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 
- Added inclusionAI/Ring-1T-FP8 to ChutesModelId type definition
- Added model configuration with pricing ($1.00/M input, $3.00/M output)
- Set appropriate context window (131072) and max tokens (32768)
- Model supports FP8 quantization for efficient inference

Fixes #8654
This commit is contained in:
Roo Code 2025-10-14 13:36:19 +00:00
parent 6b8c21f873
commit ade85c1282
1 changed files with 21 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
packages/types/src/providers/chutes.ts
View file

@ -40,6 +40,7 @@ export type ChutesModelId =
| "Qwen/Qwen3-Next-80B-A3B-Instruct"
| "Qwen/Qwen3-Next-80B-A3B-Thinking"
| "Qwen/Qwen3-VL-235B-A22B-Thinking"
| "inclusionAI/Ring-1T-FP8"
export const chutesDefaultModelId: ChutesModelId = "deepseek-ai/DeepSeek-R1-0528"
@ -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
@ -387,8 +391,19 @@ 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.",
},
"inclusionAI/Ring-1T-FP8": {
maxTokens: 32768,
contextWindow: 131072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 1.0,
outputPrice: 3.0,
description:
"Ring 1T FP8 model, a large language model optimized with FP8 quantization for efficient inference.",
},
} as const satisfies Record<string, ModelInfo>