OpenAI compatible API · Attested · Public status

Polyphemus 1.0

Compare every TrustedRouter route for Polyphemus 1.0, including token pricing, context limits, privacy policy, regional availability, measured uptime, and API support.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

`trustedrouter/polyphemus-1.0`

TrustedRouter

All models

Publisher	TrustedRoutertrustedrouter
AI IQ	No AI IQ profile matched yet.
Context	65,536 tokens
Orchestration	routing pool
Components
Credits routes	1 provider route
Input price	$0.05/1M tokens
Cached input	selected route
Output price	selected route tokens
Modes
Billing	Credits

How to use Polyphemus 1.0

TrustedRouter selects a model for your task, then runs it. Responses API only. Standard privacy, not ZDR or confidential. $0.05 per million selector prompt tokens plus the selected model's normal token charges; generation is not free. Selector tokens are estimated from the serialized conversation and tools (UTF-8 bytes / 4, rounded down, minimum one token), not measured selector usage. Selector charges use normal microdollar rounding, minimum $0.000001. If selection fails, trustedrouter/auto handles the request without a selector fee.

Input	POST /v1/responses with text input and optional function tools. Generate a fresh UUID per conversation, then reuse the same session_id and API key across conversation turns for cache-aware model selection; send the conversation history on each turn. Omit session_id for independent one-shot requests. Routing sessions expire after one hour of inactivity. This does not pin a provider or guarantee a cache hit.
Output	A standard Responses response or event stream with cost breakdown.

Input

POST /v1/responses with text input and optional function tools. Generate a fresh UUID per conversation, then reuse the same session_id and API key across conversation turns for cache-aware model selection; send the conversation history on each turn. Omit session_id for independent one-shot requests. Routing sessions expire after one hour of inactivity. This does not pin a provider or guarantee a cache hit.

Output

A standard Responses response or event stream with cost breakdown.

Example input

{"model":"trustedrouter/polyphemus-1.0","input":"What is the capital of France?"}

Example output

{"model":"trustedrouter/polyphemus-1.0","output":[{"type":"message","role":"assistant","content":[{"type":"output_text","text":"Paris."}]}]}

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

Questions

What model ID should I use for Polyphemus 1.0?

Use trustedrouter/polyphemus-1.0 as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Which providers serve Polyphemus 1.0?

TrustedRouter currently lists TrustedRouter for Polyphemus 1.0. Provider availability and routing eligibility can change as catalog and health data update.

How much does Polyphemus 1.0 cost through TrustedRouter?

The current lowest Credits input price is $0.05/1M and the lowest Credits output price is selected route. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for Polyphemus 1.0?

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.