4d75d25236
model list update
2025-04-17 07:15:28 +10:00
ab21d7661d
xai checker + non standard oai model detection
2025-04-11 02:28:53 +10:00
c4d08a209b
oai update + deepseek support
2025-01-18 00:33:13 +10:00
3387a9c573
fix for valid oai keys with restricted permissions showing up as invalid
2024-08-30 00:39:15 +10:00
7eac116ce3
again
2024-07-20 17:57:37 +10:00
98ff213fdd
oai t5 tpm update (again)
2024-07-09 19:22:22 +10:00
960205b269
update t5 tpm for oai
2024-06-26 20:19:35 +10:00
2596b9c908
fix for model ordering
2024-06-07 01:18:44 +10:00
c286038efd
start checking for 0314 32k by default instead
...
don't think anybody cares about 'real' 32k keys that have 0613 anymore, 0314 always was the better model anyway, but we'll still mark them with a flag just in case
also brought back the readme
2024-05-20 07:50:42 +10:00
f88fe7faf9
schizo
2024-03-18 10:01:49 +10:00
5d99a6802a
\n
2024-02-15 05:01:28 +10:00
681bdc3134
fix for openai gateway timeout ratelimit and some aws changes
2024-02-15 04:55:28 +10:00
fc9b4fe95d
remove debug
2024-01-30 05:15:56 +10:00
e8a90abdc1
fix tiering not showing due to change with OAI rate limits
2024-01-30 05:15:16 +10:00
b3416a6e49
bug fixes
2024-01-24 07:07:55 +10:00
3ad16793a3
implement a concurrent connection limit so we don't overflow the windows network buffer
...
(oops)
2024-01-18 12:14:21 +10:00
80bea77242
clean up requirements.txt
2024-01-18 10:29:49 +10:00
22de3b0754
added async support for various services
2024-01-18 09:14:54 +10:00
2bce800767
added accurate tier output to oai keys
...
this will help differentiate fake t4/t5 keys reporting as 10k rpm but in reality have just had their rpm limit increased by asking openai
2024-01-06 12:38:20 +10:00
a9637d8811
oops
2023-12-13 10:40:44 +10:00
57184dc988
updated oai rate limits for tier 1 keys
2023-11-10 07:13:18 +10:00
d456f75374
initial commit
2023-11-10 06:41:57 +10:00
based