Skip to content

feat: Add Kimi K2 0905 model to Groq, Moonshot, and Fireworks providers #7693

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 5, 2025
Merged

feat: Add Kimi K2 0905 model to Groq, Moonshot, and Fireworks providers #7693

Show file tree
Hide file tree
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: 13 additions & 1 deletion packages/types/src/providers/fireworks.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@ import type { ModelInfo } from "../model.js"

export type FireworksModelId =
| "accounts/fireworks/models/kimi-k2-instruct"
| "accounts/fireworks/models/kimi-k2-instruct-0905"
| "accounts/fireworks/models/qwen3-235b-a22b-instruct-2507"
| "accounts/fireworks/models/qwen3-coder-480b-a35b-instruct"
| "accounts/fireworks/models/deepseek-r1-0528"
Expand All @@ -12,9 +13,20 @@ export type FireworksModelId =
| "accounts/fireworks/models/gpt-oss-20b"
| "accounts/fireworks/models/gpt-oss-120b"

export const fireworksDefaultModelId: FireworksModelId = "accounts/fireworks/models/kimi-k2-instruct"
export const fireworksDefaultModelId: FireworksModelId = "accounts/fireworks/models/kimi-k2-instruct-0905"

export const fireworksModels = {
"accounts/fireworks/models/kimi-k2-instruct-0905": {
maxTokens: 16384,
contextWindow: 262144,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 0.6,
outputPrice: 2.5,
cacheReadsPrice: 0.15,
description:
"Kimi K2 model gets a new version update: Agentic coding: more accurate, better generalization across scaffolds. Frontend coding: improved aesthetics and functionalities on web, 3d, and other tasks. Context length: extended from 128k to 256k, providing better long-horizon support.",
},
"accounts/fireworks/models/kimi-k2-instruct": {
maxTokens: 16384,
contextWindow: 128000,
Expand Down
14 changes: 13 additions & 1 deletion packages/types/src/providers/groq.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,10 +11,11 @@ export type GroqModelId =
| "qwen/qwen3-32b"
| "deepseek-r1-distill-llama-70b"
| "moonshotai/kimi-k2-instruct"
| "moonshotai/kimi-k2-instruct-0905"
| "openai/gpt-oss-120b"
| "openai/gpt-oss-20b"

export const groqDefaultModelId: GroqModelId = "llama-3.3-70b-versatile" // Defaulting to Llama3 70B Versatile
export const groqDefaultModelId: GroqModelId = "moonshotai/kimi-k2-instruct-0905"

export const groqModels = {
// Models based on API response: https://api.groq.com/openai/v1/models
Expand Down Expand Up @@ -100,6 +101,17 @@ export const groqModels = {
cacheReadsPrice: 0.5, // 50% discount for cached input tokens
description: "Moonshot AI Kimi K2 Instruct 1T model, 128K context.",
},
"moonshotai/kimi-k2-instruct-0905": {
maxTokens: 16384,
contextWindow: 262144,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 0.6,
outputPrice: 2.5,
cacheReadsPrice: 0.15,
description:
"Kimi K2 model gets a new version update: Agentic coding: more accurate, better generalization across scaffolds. Frontend coding: improved aesthetics and functionalities on web, 3d, and other tasks. Context length: extended from 128k to 256k, providing better long-horizon support.",
},
"openai/gpt-oss-120b": {
maxTokens: 32766,
contextWindow: 131072,
Expand Down
14 changes: 7 additions & 7 deletions packages/types/src/providers/moonshot.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,15 +18,15 @@ export const moonshotModels = {
description: `Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters.`,
},
"kimi-k2-0905-preview": {
maxTokens: 32_000,
contextWindow: 262_144,
maxTokens: 16384,
contextWindow: 262144,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 0.6, // $0.60 per million tokens (cache miss)
outputPrice: 2.5, // $2.50 per million tokens
cacheWritesPrice: 0, // $0 per million tokens (cache miss)
cacheReadsPrice: 0.15, // $0.15 per million tokens (cache hit)
description: `Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters.`,
inputPrice: 0.6,
outputPrice: 2.5,
cacheReadsPrice: 0.15,
description:
"Kimi K2 model gets a new version update: Agentic coding: more accurate, better generalization across scaffolds. Frontend coding: improved aesthetics and functionalities on web, 3d, and other tasks. Context length: extended from 128k to 256k, providing better long-horizon support.",
},
"kimi-k2-turbo-preview": {
maxTokens: 32_000,
Expand Down
4 changes: 2 additions & 2 deletions src/api/providers/__tests__/moonshot.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,8 +148,8 @@ describe("MoonshotHandler", () => {
const model = handler.getModel()
expect(model.id).toBe(mockOptions.apiModelId)
expect(model.info).toBeDefined()
expect(model.info.maxTokens).toBe(32_000)
expect(model.info.contextWindow).toBe(262_144)
expect(model.info.maxTokens).toBe(16384)
expect(model.info.contextWindow).toBe(262144)
expect(model.info.supportsImages).toBe(false)
expect(model.info.supportsPromptCache).toBe(true) // Should be true now
})
Expand Down
Loading