Contact
LOG IN
Sign up

W&B Inference Pricing

The best tools for AI developers

W&B hosted models

Prices shown are per 1 million tokens.

Model

Input Tokens

Output Tokens

OpenAI GPT OSS 120B
$0.15
$0.60
OpenAI GPT OSS 20B
$0.05
$0.20
Qwen3 235B A22B Thinking-2507
$0.10
$0.10
Qwen3 Coder 480B A35B
$1.00
$1.50
Qwen3 235B A22B-2507
$0.10
$0.10
MoonshotAI Kimi K2
$1.35
$4.00
DeepSeek R1-0528
$1.35
$5.40
DeepSeek V3-0324
$1.14
$2.75
Meta Llama 3.1 8B
$0.22
$0.22
Meta Llama 3.3 70B
$0.71
$0.71
Meta Llama 4 Scout 17Bx16E
$0.17
$0.66
Microsoft Phi 4 Mini 3.8B
$0.08
$0.35

Frequently asked questions

Will I be charged for API usage in the Playground?

Yes, we treat Playground usage the same as regular API usage. You will be billed at the per-token input and output prices outlined above.

How will I know how many tokens I've used each month?

A token is a mathematical representation of natural language. Log in to your account to view your billing dashboard⁠. This dashboard will show you how many tokens you’ve used during the current and past months.

Is access to the Inference API included in Weights & Biases Enterprise or Pro licenses?

Weights & Biases Inference APIs are billed separately from Weights & Biases Enterprise, and Pro licenses. Weights & Biases subscription pricing can be found on our pricing page.