Aggiornato 19 set, 20:17 UTC
Dati modello
Scopri quali modelli stanno vincendo nell'uso reale, come cambia il mix e cosa significa per i costi.
Modelli principali. Utilizzo dei modelli in OpenCode.
010203
deepseek-v4.1-flash51T
DeepSeek+279%
muse-spark-1.3-contributor36T
Meta-1%
deepseek-v4-flash18T
DeepSeek-17%
040506070809101112131415161718
mimo-v2.57.5T
Xiaomi-20%
muse-spark-1.2-contributor3.2T
Meta-30%
glm-5.3-flash3.1T
Zhipu-7%
nemotron-3-ultra2.7T
NVIDIA+10%
deepseek-v4-flash-vision-exp1.0T
DeepSeek+5%
deepseek-v4-pro711B
DeepSeek-2%
ling-3.0-flash-fin611B
+50%
gpt-5.6-luna563B
OpenAI-1%
union-alpha470B
Nuovo
nemotron-3.5-lightning424B
NVIDIA-26%
qwen3.8-flash324B
-32%
minimax-m3285B
MiniMax-5%
deepseek-v4p1-flash230B
DeepSeekNuovo
omen-alpha221B
-84%
kimi-k2.7-code176B
Moonshot+7%
010203040506070809101112131415161718
deepseek-v4.1-flash51T
DeepSeek+279%
muse-spark-1.3-contributor36T
Meta-1%
deepseek-v4-flash18T
DeepSeek-17%
mimo-v2.57.5T
Xiaomi-20%
muse-spark-1.2-contributor3.2T
Meta-30%
glm-5.3-flash3.1T
Zhipu-7%
nemotron-3-ultra2.7T
NVIDIA+10%
deepseek-v4-flash-vision-exp1.0T
DeepSeek+5%
deepseek-v4-pro711B
DeepSeek-2%
ling-3.0-flash-fin611B
+50%
gpt-5.6-luna563B
OpenAI-1%
union-alpha470B
Nuovo
nemotron-3.5-lightning424B
NVIDIA-26%
qwen3.8-flash324B
-32%
minimax-m3285B
MiniMax-5%
deepseek-v4p1-flash230B
DeepSeekNuovo
omen-alpha221B
-84%
kimi-k2.7-code176B
Moonshot+7%
Utenti unici. Utenti unici giornalieri di OpenCode per modello.
Weekly Retention. Weekly users returning the next week.
- 01muse-spark-1.3-contributor87.4%4.5K
- 02omen-alpha81.7%1.4K
- 03muse-spark-1.2-contributor81.5%7.7K
- 04longcat-2.078.1%242
- 05mimo-v2.572.9%26K
- 06qwen3.8-flash72.3%2.2K
- 07hy371.9%3.2K
- 08qwen3.5-plus69.8%285
- 09deepseek-v4-flash-vision-exp69.6%14K
- 10kimi-k2.569.5%763
- 11glm-5.3-flash68.8%41K
- 12deepseek-v4-flash68.3%483K
- 13minimax-m2.767.0%3.1K
- 14glm-564.6%807
- 15mimo-v2.5-pro64.4%7.4K
Costo sessione. Costo medio per sessione.
COSTO / SESSIONE
TOKEN / SESSIONE
Costo/sessione$0.0113
Token/sessione2.6M
Costo token. Prezzo per 1 M di token.
Input$0.15
Output$0.60
In cache$0.0030
Rapporto cache. Quota di token di input serviti dalla cache.
Rapporto cache97%
In cache687.4B
Non in cache19.1B
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