OpenAI Whisper
Try OpenAI Whisper on us. Starter credit covers your first requests, then one key reaches this route and every other model in the catalog.
openai/whisper-1
| Publisher | OpenAIopenai |
|---|---|
| AI IQ | No AI IQ profile matched yet. |
| Input limit | 7 MiB, up to 10 minutes |
| Input formats | mp3, wav |
| Billing | audio seconds |
| Price | $0.00633/audio minute |
| API | Audio transcription |
| Providers | |
| Credits routes | 1 provider route |
| Modes | transcription US providers EU-focused |
| Billing | Credits |
How to use OpenAI Whisper
File transcription, billed per request or audio duration, not text tokens.
| Input | POST /v1/audio/transcriptions with multipart file or base64 input_audio, and model. PCM WAV or MP3, at most 7 MiB and ten minutes. |
|---|---|
| Output | JSON text and usage; verbose_json adds supported timestamps. |
Example input
{"model":"openai/whisper-1","input_audio":{"data":"<base64>","format":"wav"}}Example output
{"text":"Hello","usage":{"seconds":1,"cost":0.01}}Current route evidence
Live leaderboardRecent provider-route uptime spans not enough data across 1 route and 1 provider. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.
Providers serving this model
Audio requests use the listed model and provider. These routes do not silently switch models or providers.
Trust boundary: TR router attestation verifies the TrustedRouter gateway only. Provider policy separately describes the upstream model host's retention, confidential compute, and E2EE posture.
| Provider | Input | Cached input | Output | Weight format | TR router attested | Provider policy |
|---|---|---|---|---|---|---|
| OpenAIopenai | $0.00633/audio minute | Not applicable | Included | Unknown | yes | no verified privacy claim |
Endpoint JSON: https://api.trustedrouter.com/v1/models/openai/whisper-1/endpoints
Compare OpenAI Whisper
All comparisons- OpenAI: gpt-oss-120b vs OpenAI Whisper25 combined provider routes
Questions
What model ID should I use for OpenAI Whisper?
Use openai/whisper-1 as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.
Which providers serve OpenAI Whisper?
TrustedRouter currently lists OpenAI for OpenAI Whisper. Provider availability and routing eligibility can change as catalog and health data update.
How much does OpenAI Whisper cost through TrustedRouter?
The current Credits price is $0.00633/audio minute. Output is included; these are audio prices, not text-token prices.
How do I require zero data retention for OpenAI Whisper?
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.