Skip to content

fix incorrect max tokens values for groq provider #9790

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
michaelneale merged 1 commit into from
Jun 15, 2026
Merged

fix incorrect max tokens values for groq provider #9790

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 7 additions & 7 deletions crates/goose/src/providers/declarative/groq.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,17 +9,17 @@
{
"name": "moonshotai/kimi-k2-instruct-0905",
"context_limit": 262144,
"max_tokens": 16384
"max_tokens": 8192
},
{
"name": "openai/gpt-oss-120b",
"context_limit": 131072,
"max_tokens": 65536
"max_tokens": 8192

@chatgpt-codex-connector chatgpt-codex-connector Bot Jun 14, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

P2 Badge Update the canonical max-token limits too

This max_tokens value is not consumed from groq.json: declarative models are deserialized as Vec<ModelInfo>, and ModelInfo has no max_tokens field, so serde drops this key. The request limit is instead filled by ModelConfig::with_canonical_limits from canonical_models.json; for groq/openai/gpt-oss-120b that data still has limit.output: 65536, so default Groq requests for this model will continue sending the old limit rather than 8192. Please update the canonical limit data or wire this field through the declarative model type.

Useful? React with 👍 / 👎.

},
{
"name": "openai/gpt-oss-20b",
"context_limit": 131072,
"max_tokens": 65536
"max_tokens": 8192
},
{
"name": "meta-llama/llama-4-maverick-17b-128e-instruct",
Expand All @@ -34,22 +34,22 @@
{
"name": "qwen/qwen3-32b",
"context_limit": 131072,
"max_tokens": 40960
"max_tokens": 8192
},
{
"name": "llama-3.3-70b-versatile",
"context_limit": 131072,
"max_tokens": 32768
"max_tokens": 8192
},
{
"name": "llama-3.1-8b-instant",
"context_limit": 131072,
"max_tokens": 131072
"max_tokens": 8192
},
{
"name": "openai/gpt-oss-safeguard-20b",
"context_limit": 131072,
"max_tokens": 65536
"max_tokens": 8192
},
{
"name": "meta-llama/llama-guard-4-12b",
Expand Down
Loading