GitHub[208K]Try OpenCode

Updated Sep 22, 10:08 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.

3.1TJUL 29JUL 29

2.8TJUL 30JUL 30

3.3TJUL 31JUL 31

3.8TAUG 1AUG 1

4.6TAUG 2AUG 2

6.1TAUG 3AUG 3

5.8TAUG 4AUG 4

7.5TAUG 5AUG 5

8.9TAUG 6AUG 6

9.1TAUG 7AUG 7

9.1TAUG 8AUG 8

9.2TAUG 9AUG 9

10TAUG 10AUG 10

16TAUG 11AUG 11

19TAUG 12AUG 12

21TAUG 13AUG 13

22TAUG 14AUG 14

20TAUG 15AUG 15

18TAUG 16AUG 16

14TAUG 17AUG 17

13TAUG 18AUG 18

12TAUG 19AUG 19

13TAUG 20AUG 20

12TAUG 21AUG 21

13TAUG 22AUG 22

15TAUG 23AUG 23

19TAUG 24AUG 24

18TAUG 25AUG 25

16TAUG 26AUG 26

12TAUG 27AUG 27

10TAUG 28AUG 28

9.1TAUG 29AUG 29

8.6TAUG 30AUG 30

10TAUG 31AUG 31

11TSEP 1SEP 1

10TSEP 2SEP 2

12TSEP 3SEP 3

13TSEP 4SEP 4

11TSEP 5SEP 5

11TSEP 6SEP 6

12TSEP 7SEP 7

12TSEP 8SEP 8

13TSEP 9SEP 9

16TSEP 10SEP 10

16TSEP 11SEP 11

16TSEP 12SEP 12

15TSEP 13SEP 13

18TSEP 14SEP 14

19TSEP 15SEP 15

20TSEP 16SEP 16

21TSEP 17SEP 17

19TSEP 18SEP 18

16TSEP 19SEP 19

17TSEP 20SEP 20

20TSEP 21SEP 21

19TSEP 22SEP 22

deepseek-v4.1-flash55T

DeepSeek+67%

muse-spark-1.3-contributor37T

Meta+1%

deepseek-v4-flash18T

DeepSeek-13%

mimo-v2.56.3T

Xiaomi-30%

nemotron-3-ultra3.3T

NVIDIA+47%

muse-spark-1.2-contributor3.0T

Meta-20%

glm-5.3-flash3.0T

Zhipu-18%

deepseek-v4-flash-vision-exp1.1T

DeepSeek+3%

mimo-v2.6-flash911B

XiaomiNew

deepseek-v4-pro731B

DeepSeek0%

ling-3.0-flash-fin699B

union-alpha470B

nemotron-3.5-lightning365B

NVIDIA-20%

qwen3.8-flash321B

-16%

minimax-m3276B

MiniMax-7%

deepseek-v4p1-flash252B

DeepSeekNew

omen-alpha188B

-72%

deepseek-v4.1-flash55T

DeepSeek+67%

muse-spark-1.3-contributor37T

Meta+1%

deepseek-v4-flash18T

DeepSeek-13%

mimo-v2.56.3T

Xiaomi-30%

nemotron-3-ultra3.3T

NVIDIA+47%

muse-spark-1.2-contributor3.0T

Meta-20%

glm-5.3-flash3.0T

Zhipu-18%

deepseek-v4-flash-vision-exp1.1T

DeepSeek+3%

mimo-v2.6-flash911B

XiaomiNew

deepseek-v4-pro731B

DeepSeek0%

ling-3.0-flash-fin699B

union-alpha470B

nemotron-3.5-lightning365B

NVIDIA-20%

qwen3.8-flash321B

-16%

minimax-m3276B

MiniMax-7%

deepseek-v4p1-flash252B

DeepSeekNew

omen-alpha188B

-72%

LEARN MORETOP MODELS▸

Unique Users. Daily unique OpenCode users by model.

141KJUL 29JUL 29

139KJUL 30JUL 30

142KJUL 31JUL 31

110KAUG 1AUG 1

112KAUG 2AUG 2

169KAUG 3AUG 3

194KAUG 4AUG 4

180KAUG 5AUG 5

183KAUG 6AUG 6

189KAUG 7AUG 7

167KAUG 8AUG 8

161KAUG 9AUG 9

225KAUG 10AUG 10

408KAUG 11AUG 11

406KAUG 12AUG 12

393KAUG 13AUG 13

391KAUG 14AUG 14

333KAUG 15AUG 15

336KAUG 16AUG 16

455KAUG 17AUG 17

427KAUG 18AUG 18

441KAUG 19AUG 19

423KAUG 20AUG 20

432KAUG 21AUG 21

357KAUG 22AUG 22

320KAUG 23AUG 23

453KAUG 24AUG 24

440KAUG 25AUG 25

430KAUG 26AUG 26

388KAUG 27AUG 27

343KAUG 28AUG 28

266KAUG 29AUG 29

260KAUG 30AUG 30

352KAUG 31AUG 31

343KSEP 1SEP 1

332KSEP 2SEP 2

352KSEP 3SEP 3

328KSEP 4SEP 4

254KSEP 5SEP 5

246KSEP 6SEP 6

309KSEP 7SEP 7

299KSEP 8SEP 8

283KSEP 9SEP 9

319KSEP 10SEP 10

293KSEP 11SEP 11

235KSEP 12SEP 12

235KSEP 13SEP 13

317KSEP 14SEP 14

317KSEP 15SEP 15

331KSEP 16SEP 16

334KSEP 17SEP 17

282KSEP 18SEP 18

258KSEP 19SEP 19

242KSEP 20SEP 20

320KSEP 21SEP 21

327KSEP 22SEP 22

Weekly Retention. Weekly users returning the next week.

LEARN MORETOP MODELS▸

Session Cost. Average cost per session.

COST / SESSION

TOKENS / SESSION

Cost/Session$0.0048

Tokens/Session1.1M

LEARN MORESESSION COST▸

Token Cost. Price per 1M tokens.

Input$0.15

Output$0.60

Cached$0.0030

LEARN MORETOKEN COST▸

Cache Ratio. Share of input tokens served from cache.

Cache Ratio97%

Cached53T

Uncached1.6T

LEARN MOREMARKET SHARE▸

Geographic Breakdown

Model Comparisons. Popular model pairs from the leaderboard.

Top two by recent usagedeepseek-v4.1-flash vs muse-spark-1.3-contributordeepseek-v4.1-flashmuse-spark-1.3-contributor Leader vs challengerdeepseek-v4.1-flash vs deepseek-v4-flashdeepseek-v4.1-flashdeepseek-v4-flash Adjacent leaderboard pairmuse-spark-1.3-contributor vs deepseek-v4-flashmuse-spark-1.3-contributordeepseek-v4-flash Top model alternativedeepseek-v4-flash vs mimo-v2.5deepseek-v4-flashmimo-v2.5

Model Data

#Top Models. Usage of models across OpenCode.

Top Models. Usage of models across OpenCode.