Skip to content

Commit 6007b02

Browse files
mchencothomasgauvin
mchenco
authored and
thomasgauvin
committed
changelog and model docs (#24184)
* changelog and model docs * Update 2025-08-05-openai-open-models.mdx * updates
1 parent 0e68aa4 commit 6007b02

File tree

4 files changed

+246
-1
lines changed

4 files changed

+246
-1
lines changed

‎.gitignore‎

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -29,4 +29,6 @@ pnpm-debug.log*
2929
/assets/secrets
3030
/worker/functions/
3131

32-
.idea
32+
.idea
33+
34+
public/*

‎src/content/changelog/workers-ai/2025-08-05-openai-open-models.mdx‎

Lines changed: 45 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,45 @@
1+
---
2+
title: OpenAI open models now available on Workers AI
3+
description: Partnering with OpenAI as a Day 0 launch partner to bring you 2 new open models on Workers AI
4+
products:
5+
- agents
6+
- workers-ai
7+
date: 2025-08-05
8+
---
9+
10+
We're thrilled to be a Day 0 partner with [OpenAI](http://openai.com/index/introducing-gpt-oss) to bring their [latest open models](https://openai.com/index/gpt-oss-model-card/) to Workers AI, including support for Responses API, Code Interpreter, and Web Search (coming soon).
11+
12+
Get started with the new models at `@cf/openai/gpt-oss-120b` and `@cf/openai/gpt-oss-20b`.
13+
Check out the [blog](https://blog.cloudflare.com/openai-gpt-oss-on-workers-ai) for more details about the new models, and the [`gpt-oss-120b`](/workers-ai/models/gpt-oss-120b) and [`gpt-oss-20b`](/workers-ai/models/gpt-oss-20b) model pages for more information about pricing and context windows.
14+
15+
## Responses API
16+
If you call the model through:
17+
- Workers Binding, it will accept/return Responses API – `env.AI.run(“@cf/openai/gpt-oss-120b”)`
18+
- REST API on `/run` endpoint, it will accept/return Responses API – `https://api.cloudflare.com/client/v4/accounts/<account_id>/ai/run/@cf/openai/gpt-oss-120b`
19+
- REST API on new `/responses` endpoint, it will accept/return Responses API – `https://api.cloudflare.com/client/v4/accounts/<account_id>/ai/v1/responses`
20+
- REST API for OpenAI Compatible endpoint, it will return Chat Completions (coming soon) – `https://api.cloudflare.com/client/v4/accounts/<account_id>/ai/v1/chat/completions`
21+
22+
23+
```
24+
curl https://api.cloudflare.com/client/v4/accounts/<account_id>/ai/v1/responses \
25+
-H "Content-Type: application/json" \
26+
-H "Authorization: Bearer $CLOUDFLARE_API_KEY" \
27+
-d '{
28+
"model": "@cf/openai/gpt-oss-120b",
29+
"reasoning": {"effort": "medium"},
30+
"input": [
31+
{
32+
"role": "user",
33+
"content": "What are the benefits of open-source models?"
34+
}
35+
]
36+
}'
37+
38+
39+
```
40+
41+
## Code Interpreter
42+
The model is natively trained to support stateful code execution, and we've implemented support for this feature using our [Sandbox SDK](https://github.com/cloudflare/sandbox-sdk) and [Containers](https://blog.cloudflare.com/containers-are-available-in-public-beta-for-simple-global-and-programmable/). Cloudflare's Developer Platform is uniquely positioned to support this feature, so we're very excited to bring our products together to support this new use case.
43+
44+
## Web Search (coming soon)
45+
We are working to implement Web Search for the model, where users can bring their own Exa API Key so the model can browse the Internet.

