Provider · 2026-07-09
wandb
| Model | Input / 1M | Output / 1M | Context | Providers | Tags |
|---|---|---|---|---|---|
| Granite 4.1 8B | $0.050 | $0.100 | 131K | 1 | tools · json · open-weights |
| Mellum2 12B A2.5B | $0.050 | $0.100 | 131K | 1 | tools · json · open-weights |
| Qwen3 14B Instructderivative | $0.050 | $0.220 | 33K | 1 | tools · json · open-weights |
Frequently asked questions
How many AI models does wandb offer?
We track 2 canonical wandb models plus 1 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.
Which wandb model is the cheapest?
Granite 4.1 8B is currently the lowest-priced wandb model, at $0.050 per 1M input tokens and $0.100 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.
Which wandb model has the largest context window?
Granite 4.1 8B leads at 131K tokens. This is the total of prompt + completion.
Which wandb models support tool calling?
Multiple wandb models support tool calling, with Granite 4.1 8B being a popular pick. The capability column in the table above marks every model with wandb tool-calling support.
What are the best alternatives to wandb?
Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.
How fresh is this wandb pricing data?
Daily. Our pipeline syncs every morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.
Explore more
Top wandb models
- Granite 4.1 8B$0.05 in / $0.10 out
- Mellum2 12B A2.5B$0.05 in / $0.10 out
Browse by use case
Browse by capability
Last updated:
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.