Skip to content

fix: add Kimi, MiniMax, and Qwen model configurations for Bedrock #9905

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
mrubens merged 4 commits into from
Dec 8, 2025
Merged

fix: add Kimi, MiniMax, and Qwen model configurations for Bedrock #9905

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b931236
fix: add Kimi, MiniMax, and Qwen model configurations for Bedrock
roomote Dec 7, 2025
610a656
fix: add preserveReasoning flag and update Kimi K2 context window
roomote Dec 8, 2025
1e67ca8
fix: update MiniMax M2 context window to 196_608 for Bedrock
roomote Dec 8, 2025
8d696d3
Update packages/types/src/providers/bedrock.ts
mrubens Dec 8, 2025
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
46 changes: 46 additions & 0 deletions packages/types/src/providers/bedrock.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -439,6 +439,52 @@ export const bedrockModels = {
inputPrice: 0.02,
description: "Amazon Titan Text Embeddings V2",
},
"moonshot.kimi-k2-thinking": {
maxTokens: 32_000,
contextWindow: 262_144,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
defaultToolProtocol: "native",
preserveReasoning: true,
inputPrice: 0.6,
outputPrice: 2.5,
description: "Kimi K2 Thinking (1T parameter MoE model with 32B active parameters)",
},
Comment on lines +442 to +453
Copy link
Contributor Author

@roomote roomote bot Dec 8, 2025

Choose a reason for hiding this comment

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

The moonshot.kimi-k2-thinking configuration still differs from the tested and confirmed working configuration. According to issue #9902 comment #3622616185, the tested configuration uses maxTokens: 16_000 (not 32_000). Additionally, the model is missing supportsTemperature: true and defaultTemperature: 1.0 fields, which are present in the moonshot.ts provider configuration and were part of the tested configuration. These fields are important for the model's behavior, as Kimi K2 Thinking uses a default temperature of 1.0.

Fix it with Roo Code or mention @roomote and request a fix.

"minimax.minimax-m2": {
maxTokens: 16_384,
contextWindow: 196_608,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
defaultToolProtocol: "native",
preserveReasoning: true,
inputPrice: 0.3,
outputPrice: 1.2,
description: "MiniMax M2 (230B parameter MoE model with 10B active parameters)",
},
"qwen.qwen3-next-80b-a3b": {
maxTokens: 8192,
contextWindow: 262_144,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
defaultToolProtocol: "native",
inputPrice: 0.15,
outputPrice: 1.2,
description: "Qwen3 Next 80B (MoE model with 3B active parameters)",
},
"qwen.qwen3-coder-480b-a35b-v1:0": {
maxTokens: 8192,
contextWindow: 262_144,
supportsImages: false,
supportsPromptCache: false,
supportsNativeTools: true,
defaultToolProtocol: "native",
inputPrice: 0.45,
outputPrice: 1.8,
description: "Qwen3 Coder 480B (MoE model with 35B active parameters)",
},
} as const satisfies Record<string, ModelInfo>

export const BEDROCK_DEFAULT_TEMPERATURE = 0.3
Expand Down
Loading