anthropic/claude-4.5-sonnet-20250929
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 improvements across system design, code security, and specific
- Context window
- 1,000,000
- Input modalities
- text, image, file
- Output modalities
- text
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 20.7
- BFCL: 73.24%
- LMArena: 1,438.594
- OpenRouter Benchmarks: 80.931%
- SWE-bench: 70.6%
- Vercel AI Gateway: 6.907%
qwen/qwen3.5-397b-a17b-20260216
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 inference efficiency. It delivers state-of-the-art performance comparable to leading-e
- Context window
- 262,144
- Input modalities
- text, image, video
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 21.4
- OpenCompass LLM: 88.4%
- OpenRouter Benchmarks: 79.952%
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%
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%
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%
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%
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%
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
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%
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%
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
qwen/qwen3-235b-a22b-thinking-2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This "thinking-only" var
- Context window
- 128,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 12.7
- LMArena: 1,415.543
- OpenCompass LLM: 83.5%
- OpenRouter Benchmarks: 80.303%
openai/gpt-5-mini-2025-08-07
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 and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.
- Context window
- 400,000
- Input modalities
- text, image, file
- Output modalities
- text
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Benchmarks
- Artificial Analysis: 20.6
- BFCL: 55.46%
- Kaggle Benchmarks: 484
- LMArena: 1,373.362
- OpenRouter Benchmarks: 72.444%
- SWE-bench: 56.2%
openai/gpt-4.1-nano-2025-04-14
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 token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even
- Context window
- 1,047,576
- Input modalities
- image, text, file
- Output modalities
- text
- Capabilities
- fileInput, multimodal, promptCaching, structuredOutputs, toolCalling, visionInput, webSearch
Benchmarks
- Artificial Analysis: 7.8
- BFCL: 33.05%
- LMArena: 1,284.787
- OpenRouter Benchmarks: 50.505%
openai/gpt-oss-20b
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardw
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 10
- HELM Capabilities: 56.467%
- Kaggle Benchmarks: 100%
- LLM Stats · GitHub archive: 0.173
- OpenCompass LLM: 87.9%
- OpenRouter Benchmarks: 44.877%
qwen/qwen3-32b-04-28
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 for tasks like math, coding, and logical inference, and a "non-thinking" mode fo
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 7.3
- BFCL: 48.71%
- LLM Stats · GitHub archive: 0.73
- LMArena: 1,340.076
- OpenCompass LLM: 57.6%
- OpenRouter Benchmarks: 63.343%
nvidia/nemotron-3-nano-30b-a3b
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 8.9
- LMArena: 1,348.09
- OpenRouter Benchmarks: 47.5%
qwen/qwen3-14b-04-28
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 for tasks like math, programming, and logical inference, and a "non-thinking" mod
- Context window
- 40,960
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 6.7
- BFCL: 41.03%
- OpenRouter Benchmarks: 59.788%