TrustedRouter Confidential
Compare every TrustedRouter route for TrustedRouter Confidential, including token pricing, context limits, privacy policy, regional availability, measured uptime, and API support.
trustedrouter/confidential
| Publisher | TrustedRoutertrustedrouter |
|---|---|
| AI IQ | No AI IQ profile matched yet. |
| Context | 128,000 tokens |
| Orchestration |
routing pool
Canonical: trustedrouter/e2e
|
| Components | |
| Credits routes | 0 provider routes |
| Modes | chat US providers EU-focused |
| Billing | Credits |
Models used by this orchestration
This TrustedRouter model is an orchestration preset. The gateway routes through the component models below inside the attested prompt path, using the preset's worker, advisor, judge, or synthesizer roles.
| Component | Provider | Prompt | Cached input | Completion |
|---|---|---|---|---|
| openai/gpt-oss-120b open weights OpenAI: gpt-oss-120b |
OpenAI | $0.03165/1M to $0.36925/1M | $0.015825/1M to $0.1055/1M | $0.17935/1M to $0.79125/1M |
| deepseek/deepseek-v4-flash open weights DeepSeek: DeepSeek V4 Flash 0423 |
DeepSeek | $0.07174/1M to $0.3165/1M | $0.01/1M to $0.104973/1M | $0.17724/1M to $0.7385/1M |
| google/gemma-4-31b-it open weights Google: Gemma 4 31B |
Google AI Studio | $0.1055/1M to $0.422/1M | $0.03798/1M to $0.1477/1M | $0.3587/1M to $1.055/1M |
| z-ai/glm-5.3-flash open weights Z.ai: GLM 5.3 Flash |
Z.AI | $0.07385/1M to $0.422/1M | $0.015825/1M to $0.1055/1M | $0.2532/1M to $1.31875/1M |
| meta-llama/llama-3.3-70b-instruct open weights Meta: Llama 3.3 70B Instruct |
Cerebras | $0.142425/1M to $1.84625/1M | $0.11605/1M to $0.633/1M | $0.422/1M to $2.90125/1M |
| z-ai/glm-5.3 open weights Z.ai: GLM 5.3 |
Z.AI | $1.0339/1M to $5.1273/1M | $0.1266/1M to $1.02546/1M | $3.2494/1M to $12.81825/1M |
| moonshotai/kimi-k3 open weights MoonshotAI: Kimi K3 |
Kimi | $2.05725/1M to $4.22/1M | $0.205725/1M to $1.7302/1M | $10.28625/1M to $21.1/1M |
| mistralai/mistral-nemo Mistral: Mistral Nemo |
Mistral | $0.025848/1M to $0.0422/1M | $0.01/1M | $0.103179/1M to $0.17935/1M |
| google/gemma-4-31b-turbo open weights google/gemma-4-31B-turbo |
Google AI Studio | $0.1266/1M | $0.01266/1M | $0.39035/1M |
| qwen/qwen3-32b open weights Qwen: Qwen3 32B |
DeepInfra | $0.10972/1M to $0.1688/1M | $0.010972/1M to $0.01688/1M | $0.43888/1M to $0.6752/1M |
| qwen/qwen3-235b-a22b-thinking-2507 open weights Qwen: Qwen3 235B A22B Thinking 2507 |
Novita AI | $0.24265/1M to $0.47475/1M | $0.024265/1M to $0.031534/1M | $1.261464/1M to $3.6925/1M |
| deepseek/deepseek-v3.2 open weights DeepSeek: DeepSeek V3.2 |
DeepSeek | $0.26375/1M to $1.567836/1M | $0.079125/1M to $0.783918/1M | $0.4009/1M to $2.804507/1M |
Questions
What model ID should I use for TrustedRouter Confidential?
Use trustedrouter/confidential as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.
Which providers serve TrustedRouter Confidential?
TrustedRouter currently lists no Credits provider route for TrustedRouter Confidential. Provider availability and routing eligibility can change as catalog and health data update.
How much does TrustedRouter Confidential cost through TrustedRouter?
TrustedRouter currently publishes no Credits provider route for TrustedRouter Confidential, so no public Credits price is available.
How do I require zero data retention for TrustedRouter Confidential?
Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.