OpenAI compatible API · Attested · Public status
Lightning AI
Explore Lightning AI models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Lightning AIlightning
No provider claim
| Provider | Lightning AI |
|---|---|
| Provider website | https://lightning.ai/ |
| Models | 36 public models |
| Prepaid routes | 25 |
| BYOK routes | 36 |
| 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
39 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 | 1751 ms |
|---|---|
| Effective throughput | 58 tok/s n=5 |
| Uptime | 97.44% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| openai/gpt-3.5-turbo | 1563 ms | 1563 ms | — | 100.00% | — | 4 |
| lightning-ai/nemotron-3-nano-omni-30b-a3b-reasoning | 1567 ms | 1567 ms | — | 100.00% | — | 2 |
| openai/gpt-4 | 1588 ms | 1588 ms | — | 100.00% | — | 2 |
| openai/gpt-4o | 1689 ms | 1689 ms | — | 100.00% | — | 2 |
| lightning-ai/gpt-oss-20b | 1738 ms | 1738 ms | — | 100.00% | — | 1 |
| openai/gpt-4.1 | 1751 ms | 1751 ms | — | 100.00% | — | 3 |
| google/gemini-3-flash-preview | 2289 ms | 2289 ms | — | 100.00% | — | 1 |
| google/gemini-3.1-flash-lite-preview | 3240 ms | 3240 ms | — | 100.00% | — | 2 |
| lightning-ai/gpt-oss-120b | 3507 ms | 3506 ms | — | 100.00% | — | 3 |
| google/gemini-3.5-flash | 4220 ms | 4220 ms | 58 tok/s n=2 | 100.00% | — | 3 |
| openai/gpt-4-turbo | 5066 ms | 5066 ms | — | 100.00% | — | 1 |
| google/gemini-3.1-pro-preview | 5166 ms | 5166 ms | 40 tok/s n=1 | 100.00% | — | 1 |
| google/gemini-2.5-pro | 6756 ms | 6756 ms | — | 100.00% | — | 2 |
| google/gemini-2.5-flash | — | — | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | — | — | 117 tok/s n=2 | 100.00% | — | 9 |
| lightning-ai/deepseek-v4-pro | — | — | — | 100.00% | — | 1 |
| openai/gpt-5-nano | — | — | — | 0.00% | 1 unsupported_route |
1 |
Lightning AI performance history · Full provider & model leaderboard.
Provider models
Models served by Lightning AI.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
anthropic/claude-fable-5Anthropic: Claude Fable 5 |
IQ 137#1 | 1,000,000 | 1 | $10.55/1M | $52.75/1M | BYOK |
anthropic/claude-haiku-4-5-20251001Claude Haiku 4.5 |
— | 200,000 | 1 | $1.055/1M | $5.275/1M | BYOK |
anthropic/claude-opus-4-1-20250805Claude Opus 4.1 |
— | 200,000 | 1 | $15.825/1M | $79.125/1M | BYOK |
anthropic/claude-opus-4-5-20251101Claude Opus 4.5 |
— | 200,000 | 1 | $5.275/1M | $26.375/1M | BYOK |
anthropic/claude-opus-4-6Claude Opus 4.6 |
— | 200,000 | 1 | $5.275/1M | $26.375/1M | BYOK |
anthropic/claude-opus-4-7anthropic/claude-opus-4-7 |
— | 1,000,000 | 1 | $5.275/1M | $26.375/1M | BYOK |
anthropic/claude-opus-4-8anthropic/claude-opus-4-8 |
— | 1,000,000 | 1 | $5.275/1M | $26.375/1M | BYOK |
anthropic/claude-opus-5Claude Opus 5 |
IQ 134#3 | 1,000,000 | 1 | $5.275/1M | $26.375/1M | BYOK |
anthropic/claude-sonnet-4-5-20250929Claude Sonnet 4.5 |
— | 200,000 | 1 | $3.165/1M | $15.825/1M | BYOK |
anthropic/claude-sonnet-4-6anthropic/claude-sonnet-4-6 |
— | 1,000,000 | 1 | $3.165/1M | $15.825/1M | BYOK |
