Skip to content

Update OpenAPI specification to use gpt-5 model and replace max_token… #131

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
prabhash-varma merged 2 commits into from
Mar 25, 2026
Merged

Update OpenAPI specification to use gpt-5 model and replace max_token… #131

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
571793d
Update OpenAPI specification to use gpt-5 model and replace max_token…
prabhash-varma Mar 25, 2026
bc50f68
Update OpenAPI specification to deprecate max_tokens in favor of max_…
prabhash-varma Mar 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
103 changes: 76 additions & 27 deletions openapi.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -190,7 +190,7 @@ paths:
-H "x-portkey-api-key: $PORTKEY_API_KEY" \
-H "x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY" \
-d '{
"model": "gpt-4o",
"model": "gpt-5",
"messages": [
{
"role": "system",
Expand All @@ -200,7 +200,8 @@ paths:
"role": "user",
"content": "Hello!"
}
]
],
"max_completion_tokens": 250
}'
- lang: cURL
label: Self-Hosted
Expand All @@ -210,7 +211,7 @@ paths:
-H "x-portkey-api-key: $PORTKEY_API_KEY" \
-H "x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY" \
-d '{
"model": "gpt-4o",
"model": "gpt-5",
"messages": [
{
"role": "system",
Expand All @@ -220,7 +221,8 @@ paths:
"role": "user",
"content": "Hello!"
}
]
],
"max_completion_tokens": 250
}'
- lang: python
label: Default
Expand All @@ -233,11 +235,12 @@ paths:
)

response = portkey.chat.completions.create(
model="gpt-4o",
model="gpt-5",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
]
],
max_completion_tokens=250
)

print(response.choices[0].message)
Expand All @@ -253,11 +256,12 @@ paths:
)

response = portkey.chat.completions.create(
model="gpt-4o",
model="gpt-5",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
]
],
max_completion_tokens=250
)

print(response.choices[0].message)
Expand All @@ -274,7 +278,8 @@ paths:
async function main() {
const response = await portkey.chat.completions.create({
messages: [{ role: "system", content: "You are a helpful assistant." }],
model: "gpt-4o",
model: "gpt-5",
max_completion_tokens: 250,
});

console.log(response.choices[0]);
Expand All @@ -295,7 +300,8 @@ paths:
async function main() {
const response = await portkey.chat.completions.create({
messages: [{ role: "system", content: "You are a helpful assistant." }],
model: "gpt-4o",
model: "gpt-5",
max_completion_tokens: 250,
});

console.log(response.choices[0]);
Expand Down Expand Up @@ -1803,7 +1809,7 @@ paths:
required:
- variables
description: |
Note: Although hyperparameters are shown grouped here (like messages, max_tokens, temperature, etc.), they should only be passed at the root level, alongside 'variables' and 'stream'.
Note: Although hyperparameters are shown grouped here (like messages, max_completion_tokens, temperature, etc.), they should only be passed at the root level, alongside 'variables' and 'stream'. The `max_tokens` parameter is deprecated — use `max_completion_tokens` instead.
properties:
variables:
type: object
Expand Down Expand Up @@ -1853,7 +1859,7 @@ paths:
"variables": {
"user_input": "Hello world"
},
"max_tokens": 250,
"max_completion_tokens": 250,
"presence_penalty": 0.2
}'
Comment on lines 1861 to 1864
Copy link

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The /prompts/{promptId}/completions request schema description above still references max_tokens in its hyperparameters note, but the examples here were updated to use max_completion_tokens. Please update that note to mention max_completion_tokens (and/or note max_tokens is deprecated) to keep the documentation consistent.

Copilot uses AI. Check for mistakes.
- lang: Python
Expand All @@ -1870,7 +1876,7 @@ paths:
variables={
"user_input": "Hello world"
},
max_tokens=250,
max_completion_tokens=250,
presence_penalty=0.2
)

Expand All @@ -1890,7 +1896,7 @@ paths:
variables: {
user_input: "Hello world"
},
max_tokens: 250,
max_completion_tokens: 250,
presence_penalty: 0.2
});

Expand All @@ -1905,7 +1911,7 @@ paths:
"variables": {
"user_input": "Hello world"
},
"max_tokens": 250,
"max_completion_tokens": 250,
"presence_penalty": 0.2
}'
- lang: python
Expand All @@ -1923,7 +1929,7 @@ paths:
variables={
"user_input": "Hello world"
},
max_tokens=250,
max_completion_tokens=250,
presence_penalty=0.2
)

Expand All @@ -1943,7 +1949,7 @@ paths:
variables: {
user_input: "Hello world"
},
max_tokens: 250,
max_completion_tokens: 250,
presence_penalty: 0.2
});

