per second audio
openai/whisper-large-v3
deepinfra/openai/whisper-large-v3
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.
Price
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
No provider prices yet.
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.01 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| second_audio | Not published— | Not published— | $0.000008/second audio | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-09 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-10 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-11 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-12 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-13 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-14 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-15 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-16 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-17 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-18 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-19 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-20 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-21 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-22 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-23 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-24 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-25 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-26 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-27 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-28 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-29 | second_audio | Not published— | Not published— | $0.000008 |
| 2026-10-30 | second_audio | Not published— | Not published— | $0.000008 |
Alternatives
- Qwen/Qwen3-ASR-1.7B$0.000008/second audio · Compare
- nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b$0.000003/second audio · Compare
- openai/whisper-large-v3-turbo$0.000003/second audio · Compare
- Qwen/Qwen3-ASR-0.6B$0.000003/second audio · Compare
- Fish Audio: S2.1 Pro Free (free)$0/1M · Compare
- HeyGen: HeyGen Voice Turbo (free)$0/1M · Compare
Parameters (1)
stt
Call this model
OpenRouter id deepinfra/openai/whisper-large-v3. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepinfra/openai/whisper-large-v3","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "deepinfra/openai/whisper-large-v3",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "deepinfra/openai/whisper-large-v3", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())