TrustedRouter E2E
Compare every TrustedRouter route for TrustedRouter E2E, including token pricing, context limits, privacy policy, regional availability, measured uptime, and API support.
trustedrouter/e2e
| Publisher | TrustedRoutertrustedrouter |
|---|---|
| AI IQ | No AI IQ profile matched yet. |
| Context | 128,000 tokens |
| Orchestration | routing pool |
| Components | |
| Endpoints | 0 endpoints |
| Modes | chat US providers EU-focused |
| Routes | prepaid BYOK |
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 | Completion |
|---|---|---|---|
| openai/gpt-oss-120b open weights OpenAI: gpt-oss-120b |
OpenAI | $0.039035/1M to $0.36925/1M | $0.17935/1M to $0.79125/1M |
| google/gemma-4-31b-it open weights Google: Gemma 4 31B |
Google AI Studio | $0.1266/1M to $1.04445/1M | $0.3798/1M to $1.57195/1M |
| deepseek/deepseek-v4-flash open weights DeepSeek: DeepSeek V4 Flash 0423 |
DeepSeek | $0.07174/1M to $0.7385/1M | $0.17724/1M to $2.0045/1M |
| meta-llama/llama-3.3-70b-instruct open weights Meta: Llama 3.3 70B Instruct |
Cerebras | $0.142425/1M to $1.84625/1M | $0.422/1M to $2.90125/1M |
| z-ai/glm-5.2 open weights Z.ai: GLM 5.2 |
Z.AI | $0.7174/1M to $1.5825/1M | $1.5825/1M to $5.53875/1M |
| moonshotai/kimi-k3 open weights MoonshotAI: Kimi K3 |
Kimi | $2.69025/1M to $4.22/1M | $13.45125/1M to $21.1/1M |
| mistralai/mistral-nemo Mistral: Mistral Nemo |
Mistral | $0.025848/1M to $0.0422/1M | $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 | $0.39035/1M |
| qwen/qwen3-32b open weights Qwen: Qwen3 32B |
DeepInfra | $0.10972/1M to $0.1688/1M | $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 | $1.261464/1M to $3.6925/1M |
| deepseek/deepseek-v3.2 open weights DeepSeek: DeepSeek V3.2 |
DeepSeek | $0.220284/1M to $1.055/1M | $0.326628/1M to $1.5825/1M |
| qwen/qwen3.6-27b open weights Qwen: Qwen3.6 27B |
DeepInfra | $0.30595/1M to $0.633/1M | $2.11/1M to $3.798/1M |
Questions
What model ID should I use for TrustedRouter E2E?
Use trustedrouter/e2e as the model field with the TrustedRouter OpenAI-compatible API. The same model ID works for prepaid and eligible BYOK routes.
Which providers serve TrustedRouter E2E?
TrustedRouter currently lists TrustedRouter for TrustedRouter E2E. Provider availability and routing eligibility can change as catalog and health data update.
How much does TrustedRouter E2E cost through TrustedRouter?
The current lowest prepaid input price is BYOK only and the lowest output price is BYOK only. Prices are per one million tokens and come from the current route catalog.
How do I require zero data retention for TrustedRouter E2E?
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.