Token prices, context windows and benchmark scores for 100 models from 22 providers. Prices are in USD per 1M tokens. Models are ranked by AgenticScore, our weighting of independent benchmarks for agent and coding work.
53 open-weight · 98 with tool calling · Updated
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...
Prices per 1M tokens
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...
Prices per 1M tokens
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
Prices per 1M tokens
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...
Prices per 1M tokens
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...
Prices per 1M tokens
Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.
Prices per 1M tokens
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...
Prices per 1M tokens
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...
Prices per 1M tokens
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
Prices per 1M tokens
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
Prices per 1M tokens
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...
Prices per 1M tokens
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Prices per 1M tokens
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...
Prices per 1M tokens
Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...
Prices per 1M tokens
Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...
Prices per 1M tokens
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...
Prices per 1M tokens
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...
Prices per 1M tokens
Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.
Prices per 1M tokens
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
Prices per 1M tokens
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
Prices per 1M tokens
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
Prices per 1M tokens
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...
Prices per 1M tokens
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Prices per 1M tokens
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...
Prices per 1M tokens
AgenticScore is a 0–100 composite we calculate for agent and coding work. 80% comes from independent benchmarks: the Artificial Analysis Coding Index at 35% (SWE-bench Verified is used when that index is missing), the Artificial Analysis Intelligence Index at 25%, and the Artificial Analysis Agentic Index at 20%. The other 20% is split between output token price (10%) and capability support (10%: tool calling, reasoning, vision, prompt caching, computer use and structured output). When a model is missing one of the benchmark signals, the remaining benchmark weights are scaled up to fill the gap.
Token prices and context windows are synced from OpenRouter's model catalog (with LiteLLM's price list as a fallback) and shown in US dollars per 1 million tokens. Benchmark indexes come from Artificial Analysis; SWE-bench Verified scores are taken from the providers' published results. The directory was last updated on September 12, 2026.
Developers can rate a model from 1 to 10 on code quality, instruction following, speed and value for money. A model only shows a community rating after people have actually rated it; until then it says “No ratings yet”.
Start with models that support tool calling, then compare AgenticScore against output price, since agents generate a lot of output tokens. Check the context window if your agent reads large codebases. Right now the highest AgenticScore in the directory is Claude Fable 5.1 at 84.1. Use the compare view to put up to three models side by side.
AgenticMarket