The current free models provided by OpenCode are currently: Nemotron (NVidia), Hy3 (Tencent), Muse Spark (Meta), Ox Alpha (stealth/unknown developer), Mimo (Xiaomi), Big Pickle (OpenCode).
The current free models provided by OpenCode are currently: Nemotron (NVidia), Hy3 (Tencent), Muse Spark (Meta), Ox Alpha (stealth/unknown developer), Mimo (Xiaomi), Big Pickle (OpenCode).
4 comments
Meta Spark has been added as a free model, I guess as a replacement, since this is now the cheap model at reasonable intelligence.
It's available with Go (subscription) and they are working on making it cheaper after the recent price increase, that may see them add it back to free.
Anyway, I suspect it was just pricing. They seemed to suggest they were running it on their own hardware? But I'm not sure that was actually the case. As soon as DeepSeek's pricing changed, they basically fell back to higher prices as well.
I was very confused why I was getting approximately $30 of spend when I thought I was paying for $60, but I guess I shouldn't complain when I have a DeepSeek account and I was paying for far more token usage on OpenCode Go.
I have since defaulted my private harness to muse-spark-1.2-contributor-free, because that seems to be the prevailing model out of the current Zen list.
Where did you see this? I was to manually opt in to "allow models hosted in China" and there is writing about how their no data retention agreement with DeepSeek is only temporary -- both things such that have an implication that they are not running it inhouse.