Updated Sep 22, 11:09 PM UTC
Model Data
See which models are winning real usage, how the mix is shifting, and what that means for cost.
Top Models. Usage of models across OpenCode.
010203
deepseek-v4.1-flash55T
DeepSeek+68%
muse-spark-1.3-contributor37T
Meta+2%
deepseek-v4-flash18T
DeepSeek-13%
040506070809101112131415161718
mimo-v2.56.3T
Xiaomi-30%
nemotron-3-ultra3.4T
NVIDIA+48%
muse-spark-1.2-contributor3.1T
Meta-19%
glm-5.3-flash3.0T
Zhipu-18%
deepseek-v4-flash-vision-exp1.1T
DeepSeek+3%
mimo-v2.6-flash942B
XiaomiNew
deepseek-v4-pro735B
DeepSeek+1%
ling-3.0-flash-fin702B
+51%
gpt-5.6-luna582B
OpenAI+4%
union-alpha470B
New
nemotron-3.5-lightning367B
NVIDIA-19%
qwen3.8-flash323B
-16%
minimax-m3278B
MiniMax-6%
deepseek-v4p1-flash252B
DeepSeekNew
omen-alpha189B
-72%
010203040506070809101112131415161718
deepseek-v4.1-flash55T
DeepSeek+68%
muse-spark-1.3-contributor37T
Meta+2%
deepseek-v4-flash18T
DeepSeek-13%
mimo-v2.56.3T
Xiaomi-30%
nemotron-3-ultra3.4T
NVIDIA+48%
muse-spark-1.2-contributor3.1T
Meta-19%
glm-5.3-flash3.0T
Zhipu-18%
deepseek-v4-flash-vision-exp1.1T
DeepSeek+3%
mimo-v2.6-flash942B
XiaomiNew
deepseek-v4-pro735B
DeepSeek+1%
ling-3.0-flash-fin702B
+51%
gpt-5.6-luna582B
OpenAI+4%
union-alpha470B
New
nemotron-3.5-lightning367B
NVIDIA-19%
qwen3.8-flash323B
-16%
minimax-m3278B
MiniMax-6%
deepseek-v4p1-flash252B
DeepSeekNew
omen-alpha189B
-72%
Unique Users. Daily unique OpenCode users by model.
Weekly Retention. Weekly users returning the next week.
- 01deepseek-v4.1-flash85.0%23K
- 02muse-spark-1.3-contributor83.3%13K
- 03muse-spark-1.2-contributor81.1%8.2K
- 04longcat-2.077.7%359
- 05mimo-v2.572.7%28K
- 06hy371.1%3.4K
- 07qwen3.8-flash70.9%3.7K
- 08glm-5.3-flash69.3%53K
- 09omen-alpha69.3%3.3K
- 10deepseek-v4-flash-vision-exp68.0%17K
- 11qwen3.5-plus67.8%264
- 12deepseek-v4-flash67.6%486K
- 13kimi-k2.566.3%664
- 14minimax-m2.765.8%3.0K
- 15mimo-v2.5-pro64.9%7.0K
Session Cost. Average cost per session.
COST / SESSION
TOKENS / SESSION
Cost/Session$0.0048
Tokens/Session1.1M
Token Cost. Price per 1M tokens.
Input$0.15
Output$0.60
Cached$0.0030
Cache Ratio. Share of input tokens served from cache.
Cache Ratio97%
Cached53T
Uncached1.6T
Model Comparisons. Popular model pairs from the leaderboard.
Top two by recent usagedeepseek-v4.1-flash vs muse-spark-1.3-contributordeepseek-v4.1-flash·muse-spark-1.3-contributorLeader vs challengerdeepseek-v4.1-flash vs deepseek-v4-flashdeepseek-v4.1-flash·deepseek-v4-flashAdjacent leaderboard pairmuse-spark-1.3-contributor vs deepseek-v4-flashmuse-spark-1.3-contributor·deepseek-v4-flashTop model alternativedeepseek-v4-flash vs mimo-v2.5deepseek-v4-flash·mimo-v2.5