Models

Muse Spark 1.3 Contributor is available in Writingmate. Here is how to evaluate it for long-context research, structured drafting, and professional reasoning work.

IBM's Granite 4.2 8B landed on OpenRouter this week, and it's now in Writingmate. I ran the broken-function, structured-extraction, and long-context drafting tests I use on every new model to see if a small enterprise model actually beats reaching for a flagship.

Hy4 preview is available in Writingmate. Here is how to evaluate it for long-context research, structured drafting, and professional reasoning work.

Wan 3.0 Prime is available in Writingmate. Here is how to test it for image, text, and multimodal agent workflows.

Qwen3.8 Flash is available in Writingmate. Here is how to evaluate it for long-context research, structured drafting, and professional reasoning work.

Wan 3.0 is available in Writingmate. Here is how to test it for image, text, and multimodal agent workflows.

Avatar IV is available in Writingmate. Here is how to test it for image, text, and multimodal agent workflows.

DeepSeek shipped its first vision-capable Flash model on August 21, 2026. I ran it through the same broken-function, agentic, and long-context tests I use on every release, then added a round of screenshots, charts, and scanned documents to see where "experimental" actually shows up.

Muse Spark 1.2 Contributor is available in Writingmate. Here is how to evaluate it for long-context research, structured drafting, and professional reasoning work.