Impulse
Search…
⌘
K
Models
Providers
Capabilities
Pricing
Compare
API
Playground
Providers
/
WandB Inference
Visit website
W
WandB Inference
Cloud platform
·
docs.litellm.ai
WandB Inference models via API.
Models
16
Endpoints
3
Regions
0
Avg input
$
38562.59
Auth
API key
SDKs
0
Endpoints
POST
/v1/chat/completions
Completions
Stream
POST
/v1/messages
Messages
Stream
POST
/v1/responses
Responses
Stream
Models · 16
Model
Context
Input
Output
Capabilities
MiniMax-M2.5
Open
197K
$
0.30
$
1.20
Reasoning
Tools
JSON
Kimi-K2.5
Open
262K
$
0.60
$
3.00
Reasoning
Vision
Tools
gpt-oss-120b
Open
131K
$
15000.00
$
60000.00
gpt-oss-20b
Open
131K
$
5000.00
$
20000.00
GLM-4.5
Open
131K
$
55000.00
$
200000.00
Qwen3-235B-A22B-Thinking-2507
Open
262K
$
10000.00
$
10000.00
DeepSeek-R1-0528
Open
161K
$
135000.00
$
540000.00
Llama-4-Scout-17B-16E-Instruct
Open
64K
$
17000.00
$
66000.00
Llama-3.3-70B-Instruct
Open
128K
$
71000.00
$
71000.00
Llama-3.1-8B-Instruct
Open
128K
$
22000.00
$
22000.00
DeepSeek-V3-0324
Open
161K
$
114000.00
$
275000.00
DeepSeek-V3.1
Open
128K
$
55000.00
$
165000.00
Kimi-K2-Instruct
Open
128K
$
0.60
$
2.50
Phi-4-mini-instruct
Open
128K
$
8000.00
$
35000.00
Qwen3-235B-A22B-Instruct-2507
Open
262K
$
10000.00
$
10000.00
Qwen3-Coder-480B-A35B-Instruct
Open
262K
$
100000.00
$
150000.00
Release timeline
Jul 2025
Qwen3-235B-A22B-Thinking-2507
Aug 2025
gpt-oss-120b
Aug 2025
gpt-oss-20b
Jan 2026
Kimi-K2.5
Feb 2026
MiniMax-M2.5
Details
Category
Cloud platform
Website
docs.litellm.ai
Auth
API key
Regions
-