Propose an edit — Weights & Biases Inference
Anything look wrong? Fix it. Proposals are queued for an editor — approved corrections are applied to the entry and recorded in the public journal.
edit_proposal — wandb
// sign in to propose edits
Edits are tied to accounts so reviewers can weigh evidence and reward useful contributions. Proposals are queued — an editor reviews every change before it is applied.
- name
- Weights & Biases Inference
- domain
- wandb.ai
- category
- Paid API
- free tier
- yes
- free credits
- — not quantified — Weights & Biases states only that Inference includes 'Free credits for a limited time' on the Free plan and a $5/mo credit on Pro, with no dollar amount or expiry published for the free grant (checked 2026-09-16).
- description
- Weights & Biases Serverless Inference gives API and playground access to open-source LLMs hosted on CoreWeave, using an existing W&B account and no separate provider keys, with support for bringing your own LoRA weights for fine-tuned models. Token rates are listed per 1M tokens on the W&B pricing page: Meta Llama 3.1 8B at $0.22 input / $0.22 output, Meta Llama 3.3 70B at $0.71 / $0.71, OpenAI GPT OSS 120B at $0.03 / $0.17, NVIDIA Nemotron 3.5 Lightning at $0.07 / $0.20 with a $0.04 cache-hit rate, and DeepSeek V4-Pro at $1.15 / $2.55 with a $0.20 cache-hit rate. Inference spend is separate from platform subscriptions and can be capped with a monthly W&B Inference budget.
how this works
- 01. Only the fields below can be changed — pricing tables, models and risk reviews stay with editors.
- 02. Changes to data fields (description, category, free tier, credit values) require a rationale or source link.
- 03. Max 3 open proposals per account. Approved edits are published and logged in the public journal.
- 04. Current category: Paid API — the entry currently reports a free tier.