Lightning AI
Explore Lightning AI models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Lightning AIlightning
No provider claim
| Provider | Lightning AI |
|---|---|
| Routing status | Active |
| Provider website | https://lightning.ai/ |
| Models | 25 public models |
| Credits routes | 25 |
| Zero data retention | not claimed |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | No provider-ZDR claim is tracked here. Lightning's general privacy and security documentation is linked for retention review. Policy source |
Measured performance
40 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 | 1452 ms |
|---|---|
| Effective throughput | 49 tok/s n=4 |
| Uptime | 70.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| lightning-ai/deepseek-v4-pro | 903 ms | — | 100.00% | — | 2 |
| lightning-ai/gpt-oss-120b | 915 ms | — | 15.38% | — | 13 |
| google/gemma-4-31b-it | 1087 ms | 175 tok/s n=1 | 50.00% | — | 2 |
| lightning-ai/nemotron-3-ultra-550b-a55b | 1350 ms | — | 100.00% | — | 2 |
| openai/gpt-3.5-turbo | 1452 ms | — | 100.00% | — | 1 |
| lightning-ai/qwen3.8-27b | 1626 ms | — | 100.00% | — | 3 |
| openai/gpt-4 | 1813 ms | — | 100.00% | — | 2 |
| lightning-ai/gpt-oss-20b | 2029 ms | — | 100.00% | — | 3 |
| openai/gpt-4.1 | 2067 ms | — | 100.00% | — | 3 |
| openai/gpt-4o | 2122 ms | — | 100.00% | — | 3 |
| google/gemini-2.5-flash-lite-preview-06-17 | 2170 ms | — | 100.00% | — | 1 |
| openai/gpt-4-turbo | 2438 ms | — | 100.00% | — | 2 |
| google/gemini-3.5-flash | 3024 ms | 55 tok/s n=1 | 100.00% | — | 1 |
| google/gemini-2.5-pro | 3417 ms | — | 100.00% | — | 2 |
| google/gemini-3.1-pro-preview | — | 44 tok/s n=2 | — | — | 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/gemini-2.5-flashGoogle: Gemini 2.5 Flash |
— | 1,048,576 | $0.3165/1M | Not published | $2.6375/1M |
google/gemini-2.5-flash-lite-preview-06-17Gemini 2.5 Flash Lite |
— | 1,048,576 | $0.1055/1M | Not published | $0.422/1M |
google/gemini-2.5-proGoogle: Gemini 2.5 Pro |
IQ 100#85 | 1,048,576 | $1.31875/1M | Not published | $10.55/1M |
google/gemini-3-flash-previewGoogle: Gemini 3 Flash Preview |
IQ 116#37 | 1,048,576 | $0.5275/1M | Not published | $3.165/1M |
google/gemini-3.1-flash-lite-previewGoogle: Gemini 3.1 Flash Lite Preview |
IQ 101#79 | 1,048,576 | $0.26375/1M | Not published | $1.5825/1M |
google/gemini-3.1-pro-previewGoogle: Gemini 3.1 Pro Preview |
IQ 127#11 | 1,048,576 | $2.11/1M | Not published | $12.66/1M |
google/gemini-3.5-flashGoogle: Gemini 3.5 Flash |
IQ 124#16 | 1,048,576 | $1.5825/1M | Not published | $9.495/1M |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#80 | 262,144 | $0.1477/1M | Not published | $0.422/1M |
lightning-ai/deepseek-v4-prodeepseek-v4-pro |
IQ 117#36 | 1,048,576 | $0.93895/1M | Not published | $3.165/1M |
lightning-ai/gpt-oss-120bgpt-oss-120b |
IQ 105#69 | 128,000 | $0.026375/1M | Not published | $0.1055/1M |
lightning-ai/gpt-oss-20bgpt-oss-20b |
IQ 100#86 | 128,000 | $0.013188/1M | Not published | $0.05275/1M |
lightning-ai/nemotron-3-ultra-550b-a55bnemotron-3-ultra-550b-a55b |
— | 262,144 | $0.43255/1M | Not published | $1.266/1M |
lightning-ai/qwen3.8-27bQwen3.8-27B |
IQ 112#52 | 262,144 | $0.422/1M | Not published | $3.165/1M |
openai/gpt-3.5-turboOpenAI: GPT-3.5 Turbo |
— | 16,385 | $0.5275/1M | Not published | $1.5825/1M |
openai/gpt-4OpenAI: GPT-4 |
— | 8,191 | $31.65/1M | Not published | $63.3/1M |
openai/gpt-4-turboOpenAI: GPT-4 Turbo |
IQ 78#131 | 128,000 | $10.55/1M | Not published | $31.65/1M |
openai/gpt-4.1OpenAI: GPT-4.1 |
— | 1,047,576 | $2.11/1M | Not published | $8.44/1M |
openai/gpt-4oOpenAI: GPT-4o |
IQ 81#127 | 128,000 | $2.6375/1M | Not published | $10.55/1M |
openai/gpt-5-nanoOpenAI: GPT-5 Nano |
IQ 96#99 | 400,000 | $0.05275/1M | Not published | $0.422/1M |
openai/gpt-5.2-2025-12-11GPT 5.2 |
— | 400,000 | $1.84625/1M | Not published | $14.77/1M |
openai/gpt-5.4-2026-03-05GPT 5.4 |
— | 1,050,000 | $2.6375/1M | Not published | $15.825/1M |
openai/gpt-5.4-mini-2026-03-17GPT 5.4 mini |
— | 400,000 | $0.79125/1M | Not published | $4.7475/1M |
openai/gpt-5.4-nano-2026-03-17GPT 5.4 nano |
— | 400,000 | $0.211/1M | Not published | $1.31875/1M |
openai/gpt-5.5-2026-04-23GPT 5.5 |
— | 1,050,000 | $5.275/1M | Not published | $31.65/1M |
openai/gpt-5.6-terraOpenAI: GPT-5.6 Terra |
IQ 132#7 | 1,050,000 | $2.11/1M | Not published | $12.66/1M |
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 25 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.