Weights & Biases
Explore Weights & Biases models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Weights & Biaseswandb
No provider claim
| Provider | Weights & Biases |
|---|---|
| Routing status | Active |
| Provider website | https://wandb.ai/site/inference/ |
| Models | 28 public models |
| Prepaid routes | 28 |
| BYOK routes | 0 |
| Zero data retention | no |
| Confidential compute | no |
| Provider E2EE | no |
| Policy note | W&B Serverless Inference runs on CoreWeave infrastructure. W&B does not publish a zero-retention, confidential-compute, or end-to-end-encryption commitment for this service, so these routes use the Standard privacy tier. TrustedRouter does not enable W&B Weave tracing for provider calls. Policy source |
Measured performance
7 samplesContinuously sampled across Weights & Biases's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1531 ms |
|---|---|
| Effective throughput | 94 tok/s n=1 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| moonshotai/kimi-k2.7-code | 1120 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro | 1531 ms | — | 100.00% | — | 3 |
| meta-llama/llama-3.1-70b-instruct | 2858 ms | — | 100.00% | — | 1 |
| jetbrains/mellum2-12b-a2.5b-instruct | 3065 ms | — | 100.00% | — | 1 |
| nvidia/nemotron-3-super-120b-a12b-fp8 | 3508 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | — | 94 tok/s n=1 | — | — | 0 |
Weights & Biases performance history · Full provider & model leaderboard.
Models served by Weights & Biases.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
deepseek/deepseek-v3.1DeepSeek V3.1 |
IQ 96#92 | 131,072 | 1 | $0.58025/1M | $1.74075/1M | prepaid |
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash 0423 |
IQ 113#42 | 1,048,576 | 1 | $0.1477/1M | $0.2954/1M | prepaid |
deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,310,720 | 1 | $0.13715/1M | $0.2954/1M | prepaid |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro 0423 |
IQ 117#32 | 1,048,576 | 1 | $1.21325/1M | $2.69025/1M | prepaid |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#75 | 262,144 | 1 | $0.1055/1M | $0.3587/1M | prepaid |
ibm-granite/granite-4.1-8bgranite-4.1-8b |
— | 32,768 | 1 | $0.05275/1M | $0.1055/1M | prepaid |
jetbrains/mellum2-12b-a2.5b-instructJetBrains Mellum2 12B A2.5B |
— | 131,072 | 1 | $0.05275/1M | $0.1055/1M | prepaid |
meta-llama/llama-3.1-70b-instructMeta: Llama 3.1 70B Instruct |
— | 131,072 | 1 | $0.844/1M | $0.844/1M | prepaid |
meta-llama/llama-3.1-8b-instructMeta: Llama 3.1 8B Instruct |
— | 131,072 | 1 | $0.2321/1M | $0.2321/1M | prepaid |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | 1 | $0.74905/1M | $0.74905/1M | prepaid |
minimax/minimax-m2.5MiniMax: MiniMax M2.5 |
IQ 105#65 | 204,800 | 1 | $0.3165/1M | $1.266/1M | prepaid |
minimax/minimax-m3MiniMax: MiniMax M3 |
IQ 114#40 | 1,048,576 | 1 | $0.24265/1M | $1.0128/1M | prepaid |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 119#24 | 262,144 | 1 | $0.68575/1M | $3.59755/1M | prepaid |
moonshotai/kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code |
IQ 118#29 | 262,144 | 1 | $0.74905/1M | $3.6925/1M | prepaid |
nvidia/nemotron-3-super-120b-a12b-fp8NVIDIA Nemotron 3 Super 120B |
— | 262,144 | 1 | $0.211/1M | $0.844/1M | prepaid |
nvidia/nemotron-3-ultra-550b-a55bNVIDIA: Nemotron 3 Ultra |
— | 512,288 | 1 | $0.79125/1M | $2.90125/1M | prepaid |
nvidia/nemotron-3.5-lightning-30b-a3bnvidia/Nemotron-3.5-Lightning-30B-A3B |
— | 262,144 | 1 | $0.1055/1M | $0.26375/1M | prepaid |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#63 | 131,072 | 1 | $0.03165/1M | $0.17935/1M | prepaid |
openai/gpt-oss-20bOpenAI: gpt-oss-20b |
IQ 100#79 | 131,072 | 1 | $0.03165/1M | $0.13715/1M | prepaid |
openpipe/qwen3-14b-instructOpenPipe Qwen3 14B Instruct |
— | 32,768 | 1 | $0.05275/1M | $0.2321/1M | prepaid |
qwen/qwen3-30b-a3b-instruct-2507Qwen: Qwen3 30B A3B Instruct 2507 |
— | 262,144 | 1 | $0.1055/1M | $0.3165/1M | prepaid |
qwen/qwen3-coder-480b-a35b-instructQwen3 Coder 480B A35B Instruct |
— | 262,144 | 1 | $1.055/1M | $1.5825/1M | prepaid |
qwen/qwen3.5-35b-a3bQwen: Qwen3.5-35B-A3B |
— | 262,144 | 1 | $0.26375/1M | $1.31875/1M | prepaid |
qwen/qwen3.6-27bQwen: Qwen3.6 27B |
IQ 111#49 | 262,144 | 1 | $0.633/1M | $3.798/1M | prepaid |
qwen/qwen3.6-35b-a3bQwen: Qwen3.6 35B A3B |
IQ 100#80 | 262,144 | 1 | $0.26375/1M | $1.31875/1M | prepaid |
qwen/qwen3.8-27bQwen: Qwen3.8 27B |
IQ 112#46 | 1,000,000 | 1 | $0.422/1M | $3.165/1M | prepaid |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 114#39 | 204,800 | 1 | $1.477/1M | $4.642/1M | prepaid |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#20 | 1,048,576 | 1 | $0.8018/1M | $2.5531/1M | prepaid |
Questions
Does Weights & Biases have zero data retention?
TrustedRouter does not currently mark Weights & Biases as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Weights & Biases end-to-end encrypted?
TrustedRouter does not currently mark Weights & Biases as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Weights & Biases models are available through TrustedRouter?
This page currently lists 28 public Weights & Biases models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.