7df9e9c664
We had multiple issues with context size calculation: 1. `initial_prompt_tokens` calculation based on cache size is not reliable, cache misses might set it to much higher value. For now hardcoded to a safer constant. 2. Input context size for GPT-5 is 272k (that's where 33% came from). Fixes.
94 lines
3.2 KiB
Rust
94 lines
3.2 KiB
Rust
use crate::model_family::ModelFamily;
|
|
|
|
/// Metadata about a model, particularly OpenAI models.
|
|
/// We may want to consider including details like the pricing for
|
|
/// input tokens, output tokens, etc., though users will need to be able to
|
|
/// override this in config.toml, as this information can get out of date.
|
|
/// Though this would help present more accurate pricing information in the UI.
|
|
#[derive(Debug)]
|
|
pub(crate) struct ModelInfo {
|
|
/// Size of the context window in tokens.
|
|
pub(crate) context_window: u64,
|
|
|
|
/// Maximum number of output tokens that can be generated for the model.
|
|
pub(crate) max_output_tokens: u64,
|
|
}
|
|
|
|
pub(crate) fn get_model_info(model_family: &ModelFamily) -> Option<ModelInfo> {
|
|
let slug = model_family.slug.as_str();
|
|
match slug {
|
|
// OSS models have a 128k shared token pool.
|
|
// Arbitrarily splitting it: 3/4 input context, 1/4 output.
|
|
// https://openai.com/index/gpt-oss-model-card/
|
|
"gpt-oss-20b" => Some(ModelInfo {
|
|
context_window: 96_000,
|
|
max_output_tokens: 32_000,
|
|
}),
|
|
"gpt-oss-120b" => Some(ModelInfo {
|
|
context_window: 96_000,
|
|
max_output_tokens: 32_000,
|
|
}),
|
|
// https://platform.openai.com/docs/models/o3
|
|
"o3" => Some(ModelInfo {
|
|
context_window: 200_000,
|
|
max_output_tokens: 100_000,
|
|
}),
|
|
|
|
// https://platform.openai.com/docs/models/o4-mini
|
|
"o4-mini" => Some(ModelInfo {
|
|
context_window: 200_000,
|
|
max_output_tokens: 100_000,
|
|
}),
|
|
|
|
// https://platform.openai.com/docs/models/codex-mini-latest
|
|
"codex-mini-latest" => Some(ModelInfo {
|
|
context_window: 200_000,
|
|
max_output_tokens: 100_000,
|
|
}),
|
|
|
|
// As of Jun 25, 2025, gpt-4.1 defaults to gpt-4.1-2025-04-14.
|
|
// https://platform.openai.com/docs/models/gpt-4.1
|
|
"gpt-4.1" | "gpt-4.1-2025-04-14" => Some(ModelInfo {
|
|
context_window: 1_047_576,
|
|
max_output_tokens: 32_768,
|
|
}),
|
|
|
|
// As of Jun 25, 2025, gpt-4o defaults to gpt-4o-2024-08-06.
|
|
// https://platform.openai.com/docs/models/gpt-4o
|
|
"gpt-4o" | "gpt-4o-2024-08-06" => Some(ModelInfo {
|
|
context_window: 128_000,
|
|
max_output_tokens: 16_384,
|
|
}),
|
|
|
|
// https://platform.openai.com/docs/models/gpt-4o?snapshot=gpt-4o-2024-05-13
|
|
"gpt-4o-2024-05-13" => Some(ModelInfo {
|
|
context_window: 128_000,
|
|
max_output_tokens: 4_096,
|
|
}),
|
|
|
|
// https://platform.openai.com/docs/models/gpt-4o?snapshot=gpt-4o-2024-11-20
|
|
"gpt-4o-2024-11-20" => Some(ModelInfo {
|
|
context_window: 128_000,
|
|
max_output_tokens: 16_384,
|
|
}),
|
|
|
|
// https://platform.openai.com/docs/models/gpt-3.5-turbo
|
|
"gpt-3.5-turbo" => Some(ModelInfo {
|
|
context_window: 16_385,
|
|
max_output_tokens: 4_096,
|
|
}),
|
|
|
|
"gpt-5" => Some(ModelInfo {
|
|
context_window: 272_000,
|
|
max_output_tokens: 128_000,
|
|
}),
|
|
|
|
_ if slug.starts_with("codex-") => Some(ModelInfo {
|
|
context_window: 272_000,
|
|
max_output_tokens: 128_000,
|
|
}),
|
|
|
|
_ => None,
|
|
}
|
|
}
|