
vision
OpenAI
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/gpt-4-turbo) while bei

128K$5.00$15.00718ms
vision
Meta
Llama 3 70B InstructMeta

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...

8K$0.51$0.74946ms
instruction
Meta
Llama 3 8B InstructMeta

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...

8K$0.04$0.042528ms
instruction
Mistral
Mixtral 8x22B InstructMistral

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its s

66K$2.00$6.002405ms
codinginstructionmath
Azure
WizardLM-2 8x22BMicrosoft

WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state

66K$0.62$0.622536ms
chat
OpenAI
GPT-4 TurboOpenAI

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.

128K$10.00$30.001938ms
codingvision
Anthropic
Claude 3 HaikuAnthropic

Claude 3 Haiku is Anthropic's fastest and most compact model for

200K$0.25$1.252107ms
vision
Mistral
Mistral LargeMistral

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch ann

128K$2.00$6.002531ms
analysischatcoding
OpenAI
GPT-3.5 Turbo (older v0613)OpenAI

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 completion tasks.

4K$1.00$2.00364ms
chatcoding
OpenAI
GPT-4 Turbo PreviewOpenAI

The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by Open

128K$10.00$30.00955ms
codinginstruction
OP
Auto RouterOpenRouter

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,...

2.0M$-1000000.0000$-1000000.00001266ms
vision
OpenAI
GPT-4 Turbo (older v1106)OpenAI

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.

128K$10.00$30.002167ms
codingvision
Mistral
Mistral 7B Instruct v0.1Mistral

A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length.

4K$0.11$0.192753ms
instruction
OpenAI
GPT-3.5 Turbo InstructOpenAI

This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

4K$1.50$2.001951ms
chatinstruction
OpenAI
GPT-3.5 Turbo 16kOpenAI

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 at a higher cost. Training data: up...

16K$3.00$4.001568ms
chat
MA
Weaver (alpha)Mancer

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

8K$0.75$1.001276ms
chat
UN
ReMM SLERP 13BUndi95

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

6K$0.45$0.652708ms
chat
GR
MythoMax 13BGryphe

One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge

4K$0.06$0.061008ms
chat
OpenAI
GPT-4 (older v0314)OpenAI

GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data: up to Sep 2021.

8K$30.00$60.00633ms
chat
OpenAI
GPT-3.5 TurboOpenAI

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 completion tasks.

16K$0.50$1.50522ms
chatcoding
OpenAI
GPT-4OpenAI

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and adva

8K$30.00$60.002190ms
analysisvision