AI model library

Discover language, multimodal, image, video, audio and embedding models. Compare capabilities, context limits, platform pricing and original sources.

29,581 matching models

Qwen: Qwen3.6 35B A3B

qwen/qwen3.6-35b-a3b-20260415

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 architecture combining Gated DeltaNet linear attention with standard gated attention layers

Context window
262,144
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput

Benchmarks

  • Artificial Analysis: 18.2
  • OpenRouter Benchmarks: 75.692%

Inference prices

  • Published price : $0.02 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.10 / input_tokens_per_million · openRouter ↗
  • Published price : $0.90 / output_tokens_per_million · openRouter ↗

Qwen: Qwen3.5-122B-A10B

qwen/qwen3.5-122b-a10b-20260224

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 efficiency. In terms of overall performance, this model is second only to Qwen3.5-3

Context window
262,144
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 17.7
  • OpenRouter Benchmarks: 78.182%

Inference prices

DeepSeek: DeepSeek V3.1 Terminus

deepseek/deepseek-v3.1-terminus

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in co

Context window
163,840
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 14.8
  • LMArena: 1,417.22
  • OpenRouter Benchmarks: 73.333%

Inference prices

  • Published price : $0.27 / input_tokens_per_million · deepInfra ↗
  • Published price : $0.95 / output_tokens_per_million · deepInfra ↗

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

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

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved perfor

Context window
128,000
Input modalities
text, image, file
Output modalities
text
Capabilities
audioInput, fileInput, multimodal, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 7.3
  • LiveBench: 54.359%
  • LLM Stats · GitHub archive: 0.905
  • LMArena: 1,300.443
  • SWE-bench: 58.2%

Inference prices

Amazon: Nova 2 Lite

amazon/nova-2-lite-v1

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

Context window
1,000,000
Input modalities
text, image, video, file
Output modalities
text
Capabilities
fileInput, multimodal, reasoning, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 13.4

Inference prices

OpenAI: GPT-4 Turbo (batch)

openai/gpt-4-turbo

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

Context window
128,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 7

Inference prices

Google: Gemma 4 26B A4B

google/gemma-4-26b-a4b-it-20260403

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 quality at a fraction of the compute cost. Supports multimodal input including text,

Context window
262,144
Input modalities
image, text, video
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 16.7
  • OpenRouter Benchmarks: 65.209%

Inference prices

  • Published price : $0.05 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.09 / input_tokens_per_million · openRouter ↗
  • Published price : $0.30 / output_tokens_per_million · openRouter ↗

MoonshotAI: Kimi K2 Thinking

moonshotai/kimi-k2-thinking-20251106

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) architecture introduced in Kimi K2, it activates 32 billion parameters per forward

Context window
262,144
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 22
  • OpenCompass LLM: 94.1%

Inference prices

  • Published price : $0.15 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.60 / input_tokens_per_million · openRouter ↗
  • Published price : $2.50 / output_tokens_per_million · openRouter ↗

OpenAI: GPT-4.1 Mini

openai/gpt-4.1-mini-2025-04-14

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 instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong c

Context window
1,047,576
Input modalities
image, text, file
Output modalities
text
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 10.2
  • BFCL: 50.45%
  • LMArena: 1,340.532
  • OpenRouter Benchmarks: 64.927%
  • SWE-bench: 23.94%

Inference prices

NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b-20230311

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 Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP)

Context window
262,144
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 12.8

Inference prices

Qwen: Qwen3 Coder Next

qwen/qwen3-coder-next-2025-02-03

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 token, delivering performance comparable to models with 10 to 20x higher active co

Context window
262,144
Input modalities
text
Output modalities
text
Capabilities
promptCaching, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 9.2
  • OpenRouter Benchmarks: 76.263%

Inference prices

  • Published price : $0.07 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.12 / input_tokens_per_million · openRouter ↗
  • Published price : $0.80 / output_tokens_per_million · openRouter ↗

Google: Gemini 2.5 Pro

google/gemini-2.5-pro

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieve

Context window
1,048,576
Input modalities
text, image, file, audio, video
Output modalities
text
Capabilities
audioInput, batch, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch

Benchmarks

  • Artificial Analysis: 16.1
  • Kaggle Benchmarks: 81.081
  • LLM Stats · GitHub archive: 0.92
  • LMArena: 1,457.88
  • OpenRouter Benchmarks: 82.239%
  • SWE-bench: 53.6%

Inference prices

Mistral: Devstral 2 2512

mistralai/devstral-2512

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 exploring...

Context window
262,144
Input modalities
text, file
Output modalities
text
Capabilities
fileInput, multimodal, promptCaching, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 8.6
  • SWE-bench: 53.8%

Inference prices

  • Published price : $0.04 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.40 / input_tokens_per_million · openRouter ↗
  • Published price : $2.00 / output_tokens_per_million · openRouter ↗

Inception: Mercury 2

inception/mercury-2-20260304

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, achieving...

Context window
128,000
Input modalities
text
Output modalities
text

Benchmarks

  • Artificial Analysis: 10.8

inclusionAI: Ling 3.0 Tiny

inclusionai/ling-3.0-tiny-20260806

Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable thinking and instant modes.

Context window
262,144
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 26.5

Inference prices

  • Published price : $0.0030 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.02 / input_tokens_per_million · openRouter ↗
  • Published price : $0.05 / output_tokens_per_million · openRouter ↗

Qwen: Qwen3.5-9B

qwen/qwen3.5-9b-20260310

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 vision-language design with early fusion of multimodal tokens, allowing the mod

Context window
262,144
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput

Benchmarks

  • Artificial Analysis: 13.3
  • OpenRouter Benchmarks: 74.405%

Inference prices

  • Published price : $0.05 / cache_read_tokens_per_million · openRouter ↗
  • Published price : $0.05 / input_tokens_per_million · openRouter ↗
  • Published price : $0.08 / output_tokens_per_million · openRouter ↗

NVIDIA: Nemotron 3 Nano Omni (free)

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428

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 audio inputs and produces text output, enabling agents to perceive and reason across modaliti

Context window
256,000
Input modalities
text, audio, image, video
Output modalities
text
Capabilities
audioInput, multimodal, reasoning, toolCalling, transcription, visionInput

Benchmarks

  • Artificial Analysis: 10.3

Inference prices

OpenAI: GPT-4

openai/gpt-4

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning capabilities. Training data: up to Sep 2021.

Context window
8,191
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 6.7

Inference prices

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace