Transcription models
11 models in the catalog. Prices are the best (lowest) input price per million tokens across providers.
Transcription models — best input prices
Transcription models that turn audio into text, priced per 1M input tokens. Compare the cheapest available providers in the table below.
| Model | Type | Providers | Input | Output | Last sync | |
|---|---|---|---|---|---|---|
G2
Gemini 2.5 Flash (batch)
|
Transcription | 1,048,576 | 1 | $0.3 | $2.5 | |
|
G2
Gemini 2.5 Pro (batch)
|
Transcription | 1,048,576 | 1 | $1.25 | $10 | |
MV
MiMo-V2.5
|
Transcription | 1,050,000 | 1 | $0.168 | $0.336 | |
|
MV
MiMo-V2.6-Flash
|
Transcription | 1,048,576 | 2 | $0.14 | $0.28 | |
|
MV
MiMo-V2.6-Pro
|
Transcription | 1,050,000 | 2 | $0.43 | $0.87 | |
|
MV
MiMo-V2.6-Pro-UltraSpeed
|
Transcription | 1,048,576 | 0 | — | — | |
N3
Nemotron 3 Diarization
|
Transcription | 3,600 | 0 | — | — | |
VS
Voxtral Small 24B 2507
|
Transcription | 32,768 | 0 | — | — | |
|
MV
mimo-v2.5-asr
|
Transcription | — | 0 | — | — | |
OL
openai/whisper-large-v3
|
Transcription | — | 0 | — | — | |
|
OL
openai/whisper-large-v3-turbo
|
Transcription | — | 0 | — | — |