Support o3/o4 models #110
Draft
Support o3/o4 models #110
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
spencerbart
reviewed
Jun 6, 2025
| @@ -36,7 +36,7 @@ pub fn get_context_size(model: &str) -> usize { | |||
| let base = rest.split(':').next().unwrap_or(rest); | |||
| return get_context_size(base); | |||
| } | |||
| if starts_with_any!(model, "o1-") { | |||
| if starts_with_any!(model, "o1-", "o3-", "o4-") { | |||
There was a problem hiding this comment.
We should probably remove the - so that it includes the parent model and not just the -mini version of the model. The reasoning models also have a context window of 200,000 not 128,000 like the older 4o type model. We should probably also add gpt-4.1 which has a context window of 1,047,576.
if starts_with_any!(model, "o1", "o3", "o4") {
return 200_000;
}
if starts_with_any!(model, "gpt-4.1") {
return 1_047_576;
}
spencerbart
reviewed
Jun 6, 2025
| @@ -105,7 +105,7 @@ println!("max_tokens: {}", max_tokens); | |||
|
|
|||
| | Encoding name | OpenAI models | | |||
| | ----------------------- | ------------------------------------------------------------------------- | | |||
| | `o200k_base` | GPT-4o models, o1 models | | |||
| | `o200k_base` | GPT-4o models, o1, o3, and o4 models | | |||
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
o3ando4model prefixes for tokenizer lookupo200k_baseworks with o1/o3/o4 modelsTesting
cargo test(fails: failed to download crates)