Skip to content

feat(moonshot): implement provider with model picker, API fetching, streaming, and model metadata #857

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

Open
grizmin wants to merge 4 commits into
base: main
Choose a base branch
from
Open

feat(moonshot): implement provider with model picker, API fetching, streaming, and model metadata #857

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
204f81f
fix(moonshot): fix provider issues with model picker, refresh, and st…
grizmin Jul 7, 2026
e7aeef3
feat(moonshot): add missing models with correct pricing from official…
grizmin Jul 7, 2026
b54ddbf
Update webview-ui/src/components/settings/providers/Moonshot.tsx
grizmin Jul 7, 2026
686ae63
fix(moonshot): remove fallback pricing for unknown models to match ha…
grizmin Jul 7, 2026
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
1 change: 1 addition & 0 deletions packages/types/src/provider-settings.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,7 @@ export const dynamicProviders = [
"unbound",
"poe",
"deepseek",
"moonshot",
"opencode-go",
] as const

Expand Down
40 changes: 38 additions & 2 deletions packages/types/src/providers/moonshot.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,15 +56,51 @@ export const moonshotModels = {
"kimi-k2.5": {
maxTokens: 16_384,
contextWindow: 262_144,
supportsImages: false,
supportsImages: true, // Supports text, image, and video input
supportsPromptCache: true,
inputPrice: 0.6, // $0.60 per million tokens (cache miss)
outputPrice: 3.0, // $3.00 per million tokens
cacheReadsPrice: 0.1, // $0.10 per million tokens (cache hit)
supportsTemperature: true,
defaultTemperature: 1.0,
description:
"Kimi K2.5 is the latest generation of Moonshot AI's Kimi series, featuring improved reasoning capabilities and enhanced performance across diverse tasks.",
"Kimi K2.5 supports text, image, and video input, thinking and non-thinking modes, and dialogue and agent tasks. Context length 256k.",
},
"kimi-k2.6": {
maxTokens: 16_384,
contextWindow: 262_144,
supportsImages: true, // Native multimodal: text, image, video
supportsPromptCache: true,
inputPrice: 0.95, // $0.95 per million tokens (cache miss)
outputPrice: 4.0, // $4.00 per million tokens
cacheWritesPrice: 0, // $0 per million tokens (cache writes)
cacheReadsPrice: 0.16, // $0.16 per million tokens (cache hit)
description:
"Kimi K2.6 is Kimi's latest and most intelligent model with stronger long-term code writing capabilities, improved instruction compliance, and self-correction. Native multimodal architecture supporting text, image, and video input. Context length 256k.",
},
"kimi-k2.7-code": {
maxTokens: 16_384,
contextWindow: 262_144,
supportsImages: true, // Native multimodal: text, image, video
supportsPromptCache: true,
inputPrice: 0.95, // $0.95 per million tokens (cache miss)
outputPrice: 4.0, // $4.00 per million tokens
cacheWritesPrice: 0, // $0 per million tokens (cache writes)
cacheReadsPrice: 0.19, // $0.19 per million tokens (cache hit)
description:
"Kimi K2.7 Code is Kimi's most intelligent Coding model for higher success rates in long context programming tasks. Native multimodal architecture supporting text, image, and video input. Context length 256k.",
},
"kimi-k2.7-code-highspeed": {
maxTokens: 16_384,
contextWindow: 262_144,
supportsImages: true, // Native multimodal: text, image, video
supportsPromptCache: true,
inputPrice: 1.9, // $1.90 per million tokens (cache miss)
outputPrice: 8.0, // $8.00 per million tokens
cacheWritesPrice: 0, // $0 per million tokens (cache writes)
cacheReadsPrice: 0.38, // $0.38 per million tokens (cache hit)
description:
"Kimi K2.7 Code HighSpeed is the high-speed version of Kimi K2.7 Code with output speed of approximately 180 Tokens/s (up to 260 Tokens/s in short context). Same model architecture, faster output. Context length 256k.",
},
} as const satisfies Record<string, ModelInfo>

Expand Down
Loading
Loading