OpenAI
Explore OpenAI models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
OpenAIopenai
ZDR
| Provider | OpenAI |
|---|---|
| Routing status | Active |
| Provider website | https://openai.com/ |
| Models | 33 public models |
| Credits routes | 33 |
| Zero data retention | yes TR-funded routes |
| 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 routes; customer BYOK credentials use the data controls on the customer's own OpenAI organization or project. Policy source |
Measured performance
79 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 | 2080 ms |
|---|---|
| Effective throughput | — |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| openai/gpt-5.6-luna | 2098 ms | — | 100.00% | — | 33 |
| openai/gpt-4.1 | 762 ms | — | 100.00% | — | 2 |
| openai/gpt-5.4-mini | 849 ms | — | 100.00% | — | 2 |
| openai/gpt-4.1-mini | 983 ms | — | 100.00% | — | 3 |
| openai/gpt-5.1 | 1056 ms | — | 100.00% | — | 2 |
| openai/gpt-5.6-sol | 1074 ms | — | 100.00% | — | 2 |
| openai/gpt-4-0613 | 1102 ms | — | 100.00% | — | 2 |
| openai/gpt-4o | 1271 ms | — | 100.00% | — | 1 |
| openai/gpt-5 | 1667 ms | — | 100.00% | — | 1 |
| openai/gpt-4-turbo | 1687 ms | — | 100.00% | — | 1 |
| openai/gpt-5-nano | 1711 ms | — | 100.00% | — | 20 |
| openai/o3-mini | 1718 ms | — | 100.00% | — | 1 |
| openai/gpt-6-astra | 1929 ms | — | 100.00% | — | 1 |
| openai/gpt-5.5 | 1987 ms | — | 100.00% | — | 1 |
| openai/gpt-3.5-turbo-1106 | 2080 ms | — | 100.00% | — | 1 |
| openai/gpt-5.2 | 2247 ms | — | 100.00% | — | 1 |
| openai/gpt-5-mini | 2461 ms | — | 100.00% | — | 1 |
| openai/o4-mini | 2602 ms | — | 100.00% | — | 2 |
| openai/o3 | 3155 ms | — | 100.00% | — | 1 |
| openai/gpt-5.6-terra | 3162 ms | — | 100.00% | — | 1 |
OpenAI performance history · Full provider & model leaderboard.
Models served by OpenAI.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
openai/chat-latestchat-latest |
— | 0 | $5.275/1M | $0.5275/1M | $31.65/1M |
openai/gpt-3.5-turboOpenAI: GPT-3.5 Turbo |
— | 16,385 | $0.5275/1M | Not published | $1.5825/1M |
openai/gpt-3.5-turbo-0125gpt-3.5-turbo-0125 |
— | 0 | $0.5275/1M | Not published | $1.5825/1M |
openai/gpt-3.5-turbo-1106gpt-3.5-turbo-1106 |
— | 0 | $1.055/1M | Not published | $2.11/1M |
openai/gpt-4OpenAI: GPT-4 |
— | 8,191 | $31.65/1M | Not published | $63.3/1M |
openai/gpt-4-0613gpt-4-0613 |
— | 0 | $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 | $0.5275/1M | $8.44/1M |
openai/gpt-4.1-miniOpenAI: GPT-4.1 Mini |
— | 1,047,576 | $0.422/1M | $0.1055/1M | $1.688/1M |
openai/gpt-4.1-nanoOpenAI: GPT-4.1 Nano |
— | 1,047,576 | $0.1055/1M | $0.026375/1M | $0.422/1M |
openai/gpt-4oOpenAI: GPT-4o |
IQ 81#127 | 128,000 | $2.6375/1M | $1.31875/1M | $10.55/1M |
openai/gpt-4o-2024-05-13OpenAI: GPT-4o (2024-05-13) |
— | 128,000 | $5.275/1M | Not published | $15.825/1M |
openai/gpt-4o-miniOpenAI: GPT-4o-mini |
— | 128,000 | $0.15825/1M | $0.079125/1M | $0.633/1M |
openai/gpt-5OpenAI: GPT-5 |
IQ 112#50 | 400,000 | $1.31875/1M | $0.131875/1M | $10.55/1M |
openai/gpt-5-miniOpenAI: GPT-5 Mini |
— | 400,000 | $0.26375/1M | $0.026375/1M | $2.11/1M |
openai/gpt-5-nanoOpenAI: GPT-5 Nano |
IQ 96#99 | 400,000 | $0.05275/1M | $0.01/1M | $0.422/1M |
openai/gpt-5.1OpenAI: GPT-5.1 |
IQ 111#54 | 400,000 | $1.31875/1M | $0.131875/1M | $10.55/1M |
openai/gpt-5.2OpenAI: GPT-5.2 |
IQ 119#28 | 400,000 | $1.84625/1M | $0.184625/1M | $14.77/1M |
openai/gpt-5.4-miniOpenAI: GPT-5.4 Mini |
IQ 112#51 | 400,000 | $0.79125/1M | $0.079125/1M | $4.7475/1M |
openai/gpt-5.5OpenAI: GPT-5.5 |
IQ 133#6 | 1,050,000 | $5.275/1M | $0.5275/1M to $1.055/1M | $31.65/1M |
openai/gpt-5.6-lunaOpenAI: GPT-5.6 Luna |
IQ 129#9 | 1,050,000 | $0.211/1M | $0.0211/1M to $0.0422/1M | $1.266/1M |
openai/gpt-5.6-solOpenAI: GPT-5.6 Sol |
IQ 136#4 | 1,050,000 | $4.22/1M | $0.422/1M to $0.844/1M | $21.1/1M |
openai/gpt-5.6-terraOpenAI: GPT-5.6 Terra |
IQ 132#7 | 1,050,000 | $2.11/1M | $0.211/1M to $0.422/1M | $12.66/1M |
openai/gpt-6-astraOpenAI: GPT-6 Astra |
IQ 139#1 | 1,050,000 | $10.55/1M | $1.055/1M to $2.11/1M | $52.75/1M |
openai/o1OpenAI: o1 |
IQ 88#117 | 200,000 | $15.825/1M | $7.9125/1M | $63.3/1M |
openai/o3OpenAI: o3 |
IQ 101#82 | 200,000 | $2.11/1M | $0.5275/1M | $8.44/1M |
openai/o3-miniOpenAI: o3 Mini |
— | 200,000 | $1.1605/1M | $0.58025/1M | $4.642/1M |
openai/o4-miniOpenAI: o4 Mini |
— | 200,000 | $1.1605/1M | $0.290125/1M | $4.642/1M |
openai/sora-2OpenAI Sora 2 |
— | 2,500 | selected route | Not published | selected route |
openai/sora-2-proOpenAI Sora 2 Pro |
— | 2,500 | selected route | Not published | selected route |
openai/text-embedding-3-largeOpenAI Text Embedding 3 Large |
— | 8,191 | $0.13715/1M | Not published | selected route |
openai/text-embedding-3-smallOpenAI Text Embedding 3 Small |
— | 8,191 | $0.0211/1M | Not published | selected route |
openai/text-embedding-ada-002OpenAI Text Embedding Ada 002 |
— | 8,191 | $0.1055/1M | Not published | selected route |
Questions
Does OpenAI have zero data retention?
TrustedRouter records its managed 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 33 public OpenAI models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.