‎src/content/workers-ai-models/gpt-oss-120b.json‎

Lines changed: 99 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,99 @@
1+
{
2+
"id": "f9f2250b-1048-4a52-9910-d0bf976616a1",
3+
"source": 1,
4+
"name": "@cf/openai/gpt-oss-120b",
5+
"description": "OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-120b is for production, general purpose, high reasoning use-cases.",
6+
"task": {
7+
"id": "c329a1f9-323d-4e91-b2aa-582dd4188d34",
8+
"name": "Text Generation",
9+
"description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."
10+
},
11+
"created_at": "2025-08-05 10:27:29.131",
12+
"tags": [],
13+
"properties": [
14+
{
15+
"property_id": "context_window",
16+
"value": "128000"
17+
},
18+
{
19+
"property_id": "price",
20+
"value": [
21+
{
22+
"unit": "per M input tokens",
23+
"price": 0.35,
24+
"currency": "USD"
25+
},
26+
{
27+
"unit": "per M output tokens",
28+
"price": 0.75,
29+
"currency": "USD"
30+
}
31+
]
32+
}
33+
],
34+
"schema": {
35+
"input": {
36+
"type": "object",
37+
"title": "GPT_OSS_Responses",
38+
"properties": {
39+
"input": {
40+
"oneOf": [
41+
{
42+
"type": "string"
43+
},
44+
{
45+
"type": "array",
46+
"items": {
47+
"type": "object",
48+
"properties": {
49+
"role": {
50+
"type": "string",
51+
"description": "The role of the message input. One of user, assistant, system, or developer.",
52+
"enum": [
53+
"user",
54+
"assistant",
55+
"system",
56+
"developer"
57+
]
58+
},
59+
"content": {
60+
"oneOf": [
61+
{
62+
"type": "string",
63+
"description": "The content of the message as a string."
64+
},
65+
{
66+
"type": "array",
67+
"description": "Refer to OpenAI Responses API docs to learn more about supported content types.",
68+
"items": {
69+
"type": "object",
70+
"properties": {}
71+
}
72+
}
73+
]
74+
}
75+
}
76+
}
77+
}
78+
]
79+
}
80+
},
81+
"required": [
82+
"input"
83+
]
84+
},
85+
"output": {
86+
"oneOf": [
87+
{
88+
"type": "object",
89+
"contentType": "application/json"
90+
},
91+
{
92+
"type": "string",
93+
"contentType": "text/event-stream",
94+
"format": "binary"
95+
}
96+
]
97+
}
98+
}
99+
}

‎src/content/workers-ai-models/gpt-oss-20b.json‎

Lines changed: 99 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,99 @@
1+
{
2+
"id": "188a4e1e-253e-46d0-9616-0bf8c149763f",
3+
"source": 1,
4+
"name": "@cf/openai/gpt-oss-20b",
5+
"description": "OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-20b is for lower latency, and local or specialized use-cases.",
6+
"task": {
7+
"id": "c329a1f9-323d-4e91-b2aa-582dd4188d34",
8+
"name": "Text Generation",
9+
"description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."
10+
},
11+
"created_at": "2025-08-05 10:49:53.265",
12+
"tags": [],
13+
"properties": [
14+
{
15+
"property_id": "context_window",
16+
"value": "128000"
17+
},
18+
{
19+
"property_id": "price",
20+
"value": [
21+
{
22+
"unit": "per M input tokens",
23+
"price": 0.2,
24+
"currency": "USD"
25+
},
26+
{
27+
"unit": "per M output tokens",
28+
"price": 0.3,
29+
"currency": "USD"
30+
}
31+
]
32+
}
33+
],
34+
"schema": {
35+
"input": {
36+
"type": "object",
37+
"title": "GPT_OSS_Responses",
38+
"properties": {
39+
"input": {
40+
"oneOf": [
41+
{
42+
"type": "string"
43+
},
44+
{
45+
"type": "array",
46+
"items": {
47+
"type": "object",
48+
"properties": {
49+
"role": {
50+
"type": "string",
51+
"description": "The role of the message input. One of user, assistant, system, or developer.",
52+
"enum": [
53+
"user",
54+
"assistant",
55+
"system",
56+
"developer"
57+
]
58+
},
59+
"content": {
60+
"oneOf": [
61+
{
62+
"type": "string",
63+
"description": "The content of the message as a string."
64+
},
65+
{
66+
"type": "array",
67+
"description": "Refer to OpenAI Responses API docs to learn more about supported content types.",
68+
"items": {
69+
"type": "object",
70+
"properties": {}
71+
}
72+
}
73+
]
74+
}
75+
}
76+
}
77+
}
78+
]
79+
}
80+
},
81+
"required": [
82+
"input"
83+
]
84+
},
85+
"output": {
86+
"oneOf": [
87+
{
88+
"type": "object",
89+
"contentType": "application/json"
90+
},
91+
{
92+
"type": "string",
93+
"contentType": "text/event-stream",
94+
"format": "binary"
95+
}
96+
]
97+
}
98+
}
99+
}

0 commit comments

Comments
 (0)