Wafer
Try Wafer on us. Starter credit covers your first requests, then one key reaches all 9 Wafer models, with the privacy posture shown on every route.
Waferwafer
These privacy labels describe Wafer, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | Wafer |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://wafer.ai/ |
| Models | 9 public models |
| Credits routes | 9 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | Wafer supports request-scoped ZDR via Wafer-ZDR: required on supported models; model-level support differs, so TrustedRouter keeps provider-level claims conservative. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
usage.provider_usage.gateway_region identifies the TrustedRouter gateway, not the provider's inference location. A value such as europe-west4 does not mean the model ran in Europe. usage.inference_location.serving_region remains null when the provider has not reported it. Older gateways may return the gateway-only field as provider_usage.region.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- Not verified
No inference-location declaration has been verified for this provider. - Can locations change?
- Not verified. Do not assume that the serving location is fixed.
- Provider region pinning
- Not verified.
- Pinning through TrustedRouter
- No verified provider-specific location pin documented here.
- Infrastructure declaration
- Inference location not verified; no country-specific residency commitment.
- Evidence
- Not yet reviewed.
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
258 samplesContinuously sampled across Wafer'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 | 1296 ms |
|---|---|
| Effective throughput | 255 tok/s n=3 |
| Uptime | 98.84% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| moonshotai/kimi-k3 | 1296 ms | 255 tok/s n=2 | 98.41% | — | 189 |
| deepseek/deepseek-v4.1-flash-1017 | 2006 ms | — | 100.00% | — | 47 |
| deepseek/deepseek-v4-flash-0731-fast | 534 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-v4-pro | 543 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.3 | 755 ms | 125 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v4.1-flash | 842 ms | — | 100.00% | — | 8 |
| z-ai/glm-5.3-flash | 967 ms | — | 100.00% | — | 4 |
| qwen/qwen3.8-27b | 1096 ms | — | 100.00% | — | 3 |
Wafer performance history · Full provider & model leaderboard.
Models served by Wafer.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4-flash-0423DeepSeek-V4-Flash-0423 |
— | 1,048,576 | $0.1477/1M | $0.02954/1M | $0.2954/1M |
deepseek/deepseek-v4-flash-0731-fastDeepSeek V4 Flash 0731 Fast |
— | 1,000,000 | $0.13715/1M | $0.02954/1M | $0.24265/1M |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro 0423 |
IQ 123#34 | 1,048,576 | $0.2954/1M | $0.04642/1M | $4.1778/1M |
deepseek/deepseek-v4.1-flashDeepSeek: DeepSeek V4.1 Flash |
IQ 126#24 | 1,048,576 | $0.20045/1M | $0.01/1M | $0.68575/1M |
deepseek/deepseek-v4.1-flash-1017DeepSeek: DeepSeek V4.1 Flash 1017 |
IQ 128#19 | 1,048,576 | $0.13715/1M | $0.01/1M | $0.5275/1M |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 127#22 | 1,048,576 | $2.11/1M | $0.26375/1M | $15.825/1M |
qwen/qwen3.8-27bQwen: Qwen3.8 27B |
IQ 115#57 | 65,536 | $0.0633/1M | $0.05275/1M | $2.4265/1M |
z-ai/glm-5.3Z.ai: GLM 5.3 |
IQ 124#30 | 1,048,576 | $0.3165/1M | $0.1899/1M | $3.165/1M |
z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash |
IQ 119#50 | 1,048,576 | $0.05275/1M | $0.03165/1M | $0.211/1M |
Questions
Does Wafer have zero data retention?
TrustedRouter does not currently mark Wafer 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 Wafer end-to-end encrypted?
TrustedRouter does not currently mark Wafer 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 Wafer models are available through TrustedRouter?
This page currently lists 9 public Wafer models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.