sora ba2b5c1772 fix: terminal_bench_v2_1 result collection, apt mirror, and restore run.py env var

2026-08-05 03:56:44 +00:00

..

api_test_config.env.example

feat: add benchmark cost calculator and generic API test runner

2026-07-31 02:44:14 +00:00

api_test_runner.sh

feat: add benchmark cost calculator and generic API test runner

2026-07-31 02:44:14 +00:00

calc_glm52_cost.sh

feat: add benchmark cost calculator and generic API test runner

2026-07-31 02:44:14 +00:00

DP4-flash-int8-no-thinking-full.sh

Add sandbox images download from ModelScope; fix Excel sample count total

2026-07-27 05:34:16 +00:00

DP4-flash-int8-thinking-official.sh

chore: update evalscope runner, thinking config and webui

2026-07-31 02:36:51 +00:00

GLM52_API_TEST1.sh

feat: support --thinking-budget-tokens to control reasoning budget via API

2026-07-31 06:03:06 +00:00

k3_report_test.py

fix: set LITELLM_LOCAL_MODEL_COST_MAP=True to avoid GitHub fetch timeout

2026-08-03 07:14:05 +00:00

model_pricing.yaml

feat: add multi-model pricing, cost prediction and budget filter

2026-07-31 03:04:28 +00:00

README_API_TEST.md

feat: support --thinking-budget-tokens to control reasoning budget via API

2026-07-31 06:03:06 +00:00