Source: github.com/cline/cline/releases/tag/cli-v3.0.73
The release lets GPT-6 models such as gpt-6-sol and gpt-6.1-sol run on OpenAI and Azure OpenAI-compatible endpoints. Cline previously sent max_tokens instead of max_completion_tokens, so every request to these models was rejected.
When no model is chosen, the Cline provider now uses Claude Sonnet 5.5, which Cline's recommended list places at the top again. The model catalog was also refreshed, adding the CommandCode and Reflection providers.
Default models changed for 302.AI (Gemini 4 Argon), Eden AI and Prime Inference (Muse Spark Open), CoreWeave (Reflection Beam 1.0), NanoGPT, Pioneer (Nemotron 3.5 Super VL), and Scaleway (DeepSeek V4.1 Flash). The changes are listed in the full changelog from cli-v3.0.72 to cli-v3.0.73.
Why it matters if you build agents
If your agent calls GPT-6 models through OpenAI or Azure OpenAI-compatible endpoints via Cline, requests that were previously rejected should now go through. If you rely on Cline's defaults, check which model you get, since defaults changed for several providers. Set an explicit model if your agent's behavior depends on a specific one.
Get stories like this every weekday
One short email with the day's agent tooling news.