OpenAI compatible API · Attested · Public status
OpenAI
Explore OpenAI 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.
OpenAIopenai
No logs (prepaid)
| Provider | OpenAI |
|---|---|
| Provider website | https://openai.com/ |
| Models | 44 public models |
| Prepaid routes | 32 |
| BYOK routes | 42 |
| Zero data retention | prepaid only |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | Contracted Zero Data Retention is active for TrustedRouter's managed OpenAI account, effective July 28, 2026, and live enforcement was verified on July 29, 2026. This guarantee applies only to TrustedRouter-funded prepaid routes; customer BYOK credentials use the data controls on the customer's own OpenAI organization or project. Policy source |
Measured performance
69 samplesContinuously sampled across OpenAI'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 | 2147 ms |
|---|---|
| Effective throughput | — |
| Uptime | 97.10% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| openai/gpt-5.4-mini | 1752 ms | 493 ms | — | 100.00% | 7 provider_error |
14 |
| openai/gpt-4o-2024-05-13 | 713 ms | 713 ms | — | 100.00% | — | 1 |
| openai/gpt-4.1-nano | 949 ms | 948 ms | — | 100.00% | — | 3 |
| openai/o3-mini | 1312 ms | 1312 ms | — | 100.00% | — | 2 |
| openai/gpt-5.6-sol | 1343 ms | 1343 ms | — | 100.00% | — | 1 |
| openai/o4-mini | 1422 ms | 1422 ms | — | 100.00% | — | 2 |
| openai/gpt-5.6-terra | 1429 ms | 1429 ms | — | 100.00% | — | 2 |
| openai/gpt-4-0613 | 1786 ms | 1786 ms | — | 100.00% | — | 1 |
| openai/o3 | 1805 ms | 1805 ms | — | 100.00% | 1 provider_error |
1 |
| openai/gpt-4 | 1832 ms | 1831 ms | — | 100.00% | — | 1 |
| openai/gpt-5.5 | 2147 ms | 2147 ms | — | 100.00% | — | 1 |
| openai/o1 | 2424 ms | 2423 ms | — | 100.00% | — | 3 |
| openai/gpt-5-nano | 2555 ms | 2555 ms | — | 100.00% | — | 6 |
| openai/gpt-5.1 | 2577 ms | 2576 ms | — | 100.00% | — | 1 |
| openai/gpt-5-mini | 3152 ms | 3152 ms | — | 100.00% | — | 2 |
| openai/gpt-3.5-turbo-1106 | 3248 ms | 3248 ms | — | 100.00% | — | 2 |
| openai/gpt-4-turbo | 3463 ms | 3463 ms | — | 100.00% | — | 3 |
| openai/gpt-4.1-mini | 3666 ms | 3666 ms | — | 100.00% | — | 6 |
| openai/gpt-5.2 | 4161 ms | 4160 ms | — | 100.00% | — | 1 |
| openai/gpt-5 | 4485 ms | 4485 ms | — | 100.00% | 2 provider_error |
1 |
| openai/text-embedding-3-large | — | — | — | 100.00% | — | 8 |
| openai/gpt-3.5-turbo | 2238 ms | 2238 ms | — | 80.00% | — | 5 |
| openai/gpt-4.1 | 925 ms | 925 ms | — | 50.00% | — | 2 |
OpenAI performance history · Full provider & model leaderboard.
Provider models
Models served by OpenAI.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
openai/chat-latestchat-latest |
— | 0 | 2 | $5.275/1M | $31.65/1M | prepaid BYOK |
openai/gpt-3.5-turboOpenAI: GPT-3.5 Turbo |
— | 16,385 | 2 | $0.5275/1M | $1.5825/1M | prepaid BYOK |
openai/gpt-3.5-turbo-0125gpt-3.5-turbo-0125 |
— | 0 | 2 | $0.5275/1M | $1.5825/1M | prepaid BYOK |
openai/gpt-3.5-turbo-1106gpt-3.5-turbo-1106 |
— | 0 | 2 | $1.055/1M | $2.11/1M | prepaid BYOK |
openai/gpt-3.5-turbo-instructOpenAI: GPT-3.5 Turbo Instruct |
— | 4,095 | 1 | $1.5825/1M | $2.11/1M | BYOK |
openai/gpt-4OpenAI: GPT-4 |
— | 8,191 | 2 | $31.65/1M | $63.3/1M | prepaid BYOK |
openai/gpt-4-0613gpt-4-0613 |
— | 0 | 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-4.1-miniOpenAI: GPT-4.1 Mini |
— | 1,047,576 | 2 | $0.422/1M | $1.688/1M | prepaid BYOK |
openai/gpt-4.1-nanoOpenAI: GPT-4.1 Nano |
— | 1,047,576 | 2 | $0.1055/1M | $0.422/1M | prepaid BYOK |
openai/gpt-4oOpenAI: GPT-4o |
