Lightning AI
Explore Lightning AI models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Lightning AIlightning
These privacy labels describe Lightning AI, 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 | Lightning AI |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://lightning.ai/ |
| Models | 5 public models |
| Credits routes | 5 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | No provider-ZDR claim is tracked here. Lightning's general privacy and security documentation is linked for retention review. 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.
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
22 samplesContinuously sampled across Lightning AI'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 | 952 ms |
|---|---|
| Effective throughput | 165 tok/s n=1 |
| Uptime | 40.91% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| lightning-ai/deepseek-v4.1-flash | 945 ms | — | 75.00% | — | 4 |
| lightning-ai/mimo-v2.6-pro | 952 ms | — | 33.33% | 1 provider_auth_config |
6 |
| lightning-ai/qwen3.8-27b | 1264 ms | — | 50.00% | — | 2 |
| lightning-ai/glm-5.3 | 2260 ms | — | 60.00% | — | 5 |
| google/gemma-4-31b-it | — | 165 tok/s n=1 | 0.00% | 1 provider_auth_config |
1 |
| lightning-ai/glm-5.3-flash | — | — | 0.00% | — | 4 |
| qwen/qwen3.8-27b | — | — | — | 1 provider_auth_config |
0 |
Lightning AI performance history · Full provider & model leaderboard.
Models served by Lightning AI.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#110 | 262,144 | $0.1477/1M | Not published | $0.422/1M |
lightning-ai/deepseek-v4.1-flashdeepseek-v4.1-flash |
IQ 126#21 | 1,048,576 | $0.3165/1M | Not published | $1.266/1M |
lightning-ai/glm-5.3glm-5.3 |
IQ 125#24 | 131,072 | $1.477/1M | Not published | $4.642/1M |
lightning-ai/mimo-v2.6-promimo-v2.6-pro |
IQ 125#27 | 262,144 | $0.4642/1M | Not published | $0.91785/1M |
qwen/qwen3.8-27bQwen: Qwen3.8 27B |
IQ 116#50 | 65,536 | $0.422/1M | Not published | $3.165/1M |
Questions
Does Lightning AI have zero data retention?
TrustedRouter does not currently mark Lightning AI 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 Lightning AI end-to-end encrypted?
TrustedRouter does not currently mark Lightning AI 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 Lightning AI models are available through TrustedRouter?
This page currently lists 5 public Lightning AI models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.