AI Model Catalog: 2182 Models Compared — Pricing, Context & Benchmarks

Anthropic: Anthropic: Claude Haiku 4.5 T

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 performance...

anthropic/claude-haiku-4.5 200K context $1/M input $5/M output

Alibaba Qwen: Qwen: Qwen3 VL 8B Thinking T

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. It integrates enhanced multimodal alignment and...

qwen/qwen3-vl-8b-thinking 131.072K context $0.18/M input $2.1/M output

Alibaba Qwen: Qwen: Qwen3 VL 8B Instruct T

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 fusion with Interleaved-MRoPE for long-horizon...

qwen/qwen3-vl-8b-instruct 262.144K context $0.25/M input $0.75/M output

Alibaba Qwen: Qwen: Qwen3 VL 30B A3B Thinking T

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 tasks. It excels...

qwen/qwen3-vl-30b-a3b-thinking 262.144K context $0.29/M input $1/M output

Alibaba Qwen: Qwen: Qwen3 VL 30B A3B Instruct T

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 multimodal tasks. It excels in perception...

qwen/qwen3-vl-30b-a3b-instruct 262.144K context $0.15/M input $0.6/M output

Anthropic: Anthropic: Claude Sonnet 4.5 T

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-bench Verified, with...

anthropic/claude-sonnet-4.5 1M context $3/M input $15/M output

Alibaba Qwen: Qwen: Qwen3 VL 235B A22B Thinking T

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 STEM and math....

qwen/qwen3-vl-235b-a22b-thinking 131.072K context $0.4/M input $4/M output

Alibaba Qwen: Qwen: Qwen3 VL 235B A22B Instruct T

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 use (VQA, document parsing, chart/table...

qwen/qwen3-vl-235b-a22b-instruct 131.072K context $0.21/M input $1.9/M output

Mistral AI: Mistral: Mistral Medium 3.1 T

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 operational cost. It balances...

mistralai/mistral-medium-3.1 131.072K context $0.4/M input $2/M output

Z Ai: Z.ai: GLM 4.5V T

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-of-the-art results in video understanding,...

z-ai/glm-4.5v 65.536K context $0.6/M input $1.8/M output

OpenAI: OpenAI: GPT-5 Chat T

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

openai/gpt-5-chat 128K context $1.25/M input $10/M output

Anthropic: Anthropic: Claude Opus 4.1 T

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 gains...

anthropic/claude-opus-4.1 200K context $15/M input $75/M output

Bytedance: ByteDance: UI-TARS 7B T

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-TARS framework with reinforcement...

bytedance/ui-tars-1.5-7b 128K context $0.1/M input $0.2/M output

Mistral AI: Mistral: Mistral Small 3.2 24B T

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, version 3.2 significantly improves accuracy on...

mistralai/mistral-small-3.2-24b-instruct 128K context $0.075/M input $0.2/M output

Anthropic: Anthropic: Claude Opus 4 T

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...

anthropic/claude-opus-4 200K context $15/M input $75/M output

Anthropic: Anthropic: Claude Sonnet 4 T

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-art performance on SWE-bench (72.7%),...

anthropic/claude-sonnet-4 200K context $3/M input $15/M output

Mistral AI: Mistral: Mistral Medium 3 T

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 and multimodal performance with 8× lower cost...

mistralai/mistral-medium-3 131.072K context $0.4/M input $2/M output

Google: Google: Gemini 2.5 Pro Preview 05-06 T

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 responses with enhanced accuracy...

google/gemini-2.5-pro-preview-05-06 1.04858M context $1.25/M input $10/M output

Meta: Meta: Llama Guard 4 12B T

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...

meta-llama/llama-guard-4-12b 163.84K context $0.18/M input $0.18/M output

OpenAI: OpenAI: o4 Mini High T

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 performance while retaining...

openai/o4-mini-high 200K context $1.1/M input $4.4/M output

Meta: Meta: Llama 4 Maverick T

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 forward...

meta-llama/llama-4-maverick 128K context $0.188/M input $0.652/M output

Meta: Meta: Llama 4 Scout T

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...

meta-llama/llama-4-scout 327.68K context $0.1/M input $0.3/M output

Mistral AI: Mistral: Mistral Small 3.1 24B T

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-based reasoning and...

mistralai/mistral-small-3.1-24b-instruct 128K context $0.351/M input $0.555/M output

Alibaba Qwen: Qwen: Qwen2.5 VL 72B Instruct T

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.

qwen/qwen2.5-vl-72b-instruct 128K context $0.8/M input $1/M output

MiniMax: MiniMax: MiniMax-01 T

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 handle a context...

minimax/minimax-01 1.00019M context $0.2/M input $1.1/M output

Meta: Meta: Llama 3.2 11B Vision Instruct T

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...

meta-llama/llama-3.2-11b-vision-instruct 131.072K context $0.345/M input $0.345/M output

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

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 affordable...

openai/gpt-4o-mini-2024-07-18 128K context $0.15/M input $0.6/M output

Anthropic: Anthropic: Claude 3 Haiku T

Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) #multimodal

anthropic/claude-3-haiku 200K context $0.25/M input $1.25/M output

Openrouter: Auto Router T

The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on...

openrouter/auto 2M context Input not listed Output not listed

Meta: meta-llama/Llama-4-Maverick-17B-128E-Instruct