Discover language, multimodal, image, video, audio and embedding models. Compare capabilities, context limits, platform pricing and original sources.
qwen/qwen3.6-plus-04-02
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 the 3.5 series, it delivers major gains in agentic coding, front-end development,
- Context window
- 1,000,000
- Input modalities
- text, image, video
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
Inference prices
- Published price : $0.41 / cache_write_tokens_per_million · openRouter ↗
- Published price : $0.33 / input_tokens_per_million · openRouter ↗
- Published price : $1.95 / output_tokens_per_million · openRouter ↗
z-ai/glm-5.2-20260616
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation. Reasoning efforts `high` and `xhigh` are s
- Context window
- 1,048,576
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 33.7
- OpenRouter Benchmarks: 76.933%
Inference prices
- Published price : $0.01 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.01 / input_tokens_per_million · openRouter ↗
- Published price : $6.80 / output_tokens_per_million · openRouter ↗
x-ai/grok-build-0.1-20260520
Grok Build 0.1 is SpaceXAI’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 agents, tool use, and multi-step development tasks. The model powers SpaceXA
- Context window
- 256,000
- Input modalities
- text, image, file
- Output modalities
- text
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Benchmarks
- Artificial Analysis: 27.2
- LMArena: 1,163.967
Inference prices
openai/gpt-5.1-20251113
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. It uses adaptive reasoning to allocate computation dynamically, responding quick
- Context window
- 400,000
- Input modalities
- image, text, file
- Output modalities
- text
- Capabilities
- fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 24.7
- LMArena: 1,442.598
- OpenRouter Benchmarks: 80%
- SWE-bench: 66%
Inference prices
google/gemini-3.6-flash-20260721
Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete
- 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: 34
- LMArena: 1,479.263
- OpenRouter Benchmarks: 93.013%
Inference prices
meta/muse-spark-1.1-20260709
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window. The model is designed to orchestrate multi-agent workflows, acting as either a main agent that p
- Context window
- 1,048,576
- Input modalities
- text, image, video, file
- Output modalities
- text
- Capabilities
- audioInput, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch
Benchmarks
- Artificial Analysis: 33.7
Inference prices
- Standard · Cached input / 1M tokens : $0.15 / cache_read_tokens_per_million · meta ↗
- Standard · Input / 1M tokens : $1.25 / input_tokens_per_million · meta ↗
- Standard · Output / 1M tokens : $4.25 / output_tokens_per_million · meta ↗
google/gemini-3.5-flash-20260519
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 agentic execution loops, supporting text, image, video, audio, and PDF inputs. Def
- 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: 33.6
- LMArena: 1,482.936
- OpenRouter Benchmarks: 92.256%
Inference prices
anthropic/claude-4.6-sonnet-20260217
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, end-to-end project management with memory, polished document creation, and confi
- Context window
- 1,000,000
- Input modalities
- text, image, file
- Output modalities
- text
- Capabilities
- batch, computerUse, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Benchmarks
- Artificial Analysis: 30.1
- OpenRouter Benchmarks: 74.2%
Inference prices
moonshotai/kimi-k2.5-0127
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 approximately 15T mixed visual and text tokens, it delivers strong performance in ge
- Context window
- 262,144
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 23.5
- OpenRouter Benchmarks: 90.284%
Inference prices
- Cached input tokens (per 1M) : $0.07 / cache_read_tokens_per_million · siliconFlow ↗
- Input tokens (per 1M) : $0.45 / input_tokens_per_million · siliconFlow ↗
- Output tokens (per 1M) : $2.25 / output_tokens_per_million · siliconFlow ↗
motif-technologies/motif-3
Motif 3 is a Mixture-of-Experts language model from Motif Technologies, with 314B total and 13.2B active parameters. It is a general-purpose multilingual model for English and Korean, particularly strong at long-horizon agentic tool use and terminal-based problem solving, with ad
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 63.5
Inference prices
- Published price : $0.06 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.30 / input_tokens_per_million · openRouter ↗
- Published price : $1.20 / output_tokens_per_million · openRouter ↗
z-ai/glm-4.6
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...
- Context window
- 204,800
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 18.5
- BFCL: 72.38%
- OpenCompass LLM: 78.2%
- OpenRouter Benchmarks: 85.607%
- SWE-bench: 55.4%
Inference prices
- Published price : $0.50 / input_tokens_per_million · deepInfra ↗
- Published price : $2.00 / output_tokens_per_million · deepInfra ↗
z-ai/glm-4.7-20251222
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 in executing complex agent tasks while delivering more natural conversational e
- Context window
- 204,800
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 22.2
- OpenCompass LLM: 83.8%
- OpenRouter Benchmarks: 83.694%
Inference prices
- Published price : $0.08 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.40 / input_tokens_per_million · openRouter ↗
- Published price : $1.75 / output_tokens_per_million · openRouter ↗
qwen/qwen3.7-max-20260520
Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks, and long-horizon autonomous execution. The model offers notable gains
- Context window
- 1,000,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 29.5
- OpenRouter Benchmarks: 90.909%
Inference prices
deepseek/deepseek-v3.2-20251201
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 fine-grained sparse attention mechanism that reduces training and inference cost wh
- Context window
- 163,840
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 21.5
- OpenCompass LLM: 85.8%
- OpenRouter Benchmarks: 72.8%
Inference prices
- Published price : $0.13 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.26 / input_tokens_per_million · openRouter ↗
- Published price : $0.38 / output_tokens_per_million · openRouter ↗
inclusionai/ling-3.0-flash-vl-20260910
Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual agent capabilities. Hybrid instant/reasoning model with tool calling.
- Context window
- 131,072
- Input modalities
- text, image, video
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 24.6
- OpenRouter Benchmarks: 83.518%
Inference prices
- Published price : $0.01 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.06 / input_tokens_per_million · openRouter ↗
- Published price : $0.18 / output_tokens_per_million · openRouter ↗
tencent/hy3-preview-20260421
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, allowing it to balance speed and depth depending on the task, while delivering
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, toolCalling
Benchmarks
- Artificial Analysis: 25.3
- LMArena: 1,401.297
- OpenCompass LLM: 81%
Inference prices
- Published price : $0.06 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.18 / input_tokens_per_million · openRouter ↗
- Published price : $0.60 / output_tokens_per_million · openRouter ↗
moonshotai/kimi-k2.6-20260420
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 across Python, Rust, and Go, and can convert prompts and visual inputs into pro
- Context window
- 262,144
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 27
- OpenCompass LLM: 82.7%
- OpenRouter Benchmarks: 89.625%
Inference prices
moonshotai/kimi-k2.7-code-20260612
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates
- Context window
- 262,144
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput
Benchmarks
- Artificial Analysis: 25.8
- OpenRouter Benchmarks: 74.333%
Inference prices