Skip to content

Add Ring 1T FP8 model to Chutes provider #8655

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
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add Ring 1T FP8 model to Chutes provider #8655

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
26 changes: 20 additions & 6 deletions packages/types/src/providers/chutes.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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"
Expand Down Expand Up @@ -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,
Expand All @@ -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,
Expand All @@ -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
Expand Down Expand Up @@ -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,
Expand Down Expand Up @@ -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 changes: 22 additions & 0 deletions src/api/providers/__tests__/chutes.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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 } }] })
Expand Down