IQ # | 128,000 | 2 | $2.6375/1M | $10.55/1M | prepaid BYOK |
openai/gpt-4o-2024-05-13OpenAI: GPT-4o (2024-05-13) |
— | 128,000 | 2 | $5.275/1M | $15.825/1M | prepaid BYOK |
openai/gpt-4o-miniOpenAI: GPT-4o-mini |
— | 128,000 | 2 | $0.15825/1M | $0.633/1M | prepaid BYOK |
openai/gpt-5OpenAI: GPT-5 |
IQ 111#44 | 400,000 | 2 | $1.31875/1M | $10.55/1M | prepaid BYOK |
openai/gpt-5-miniOpenAI: GPT-5 Mini |
— | 400,000 | 2 | $0.26375/1M | $2.11/1M | 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-proOpenAI: GPT-5 Pro |
— | 400,000 | 1 | $15.825/1M | $126.6/1M | BYOK |
openai/gpt-5.1OpenAI: GPT-5.1 |
IQ 111#45 | 400,000 | 2 | $1.31875/1M | $10.55/1M | prepaid BYOK |
openai/gpt-5.2OpenAI: GPT-5.2 |
IQ 119#21 | 400,000 | 2 | $1.84625/1M | $14.77/1M | prepaid BYOK |
openai/gpt-5.2-proOpenAI: GPT-5.2 Pro |
— | 400,000 | 1 | $22.155/1M | $177.24/1M | BYOK |
openai/gpt-5.3-codexOpenAI: GPT-5.3-Codex |
IQ 119#22 | 400,000 | 1 | $1.84625/1M | $14.77/1M | BYOK |
openai/gpt-5.4OpenAI: GPT-5.4 |
IQ 128#8 | 1,050,000 | 1 | $2.6375/1M | $15.825/1M | BYOK |
openai/gpt-5.4-miniOpenAI: GPT-5.4 Mini |
IQ 112#43 | 400,000 | 2 | $0.79125/1M | $4.7475/1M | prepaid BYOK |
openai/gpt-5.4-nanoOpenAI: GPT-5.4 Nano |
IQ 106#57 | 400,000 | 1 | $0.211/1M | $1.31875/1M | BYOK |
openai/gpt-5.4-proOpenAI: GPT-5.4 Pro |
— | 1,050,000 | 1 | $31.65/1M | $189.9/1M | BYOK |
openai/gpt-5.5OpenAI: GPT-5.5 |
IQ 133#4 | 1,050,000 | 2 | $5.275/1M | $31.65/1M | prepaid BYOK |
openai/gpt-5.5-proOpenAI: GPT-5.5 Pro |
— | 1,050,000 | 1 | $31.65/1M | $189.9/1M | BYOK |
openai/gpt-5.6-lunaOpenAI: GPT-5.6 Luna |
IQ 129#7 | 1,050,000 | 2 | $0.211/1M | $1.266/1M | prepaid BYOK |
openai/gpt-5.6-solOpenAI: GPT-5.6 Sol |
IQ 136#2 | 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 |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#61 | 131,072 | 1 | $0.039035/1M | $0.17935/1M | BYOK |
openai/gpt-oss-20bOpenAI: gpt-oss-20b |
IQ 100#77 | 131,072 | 1 | $0.03165/1M | $0.1477/1M | BYOK |
openai/o1OpenAI: o1 |
IQ # | 200,000 | 2 | $15.825/1M | $63.3/1M | prepaid BYOK |
openai/o1-proOpenAI: o1-pro |
— | 200,000 | 1 | $158.25/1M | $633/1M | BYOK |
openai/o3OpenAI: o3 |
IQ 103#69 | 200,000 | 2 | $2.11/1M | $8.44/1M | prepaid BYOK |
openai/o3-miniOpenAI: o3 Mini |
— | 200,000 | 2 | $1.1605/1M | $4.642/1M | prepaid BYOK |
openai/o3-proOpenAI: o3 Pro |
— | 200,000 | 1 | $21.1/1M | $84.4/1M | BYOK |
openai/o4-miniOpenAI: o4 Mini |
— | 200,000 | 2 | $1.1605/1M | $4.642/1M | prepaid BYOK |
openai/sora-2OpenAI Sora 2 |
— | 2,500 | 1 | selected route | selected route | prepaid |
openai/sora-2-proOpenAI Sora 2 Pro |
— | 2,500 | 1 | selected route | selected route | prepaid |
openai/text-embedding-3-largeOpenAI Text Embedding 3 Large |
— | 8,191 | 2 | $0.13715/1M | selected route | prepaid BYOK |
openai/text-embedding-3-smallOpenAI Text Embedding 3 Small |
— | 8,191 | 2 | $0.0211/1M | selected route | prepaid BYOK |
openai/text-embedding-ada-002OpenAI Text Embedding Ada 002 |
— | 8,191 | 2 | $0.1055/1M | selected route | prepaid BYOK |
Questions
Does OpenAI have zero data retention?
TrustedRouter records managed prepaid OpenAI routes as zero data retention. That classification does not automatically cover every direct or BYOK account. Use provider.min_privacy=zdr to require an eligible route.
Is OpenAI end-to-end encrypted?
TrustedRouter does not currently mark OpenAI 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 OpenAI models are available through TrustedRouter?
This page currently lists 44 public OpenAI models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.