xiaomi/mimo-v2.6-pro-20260921
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding workloads. The model features a 1M-token context window and native multimodal capabilities. Optimize
- Context window
- 1,050,000
- Input modalities
- text, image, video, audio
- Output modalities
- text
- Capabilities
- audioInput, multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 29.9
- OpenRouter Benchmarks: 90.123%
Inference prices
inclusionai/ling-3.1-flash-20261002
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
- Context window
- 1,000,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, toolCalling
Benchmarks
- Artificial Analysis: 29.6
- OpenRouter Benchmarks: 94.792%
Inference prices
minimax/minimax-m3.1-flash-20261019
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real c
- Context window
- 1,048,576
- Input modalities
- text, image, video
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 29.1
- OpenRouter Benchmarks: 86.785%
Inference prices
deepseek/deepseek-v4.1-flash-20261017
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) archite
- Context window
- 1,048,576
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 28.6
- OpenRouter Benchmarks: 92.812%
Inference prices
stepfun/step-5-preview-20261008
Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance. It is designed
- Context window
- 1,000,000
- Input modalities
- text, image, video
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 28.5
Inference prices
openai/gpt-6-luna-20260922
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex softw
- Context window
- 1,050,000
- Input modalities
- file, image, text
- Output modalities
- text
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Benchmarks
- Artificial Analysis: 27.9
- LMArena: 1,388.381
- OpenRouter Benchmarks: 88.159%
Inference prices
z-ai/glm-5.3-flash-20260826
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.
- Context window
- 1,048,576
- Input modalities
- text, image, video
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 27.8
- OpenRouter Benchmarks: 92.521%
- Vercel AI Gateway: 7.127%
Inference prices
xiaomi/mimo-v2.6-flash-20260921
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for greater computational efficiency. The model features a 1M-token c
- Context window
- 1,050,000
- Input modalities
- text, image, video, audio
- Output modalities
- text
- Capabilities
- audioInput, multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 26.7
- OpenRouter Benchmarks: 77.667%
Inference prices
openai/gpt-5.6-luna-20260709
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.
- Context window
- 1,050,000
- Input modalities
- file, image, text
- Output modalities
- text
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Benchmarks
- Artificial Analysis: 23.8
- LMArena: 1,431.01
- OpenRouter Benchmarks: 72.667%
Inference prices
deepseek/deepseek-v4-pro-20260813
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
- Context window
- 1,048,576
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 23.1
- OpenRouter Benchmarks: 91.898%
Inference prices
inclusionai/ling-3.0-flash-fin-20260827
Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment...
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 22.6
- OpenRouter Benchmarks: 65.333%
Inference prices
deepseek/deepseek-v4-pro-20260423
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 reasoning, coding, and long-horizon agent workflows, with strong performance across k
- Context window
- 1,048,576
- Input modalities
- text
- Output modalities
- text
- Capabilities
- audioInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 20.8
- Kaggle Benchmarks: 1,387.2
- OpenCompass LLM: 97.1%
- OpenRouter Benchmarks: 91.688%
Inference prices
qwen/qwen3.8-27b-20260814
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.
- Context window
- 1,024,000
- Input modalities
- text, image, video
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 20.1
- OpenRouter Benchmarks: 83.165%
Inference prices
minimax/minimax-m3-20260531
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full a
- Context window
- 1,048,576
- Input modalities
- text, image, video
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, streaming, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 18.9
- OpenCompass LLM: 90.8%
- OpenRouter Benchmarks: 91.659%
Inference prices
moonshotai/kimi-k3-20260715
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against ima
- Context window
- 1,048,576
- Input modalities
- text, image, video
- Output modalities
- text
- Capabilities
- audioInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 17.4
- OpenRouter Benchmarks: 93.07%
- Vercel AI Gateway: 7.458%
Inference prices
thinkingmachines/inkling-small-20260730
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retri
- Context window
- 524,288
- Input modalities
- text, image, audio
- Output modalities
- text
- Capabilities
- audioInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 12.9
- OpenRouter Benchmarks: 87.037%
Inference prices
thinkingmachines/inkling-20260715
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and m
- Context window
- 524,288
- Input modalities
- text, image, audio
- Output modalities
- text
- Capabilities
- audioInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 12.5
- OpenRouter Benchmarks: 69%
Inference prices
google/gemini-3.5-flash-lite-20260721
Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.
- Context window
- 1,048,576
- Input modalities
- text, image, video, file, audio
- Output modalities
- text
- Capabilities
- audioInput, batch, computerUse, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch
Benchmarks
- Artificial Analysis: 11.7
- LMArena: 1,434.544
- OpenRouter Benchmarks: 73.333%
Inference prices