Whisper

OpenAIOpen weights

Whisper by OpenAI costs — per 1M input tokens and — per 1M output tokens, with a —-token context window.

Pricing

Input (per 1M tokens)

—

Output (per 1M tokens)

—

Cached input (per 1M)

—

Specifications

Provider: OpenAI
Context window: —
Parameters: 2B
Released: Sep 2022
Open weights: Yes
Frontier model: No

Compare Whisper with…

Whisper vs DeepSeek V3.1 Terminus$1.00/1M Whisper vs Qwen2.5 Coder 32B Instruct$1.00/1M Whisper vs Nemotron 3 Super 120B A12B$1.00/1M Whisper vs MiniMax M2$1.02/1M Whisper vs MiniMax M3 Thinking$0.96/1M Whisper vs MiniMax M2.5$0.95/1M

FAQ

How much does Whisper cost?

Whisper is priced at — per 1M input tokens and — per 1M output tokens. Output tokens cost more than input.

What is Whisper's context window?

Whisper supports a context window of — tokens — the maximum prompt plus response length it can handle in a single request.

Is Whisper open weight?

Yes — Whisper has openly available weights.

Data as of 2026-10-20. Source: Epoch AI, Data on AI Models (CC BY 4.0), epoch.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.