Regolo
Explore Regolo models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Regoloregolo
ZDR
These privacy labels describe Regolo, the upstream model provider. ZDR is a retention policy; verified confidential inference additionally requires attested provider compute and end-to-end encryption.
| Provider | Regolo |
|---|---|
| Routing status | Active |
| Provider website | https://regolo.ai/ |
| Models | 11 public models |
| Credits routes | 11 |
| Zero data retention | yes All routes |
| Verified confidential inference | Not verified |
| Policy note | Regolo states that inference prompts and outputs are processed in memory and discarded, with no reuse for training. This is a provider policy, not verified confidential compute or provider-side E2EE. Policy source |
Measured performance
24 samplesContinuously sampled across Regolo'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 | 1782 ms |
|---|---|
| Effective throughput | 139 tok/s n=2 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| mistralai/mistral-small-2603 | 954 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.3-70b-instruct | 1162 ms | — | 100.00% | — | 4 |
| qwen/qwen3.5-9b | 1515 ms | — | 100.00% | — | 2 |
| qwen/qwen3-coder-next | 1525 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 1782 ms | 139 tok/s n=2 | 100.00% | — | 3 |
| swiss-ai/apertus-70b-instruct | 1913 ms | — | 100.00% | — | 3 |
| qwen/qwen3.5-122b-a10b | 1965 ms | — | 100.00% | — | 2 |
| qwen/qwen3.8-27b | 2096 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 2201 ms | — | 100.00% | — | 5 |
| openai/gpt-oss-20b | 2469 ms | — | 100.00% | — | 1 |
Regolo performance history · Full provider & model leaderboard.
Models served by Regolo.
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 103#80 | 262,144 | $0.487453/1M | Not published | $2.559125/1M |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | $0.731179/1M | Not published | $3.290303/1M |
mistralai/mistral-small-2603Mistral: Mistral Small 4 |
— | 262,144 | $0.609316/1M | Not published | $2.559125/1M |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 98#99 | 131,072 | $1.218631/1M | Not published | $5.118249/1M |
openai/gpt-oss-20bOpenAI: gpt-oss-20b |
IQ 93#113 | 131,072 | $0.121864/1M | Not published | $0.511825/1M |
qwen/qwen3-coder-nextQwen: Qwen3 Coder Next |
— | 262,144 | $0.609316/1M | Not published | $2.437261/1M |
qwen/qwen3.5-122b-a10bQwen: Qwen3.5-122B-A10B |
— | 262,144 | $1.218631/1M | Not published | $5.118249/1M |
qwen/qwen3.5-9bQwen: Qwen3.5-9B |
IQ 95#108 | 262,144 | $0.085305/1M | Not published | $0.426521/1M |
qwen/qwen3.8-27bQwen: Qwen3.8 27B |
IQ 110#60 | 262,144 | $0.609316/1M | Not published | $2.559125/1M |
swiss-ai/apertus-70b-instructapertus-70b |
— | 30,000 | $0.487453/1M | Not published | $2.559125/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#28 | 1,048,576 | $2.437261/1M | Not published | $6.336879/1M |
Questions
Does Regolo have zero data retention?
TrustedRouter records Regolo as supporting provider-level zero data retention based on the policy source linked on this page. This is a provider policy claim, separate from TrustedRouter's content-stateless real-time gateway and from end-to-end confidential compute.
Is Regolo end-to-end encrypted?
TrustedRouter does not currently mark Regolo 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 Regolo models are available through TrustedRouter?
This page currently lists 11 public Regolo models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.