Skip to content

feat: add Qwen3 Next 80B A3B models to chutes provider #7948

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
merged 1 commit into from
Sep 14, 2025
Merged

feat: add Qwen3 Next 80B A3B models to chutes provider #7948

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
22 changes: 22 additions & 0 deletions packages/types/src/providers/chutes.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,8 @@ export type ChutesModelId =
| "moonshotai/Kimi-K2-Instruct-75k"
| "moonshotai/Kimi-K2-Instruct-0905"
| "Qwen/Qwen3-235B-A22B-Thinking-2507"
| "Qwen/Qwen3-Next-80B-A3B-Instruct"
| "Qwen/Qwen3-Next-80B-A3B-Thinking"

export const chutesDefaultModelId: ChutesModelId = "deepseek-ai/DeepSeek-R1-0528"

Expand Down Expand Up @@ -308,4 +310,24 @@ export const chutesModels = {
outputPrice: 0.31202496,
description: "Qwen3 235B A22B Thinking 2507 model with 262K context window.",
},
"Qwen/Qwen3-Next-80B-A3B-Instruct": {
maxTokens: 32768,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
description:
"Fast, stable instruction-tuned model optimized for complex tasks, RAG, and tool use without thinking traces.",
},
"Qwen/Qwen3-Next-80B-A3B-Thinking": {
Copy link
Contributor

@roomote roomote bot Sep 12, 2025

Choose a reason for hiding this comment

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

Given that this is a "Thinking" model with structured thinking traces (as mentioned in the description), should we consider adding reasoning support properties like supportsReasoningBudget: true or supportsReasoningEffort: true?

I noticed other thinking models in the codebase like "Qwen3-235B-A22B-Thinking-2507" (line 304) have similar descriptions. Would this model benefit from the same reasoning capabilities?

maxTokens: 32768,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0,
outputPrice: 0,
description:
"Reasoning-first model with structured thinking traces for multi-step problems, math proofs, and code synthesis.",
},
} as const satisfies Record<string, ModelInfo>
Loading