Gateway
Weights & Biases
Weights & Biases is a Gateway provider with 8 models across 8 offerings.
Access
- API base URL
- https://api.inference.wandb.ai/v1
- SDK
- @ai-sdk/openai-compatible
- Environment variables
- WANDB_API_KEY
Protocols
Openai chat
Organizations
| Organization | Families | Models |
|---|---|---|
| 1 | 1 | |
| Ibm Granite | 1 | 1 |
| Moonshot AI | 1 | 4 |
| OpenAI | 1 | 2 |
Models
8 of 8 model versions
| Model | Organization | Family | Provider model ID | Context | Max output | Input | Output | Reasoning | Tool call | Structured | Temperature | Weights | Pricing | Released | Updated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Kimi K3 moonshotai/kimi/k3 | Moonshot AI | Kimi | moonshotai/Kimi-K3 Openai chat · Streaming | 1M | 131K | TextImageVideo | Text | Yes | Yes | Yes | -No | Open weight | input $3/M · cache read $0.3/M output $15/M | 2026-07-16 | 2026-07-30 | |
| Kimi K2.7 Code moonshotai/kimi/k2-7-code | Moonshot AI | Kimi | moonshotai/Kimi-K2.7-Code Openai chat · Streaming | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | -No | Open weight | input $0.71/M · cache read $0.15/M output $3.5/M | 2026-06-12 | 2026-07-22 | |
| Granite 4.1 8B ibm-granite/granite/4-1-8b | Ibm Granite | Granite | ibm-granite/granite-4.1-8b Openai chat · Streaming | 131K | 131K | Text | Text | -No | Yes | Yes | Yes | Open weight | input $0.05/M · cache read $0.05/M output $0.1/M | 2026-04-30 | 2026-04-30 | |
| Kimi K2.6 moonshotai/kimi/k2-6 | Moonshot AI | Kimi | moonshotai/Kimi-K2.6 Openai chat · Streaming | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | Yes | Open weight | input $0.65/M · cache read $0.15/M output $3.41/M | 2026-04-21 | 2026-07-22 | |
| Gemma 4 31B IT google/gemma/4-31b-it | Gemma | google/gemma-4-31B-it Openai chat · Streaming | 262K | 33K | TextImage | Text | Yes | Yes | Yes | Yes | Open weight | input $0.1/M · cache read $0.1/M output $0.34/M | 2026-04-02 | 2026-04-30 | ||
| Kimi K2.5 moonshotai/kimi/k2-5 | Moonshot AI | Kimi | moonshotai/Kimi-K2.5 Openai chat · Streaming | 262K | 262K | TextImageVideo | Text | Yes | Yes | Yes | -No | Open weight | input $0.6/M · cache read $0.1/M output $3/M | 2026-01 | 2026-07-22 | |
| GPT OSS 120B openai/gpt/oss-120b | OpenAI | GPT | openai/gpt-oss-120b Openai chat · Streaming | 131K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.03/M · cache read $0.03/M output $0.17/M | 2025-08-05 | 2026-07-22 | |
| GPT OSS 20B openai/gpt/oss-20b | OpenAI | GPT | openai/gpt-oss-20b Openai chat · Streaming | 131K | 33K | Text | Text | Yes | Yes | Yes | Yes | Open weight | input $0.03/M · cache read $0.03/M output $0.13/M | 2025-08-05 | 2026-03-01 |