scriptoriumadmin/Roo-Code
1
0
Fork 0
mirror of https://github.com/RooVetGit/Roo-Code.git synced 2026-08-28 05:27:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add Ring 1T FP8 model to Chutes provider

Browse source 
- Add inclusionAI/Ring-1T-FP8 to ChutesModelId type union
- Add model configuration with $1.0000 input and $3.0000 output pricing per million tokens
- Add comprehensive test case for the new model
- Resolves issue #8654
This commit is contained in:
Roo Code 2025-10-14 13:31:08 +00:00
parent 6b8c21f873
commit 19d7a38860
2 changed files with 42 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
packages/types/src/providers/chutes.ts
View file

@ -30,6 +30,7 @@ export type ChutesModelId =
| "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
| "microsoft/MAI-DS-R1-FP8"
| "tngtech/DeepSeek-R1T-Chimera"
| "inclusionAI/Ring-1T-FP8"
| "zai-org/GLM-4.5-Air"
| "zai-org/GLM-4.5-FP8"
| "zai-org/GLM-4.5-turbo"
@ -87,7 +88,8 @@ export const chutesModels = {
supportsPromptCache: false,
inputPrice: 0.23,
outputPrice: 0.9,
description: "DeepSeek‑V3.1‑Terminus is an update to V3.1 that improves language consistency by reducing CN/EN mix‑ups and eliminating random characters, while strengthening agent capabilities with notably better Code Agent and Search Agent performance.",
description:
"DeepSeek‑V3.1‑Terminus is an update to V3.1 that improves language consistency by reducing CN/EN mix‑ups and eliminating random characters, while strengthening agent capabilities with notably better Code Agent and Search Agent performance.",
},
"deepseek-ai/DeepSeek-V3.1-turbo": {
maxTokens: 32768,
@ -96,7 +98,8 @@ export const chutesModels = {
supportsPromptCache: false,
inputPrice: 1.0,
outputPrice: 3.0,
description: "DeepSeek-V3.1-turbo is an FP8, speculative-decoding turbo variant optimized for ultra-fast single-shot queries (~200 TPS), with outputs close to the originals and solid function calling/reasoning/structured output, priced at $1/M input and $3/M output tokens, using 2× quota per request and not intended for bulk workloads.",
description:
"DeepSeek-V3.1-turbo is an FP8, speculative-decoding turbo variant optimized for ultra-fast single-shot queries (~200 TPS), with outputs close to the originals and solid function calling/reasoning/structured output, priced at $1/M input and $3/M output tokens, using 2× quota per request and not intended for bulk workloads.",
},
"deepseek-ai/DeepSeek-V3.2-Exp": {
maxTokens: 163840,
@ -105,7 +108,8 @@ export const chutesModels = {
supportsPromptCache: false,
inputPrice: 0.25,
outputPrice: 0.35,
description: "DeepSeek-V3.2-Exp is an experimental LLM that introduces DeepSeek Sparse Attention to improve long‑context training and inference efficiency while maintaining performance comparable to V3.1‑Terminus.",
description:
"DeepSeek-V3.2-Exp is an experimental LLM that introduces DeepSeek Sparse Attention to improve long‑context training and inference efficiency while maintaining performance comparable to V3.1‑Terminus.",
},
"unsloth/Llama-3.3-70B-Instruct": {
maxTokens: 32768, // From Groq
@ -287,6 +291,15 @@ export const chutesModels = {
outputPrice: 0,
description: "TNGTech DeepSeek R1T Chimera model.",
},
"inclusionAI/Ring-1T-FP8": {
maxTokens: 32768,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 1.0,
outputPrice: 3.0,
description: "Ring 1T FP8 model optimized for efficient inference with FP8 precision.",
},
"zai-org/GLM-4.5-Air": {
maxTokens: 32768,
contextWindow: 151329,
@ -387,8 +400,9 @@ export const chutesModels = {
contextWindow: 262144,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 0.1600,
outputPrice: 0.6500,
description: "Qwen3‑VL‑235B‑A22B‑Thinking is an open‑weight MoE vision‑language model (235B total, ~22B activated) optimized for deliberate multi‑step reasoning with strong text‑image‑video understanding and long‑context capabilities.",
inputPrice: 0.16,
outputPrice: 0.65,
description:
"Qwen3‑VL‑235B‑A22B‑Thinking is an open‑weight MoE vision‑language model (235B total, ~22B activated) optimized for deliberate multi‑step reasoning with strong text‑image‑video understanding and long‑context capabilities.",
},
} as const satisfies Record<string, ModelInfo>

22
src/api/providers/__tests__/chutes.spec.ts
View file

@ -341,6 +341,28 @@ describe("ChutesHandler", () => {
)
})
it("should return inclusionAI/Ring-1T-FP8 model with correct configuration", () => {
const testModelId: ChutesModelId = "inclusionAI/Ring-1T-FP8"
const handlerWithModel = new ChutesHandler({
apiModelId: testModelId,
chutesApiKey: "test-chutes-api-key",
})
const model = handlerWithModel.getModel()
expect(model.id).toBe(testModelId)
expect(model.info).toEqual(
expect.objectContaining({
maxTokens: 32768,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 1.0,
outputPrice: 3.0,
description: "Ring 1T FP8 model optimized for efficient inference with FP8 precision.",
temperature: 0.5, // Default temperature for non-DeepSeek models
}),
)
})
it("completePrompt method should return text from Chutes API", async () => {
const expectedResponse = "This is a test response from Chutes"
mockCreate.mockResolvedValueOnce({ choices: [{ message: { content: expectedResponse } }] })