Input $1.4→$0.1785 · Output $4.4→$2.805 per 1M tokens
Input $2→$4 · Output $10→$20 per 1M tokens
Input $0.27→$0.1344 · Output $0.41→$0.2016 per 1M tokens
Input $0.035→$0.3 · Output $0.29→$1.2 per 1M tokens
Input $0.0825→$0.132 · Output $0.33→$0.528 per 1M tokens
Input $0.9646→$1.4 · Output $3.0316→$4.4 per 1M tokens
Input $0.045→$0.15 · Output $0.14→$0.5 per 1M tokens
Input $0.95→$0.65 · Output $4→$3.41 per 1M tokens
Input $0.21→$0.3 · Output $0.84→$1.2 per 1M tokens
Input $0.3125→$0.1625 · Output $1.25→$1.3 per 1M tokens
Input $0.269→$0.28 · Output $0.4→$0.42 per 1M tokens
Input $0.348→$0.9553 · Output $0.696→$1.9105 per 1M tokens
Input $0.0675→$0.09 · Output $0.225→$0.3 per 1M tokens
Input $0.0469→$0.14 · Output $0.0938→$0.28 per 1M tokens
Input $0.293→$0.3995 · Output $3.5→$4.2 per 1M tokens
Input $0.25→$0.29 · Output $1→$1.14 per 1M tokens
Input $0.2156→$0.44 · Output $0.6468→$1.32 per 1M tokens
Listed with an expiration date of 2026-09-28.
Listed with an expiration date of 2026-09-28.
Listed with an expiration date of 2026-09-28.
Listed with an expiration date of 2026-09-28.
Furniture Assembly 44.2%
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...
Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openrouter.ai/~typesafe/jev-latest), TypeSafe's first System One model, and adapts as yo
Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,.
Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using r
Furniture Assembly 22.5%
Furniture Assembly 40.0%
Furniture Assembly 20.8%
GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token.
Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...
Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...
Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...
Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...
Furniture Assembly 28.3%
Furniture Assembly 58.3%
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...
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...
GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: ht