scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 109

feat(featherless): add support for WeiboAI VibeThinker models

Browse source 
Add VibeThinker-1.5B and VibeThinker-3B models via Featherless AI provider.

Models:
- featherless_ai/WeiboAI/VibeThinker-1.5B (1.5B params, Qwen2.5-Math-1.5B base)
- featherless_ai/WeiboAI/VibeThinker-3B (3B params, Qwen2.5-Coder-3B base)

Both models:
- 32K context window
- 8K max output tokens
- Reasoning-optimized (math, code, GPQA)
- MIT licensed

Closes #30754
This commit is contained in:
FadelT 2026-06-18 16:52:00 +02:00
parent c0a146929c
commit 303eb586b0
1 changed files with 14 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
model_prices_and_context_window.json
View file

@ -14720,6 +14720,20 @@
"max_tokens": 4096,
"mode": "chat"
},
"featherless_ai/WeiboAI/VibeThinker-1.5B": {
"litellm_provider": "featherless_ai",
"max_input_tokens": 32768,
"max_output_tokens": 8192,
"max_tokens": 32768,
"mode": "chat"
},
"featherless_ai/WeiboAI/VibeThinker-3B": {
"litellm_provider": "featherless_ai",
"max_input_tokens": 32768,
"max_output_tokens": 8192,
"max_tokens": 32768,
"mode": "chat"
},
"fireworks-ai-4.1b-to-16b": {
"input_cost_per_token": 2e-07,
"litellm_provider": "fireworks_ai",