per character
sesame/csm-1b
deepinfra/sesame/csm-1b
CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio decoder that produces Mimi audio codes.
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.
No published price at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| character | $7/character | Not published— | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | character | $7 | Not published— | Not published— |
| 2026-10-09 | character | $7 | Not published— | Not published— |
| 2026-10-10 | character | $7 | Not published— | Not published— |
| 2026-10-11 | character | $7 | Not published— | Not published— |
| 2026-10-12 | character | $7 | Not published— | Not published— |
| 2026-10-13 | character | $7 | Not published— | Not published— |
| 2026-10-14 | character | $7 | Not published— | Not published— |
| 2026-10-15 | character | $7 | Not published— | Not published— |
| 2026-10-16 | character | $7 | Not published— | Not published— |
| 2026-10-17 | character | $7 | Not published— | Not published— |
| 2026-10-18 | character | $7 | Not published— | Not published— |
| 2026-10-19 | character | $7 | Not published— | Not published— |
| 2026-10-20 | character | $7 | Not published— | Not published— |
| 2026-10-21 | character | $7 | Not published— | Not published— |
| 2026-10-22 | character | $7 | Not published— | Not published— |
| 2026-10-23 | character | $7 | Not published— | Not published— |
| 2026-10-24 | character | $7 | Not published— | Not published— |
| 2026-10-25 | character | $7 | Not published— | Not published— |
| 2026-10-26 | character | $7 | Not published— | Not published— |
| 2026-10-27 | character | $7 | Not published— | Not published— |
| 2026-10-28 | character | $7 | Not published— | Not published— |
| 2026-10-29 | character | $7 | Not published— | Not published— |
| 2026-10-30 | character | $7 | Not published— | Not published— |
Alternatives
- Audio8/Audio8-TTS-Preview-0.6b$5/character · Compare
- Xiaomi: MiMo-V2.6-Pro-UltraSpeed$4.35/1M · Compare
- Google: Gemini 3.1 Pro Preview$4/1M · Compare
- Kokoro 82M$4/1M · Compare
- Meta: Muse Wonder$4/1M · Compare
- Google: Gemini 2.5 Pro$2.5/1M · Compare
Parameters (1)
tts
Call this model
OpenRouter id deepinfra/sesame/csm-1b. 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/sesame/csm-1b","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/sesame/csm-1b",
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/sesame/csm-1b", "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())