anthropic/claude-sonnet-5Anthropic: Claude Sonnet 5 |
IQ 125#12 | 1,000,000 | 1 | $2.11/1M | $15.825/1M | BYOK |
google/gemini-2.5-flashGoogle: Gemini 2.5 Flash |
— | 1,048,576 | 2 | $0.3165/1M | $2.6375/1M | prepaid BYOK |
google/gemini-2.5-flash-lite-preview-06-17Gemini 2.5 Flash Lite |
— | 1,048,576 | 2 | $0.1055/1M | $0.422/1M | prepaid BYOK |
google/gemini-2.5-proGoogle: Gemini 2.5 Pro |
IQ 103#65 | 1,048,576 | 2 | $1.31875/1M | $10.55/1M | prepaid BYOK |
google/gemini-3-flash-previewGoogle: Gemini 3 Flash Preview |
IQ 116#32 | 1,048,576 | 2 | $0.5275/1M | $3.165/1M | prepaid BYOK |
google/gemini-3.1-flash-lite-previewGoogle: Gemini 3.1 Flash Lite Preview |
IQ 101#72 | 1,048,576 | 2 | $0.26375/1M | $1.5825/1M | prepaid BYOK |
google/gemini-3.1-pro-previewGoogle: Gemini 3.1 Pro Preview |
IQ 127#10 | 1,048,576 | 2 | $2.11/1M | $12.66/1M | prepaid BYOK |
google/gemini-3.5-flashGoogle: Gemini 3.5 Flash |
IQ 124#13 | 1,048,576 | 2 | $1.5825/1M | $9.495/1M | prepaid BYOK |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#73 | 262,144 | 2 | $0.1477/1M | $0.422/1M | prepaid BYOK |
lightning-ai/deepseek-v4-prodeepseek-v4-pro |
IQ 117#31 | 1,048,576 | 2 | $0.93895/1M | $3.165/1M | prepaid BYOK |
lightning-ai/gpt-oss-120bgpt-oss-120b |
IQ 105#61 | 128,000 | 2 | $0.026375/1M | $0.1055/1M | prepaid BYOK |
lightning-ai/gpt-oss-20bgpt-oss-20b |
IQ 100#77 | 128,000 | 2 | $0.013188/1M | $0.05275/1M | prepaid BYOK |
lightning-ai/nemotron-3-nano-omni-30b-a3b-reasoningnemotron-3-nano-omni-30b-a3b-reasoning |
— | 256,000 | 2 | $0.26375/1M | $0.5275/1M | prepaid BYOK |
lightning-ai/nemotron-3-ultra-550b-a55bnemotron-3-ultra-550b-a55b |
— | 262,144 | 2 | $0.43255/1M | $1.266/1M | prepaid BYOK |
openai/gpt-3.5-turboOpenAI: GPT-3.5 Turbo |
— | 16,385 | 2 | $0.5275/1M | $1.5825/1M | prepaid BYOK |
openai/gpt-4OpenAI: GPT-4 |
— | 8,191 | 2 | $31.65/1M | $63.3/1M | prepaid BYOK |
openai/gpt-4-turboOpenAI: GPT-4 Turbo |
IQ # | 128,000 | 2 | $10.55/1M | $31.65/1M | prepaid BYOK |
openai/gpt-4.1OpenAI: GPT-4.1 |
— | 1,047,576 | 2 | $2.11/1M | $8.44/1M | prepaid BYOK |
openai/gpt-4oOpenAI: GPT-4o |
IQ # | 128,000 | 2 | $2.6375/1M | $10.55/1M | prepaid BYOK |
openai/gpt-5-nanoOpenAI: GPT-5 Nano |
IQ 96#90 | 400,000 | 2 | $0.05275/1M | $0.422/1M | prepaid BYOK |
openai/gpt-5.2-2025-12-11GPT 5.2 |
— | 400,000 | 2 | $1.84625/1M | $14.77/1M | prepaid BYOK |
openai/gpt-5.4-2026-03-05GPT 5.4 |
— | 1,050,000 | 2 | $2.6375/1M | $15.825/1M | prepaid BYOK |
openai/gpt-5.4-mini-2026-03-17GPT 5.4 mini |
— | 400,000 | 2 | $0.79125/1M | $4.7475/1M | prepaid BYOK |
openai/gpt-5.4-nano-2026-03-17GPT 5.4 nano |
— | 400,000 | 2 | $0.211/1M | $1.31875/1M | prepaid BYOK |
openai/gpt-5.5-2026-04-23GPT 5.5 |
— | 1,050,000 | 2 | $5.275/1M | $31.65/1M | prepaid BYOK |
openai/gpt-5.6-terraOpenAI: GPT-5.6 Terra |
IQ 132#5 | 1,050,000 | 2 | $2.11/1M | $12.66/1M | prepaid BYOK |
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 36 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.