Expand Down Expand Up @@ -1975,7 +1981,7 @@ paths:
required:
- variables
description: |
Note: Although hyperparameters are shown grouped here (like messages, max_tokens, temperature, etc.), they should only be passed at the root level, alongside 'variables' and 'stream'.
Note: Although hyperparameters are shown grouped here (like messages, max_completion_tokens, temperature, etc.), they should only be passed at the root level, alongside 'variables' and 'stream'. The `max_tokens` parameter is deprecated — use `max_completion_tokens` instead.
properties:
variables:
type: object
Expand Down Expand Up @@ -2008,7 +2014,7 @@ paths:
"variables": {
"user_input": "Hello world"
},
"max_tokens": 250,
"max_completion_tokens": 250,
"presence_penalty": 0.2
}'
Comment on lines 2015 to 2019
Copy link

Copilot AI Mar 25, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The /prompts/{promptId}/render request schema description above still references max_tokens in its hyperparameters note, but the examples here were updated to use max_completion_tokens. Please update that note to mention max_completion_tokens (and/or note max_tokens is deprecated) to keep the documentation consistent.

Copilot uses AI. Check for mistakes.
- lang: Python
Expand All @@ -2025,7 +2031,7 @@ paths:
variables={
"user_input": "Hello world"
},
max_tokens=250,
max_completion_tokens=250,
presence_penalty=0.2
)

Expand All @@ -2045,7 +2051,7 @@ paths:
variables: {
user_input: "Hello world"
},
max_tokens: 250,
max_completion_tokens: 250,
presence_penalty: 0.2
});

Expand All @@ -2060,7 +2066,7 @@ paths:
"variables": {
"user_input": "Hello world"
},
"max_tokens": 250,
"max_completion_tokens": 250,
"presence_penalty": 0.2
}'
- lang: Python
Expand All @@ -2078,7 +2084,7 @@ paths:
variables={
"user_input": "Hello world"
},
max_tokens=250,
max_completion_tokens=250,
presence_penalty=0.2
)

Expand All @@ -2099,7 +2105,7 @@ paths:
variables: {
user_input: "Hello world"
},
max_tokens: 250,
max_completion_tokens: 250,
presence_penalty: 0.2
});

Expand Down Expand Up @@ -22282,13 +22288,22 @@ components:
$ref: "#/components/schemas/ChatCompletionRequestMessage"
model:
description: ID of the model to use. See the [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API.
example: "gpt-4-turbo"
example: "gpt-5"
anyOf:
- type: string
- type: string
enum:
[
"gpt-5",
"gpt-5-mini",
"gpt-5-nano",
"o4-mini",
"o3",
"o3-mini",
"o1",
"o1-mini",
"gpt-4o",
"gpt-4o-mini",
"gpt-4o-2024-05-13",
"gpt-4-turbo",
"gpt-4-turbo-2024-04-09",
Expand Down Expand Up @@ -22342,9 +22357,21 @@ components:
nullable: true
max_tokens:
description: |
The maximum number of [tokens](https://platform.openai.com/tokenizer?view=bpe) that can be generated in the chat completion.
Deprecated in favor of `max_completion_tokens`.

The maximum number of [tokens](https://platform.openai.com/tokenizer?view=bpe) that can be generated in the chat completion. This value can be used to control [costs](https://openai.com/api/pricing/) for text generated via API.

The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens.
**Supported models:** GPT-4o, GPT-4o-mini, GPT-4, GPT-4 Turbo, GPT-3.5 Turbo.

**Not supported:** o-series reasoning models (o1, o3, o3-mini, o4-mini) and GPT-5 series — use `max_completion_tokens` instead.
type: integer
nullable: true
deprecated: true
max_completion_tokens:
description: |
An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).

**Supported models:** GPT-5 series, o-series reasoning models (o1, o3, o3-mini, o4-mini) — required. Also supported on GPT-4o, GPT-4o-mini, GPT-4, GPT-4 Turbo, GPT-3.5 Turbo as a replacement for `max_tokens`.
type: integer
nullable: true
n:
Expand Down Expand Up @@ -24999,6 +25026,28 @@ components:
total_tokens:
type: integer
description: Total number of tokens used in the request (prompt + completion).
completion_tokens_details:
type: object
nullable: true
description: Breakdown of tokens used in a completion.
properties:
reasoning_tokens:
type: integer
description: Tokens generated by the model for reasoning.
accepted_prediction_tokens:
type: integer
description: When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.
rejected_prediction_tokens:
type: integer
description: When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion.
prompt_tokens_details:
type: object
nullable: true
description: Breakdown of tokens used in the prompt.
properties:
cached_tokens:
type: integer
description: Cached tokens present in the prompt.
required:
- prompt_tokens
- completion_tokens
Expand Down
Loading