Skip to content

Commit 7879a9e

Browse files
committed
update billing snippets
1 parent a4ec7c5 commit 7879a9e

File tree

1 file changed

+159
-16
lines changed

1 file changed

+159
-16
lines changed

docs/inference-providers/pricing.md

Lines changed: 159 additions & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -94,30 +94,173 @@ Enterprise Hub organizations receive a pool of free usage credits based on the n
9494
<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/inference-providers/enterprise-org-settings-dark.png"/>
9595
</div>
9696

97-
If you are using the JavaScript `InferenceClient`, you can set the `billTo` attribute at a client level:
97+
98+
99+
<hfoptions id="python-clients">
100+
101+
<hfoption id="huggingface_hub">
102+
103+
To bill your organization, use the `bill_to` parameter when initializing the client.
104+
105+
```python
106+
import os
107+
from huggingface_hub import InferenceClient
108+
109+
client = InferenceClient(bill_to="my-org-name")
110+
111+
completion = client.chat.completions.create(
112+
model="deepseek-ai/DeepSeek-V3-0324",
113+
messages=[
114+
{
115+
"role": "user",
116+
"content": "How many 'G's in 'huggingface'?"
117+
}
118+
],
119+
)
120+
121+
print(completion.choices[0].message)
122+
```
123+
124+
</hfoption>
125+
126+
<hfoption id="openai">
127+
128+
To bill your organization when using OpenAI's Python client, set the `X-HF-Bill-To` header using `extra_headers`.
129+
130+
```python
131+
import os
132+
from openai import OpenAI
133+
134+
client = OpenAI(
135+
base_url="https://router.huggingface.co/v1",
136+
api_key=os.environ["HF_TOKEN"],
137+
extra_headers={"X-HF-Bill-To": "my-org-name"},
138+
)
139+
140+
completion = client.chat.completions.create(
141+
model="deepseek-ai/DeepSeek-V3-0324",
142+
messages=[
143+
{
144+
"role": "user",
145+
"content": "How many 'G's in 'huggingface'?"
146+
}
147+
],
148+
)
149+
```
150+
151+
</hfoption>
152+
153+
<hfoption id="requests">
154+
155+
To bill your organization when making direct HTTP requests, include the `X-HF-Bill-To` header.
156+
157+
```python
158+
import os
159+
import requests
160+
161+
API_URL = "https://router.huggingface.co/v1/chat/completions"
162+
headers = {"Authorization": f"Bearer {os.environ['HF_TOKEN']}", "X-HF-Bill-To": "my-org-name"}
163+
payload = {
164+
"messages": [
165+
{
166+
"role": "user",
167+
"content": "How many 'G's in 'huggingface'?"
168+
}
169+
],
170+
"model": "deepseek-ai/DeepSeek-V3-0324",
171+
}
172+
173+
response = requests.post(API_URL, headers=headers, json=payload)
174+
print(response.json()["choices"][0]["message"])
175+
```
176+
177+
</hfoption>
178+
179+
</hfoptions>
180+
181+
Similarily in JavaScript:
182+
183+
<hfoptions id="javascript-clients">
184+
185+
<hfoption id="huggingface.js">
186+
187+
If you are using the JavaScript `InferenceClient`, you can set the `billTo` attribute at a client level to bill your organization.
98188

99189
```js
100190
import { InferenceClient } from "@huggingface/inference";
101191

102-
const client = new InferenceClient("hf_token", { billTo: "my-org-name" });
192+
const client = new InferenceClient(process.env.HF_TOKEN, { billTo: "my-org-name" });
103193

104-
const image = await client.textToImage({
105-
model: "black-forest-labs/FLUX.1-schnell",
106-
inputs: "A majestic lion in a fantasy forest",
107-
provider: "fal-ai",
194+
const completion = await client.chat.completions.create({
195+
model: "deepseek-ai/DeepSeek-V3-0324",
196+
messages: [
197+
{
198+
role: "user",
199+
content: "How many 'G's in 'huggingface'?",
200+
},
201+
],
108202
});
109-
/// Use the generated image (it's a Blob)
110203
```
111204

112-
And similarly in Python:
205+
</hfoption>
113206

114-
```py
115-
from huggingface_hub import InferenceClient
116-
client = InferenceClient(provider="fal-ai", bill_to="my-org-name")
117-
image = client.text_to_image(
118-
"A majestic lion in a fantasy forest",
119-
model="black-forest-labs/FLUX.1-schnell",
120-
)
121-
image.save("lion.png")
207+
<hfoption id="openai">
208+
209+
To bill your organization with the OpenAI JavaScript client, set the `X-HF-Bill-To` header using the `defaultHeaders` option.
210+
211+
```javascript
212+
import OpenAI from "openai";
213+
214+
const client = new OpenAI({
215+
baseURL: "https://router.huggingface.co/v1",
216+
apiKey: process.env.HF_TOKEN,
217+
defaultHeaders: { "X-HF-Bill-To": "my-org-name" },
218+
});
219+
220+
const completion = await client.chat.completions.create({
221+
model: "deepseek-ai/DeepSeek-V3-0324",
222+
messages: [
223+
{
224+
role: "user",
225+
content: "How many 'G's in 'huggingface'?",
226+
},
227+
],
228+
});
229+
230+
console.log(completion.choices[0].message.content);
231+
```
232+
233+
</hfoption>
234+
235+
<hfoption id="fetch">
236+
237+
When using `fetch`, include the `X-HF-Bill-To` header to bill your organization.
238+
239+
```js
240+
import fetch from "node-fetch";
241+
242+
const response = await fetch(
243+
"https://router.huggingface.co/v1/chat/completions",
244+
{
245+
method: "POST",
246+
headers: {
247+
Authorization: `Bearer ${process.env.HF_TOKEN}`,
248+
"Content-Type": "application/json",
249+
"X-HF-Bill-To": "my-org-name",
250+
},
251+
body: JSON.stringify({
252+
model: "deepseek-ai/DeepSeek-V3-0324",
253+
messages: [
254+
{
255+
role: "user",
256+
content: "How many 'G's in 'huggingface'?",
257+
},
258+
],
259+
}),
260+
}
261+
);
262+
console.log(await response.json());
122263
```
264+
</hfoption>
123265

266+
</hfoptions>

0 commit comments

Comments
 (0)