per page
Document Extraction API
sarvam/document-extraction-api
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.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| Sarvam | — | — | Not published— | Not published— | — | — | Listed | sarvam-docs |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$10.50 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| page | Not published— | Not published— | $0.0105/page | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-09 | page | Not published— | Not published— | $0.0103 |
| 2026-10-10 | page | Not published— | Not published— | $0.0103 |
| 2026-10-11 | page | Not published— | Not published— | $0.0103 |
| 2026-10-12 | page | Not published— | Not published— | $0.0104 |
| 2026-10-13 | page | Not published— | Not published— | $0.0105 |
| 2026-10-14 | page | Not published— | Not published— | $0.0105 |
| 2026-10-15 | page | Not published— | Not published— | $0.0105 |
| 2026-10-16 | page | Not published— | Not published— | $0.0105 |
| 2026-10-17 | page | Not published— | Not published— | $0.0105 |
| 2026-10-18 | page | Not published— | Not published— | $0.0105 |
| 2026-10-19 | page | Not published— | Not published— | $0.0105 |
| 2026-10-20 | page | Not published— | Not published— | $0.0105 |
| 2026-10-21 | page | Not published— | Not published— | $0.0106 |
| 2026-10-22 | page | Not published— | Not published— | $0.0105 |
| 2026-10-23 | page | Not published— | Not published— | $0.0105 |
| 2026-10-24 | page | Not published— | Not published— | $0.0105 |
| 2026-10-25 | page | Not published— | Not published— | $0.0105 |
| 2026-10-26 | page | Not published— | Not published— | $0.0105 |
| 2026-10-27 | page | Not published— | Not published— | $0.0105 |
| 2026-10-28 | page | Not published— | Not published— | $0.0105 |
| 2026-10-29 | page | Not published— | Not published— | $0.0105 |
| 2026-10-30 | page | Not published— | Not published— | $0.0105 |
Alternatives
- BAAI/bge-en-icl$0.01/1M · Compare
- BAAI/bge-large-en-v1.5$0.01/1M · Compare
- BAAI/bge-m3$0.01/1M · Compare
- BAAI/bge-m3-multi$0.01/1M · Compare
- BAAI/bge-m3-multi-8k$0.01/1M · Compare
- BAAI: bge-large-en-v1.5$0.01/1M · Compare
Call this model
OpenRouter id sarvam/document-extraction-api. 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":"sarvam/document-extraction-api","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: "sarvam/document-extraction-api",
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": "sarvam/document-extraction-api", "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())