From 202115a41481393a3a21187d9218aae7f05cd227 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ra=C3=BAl=20Correia?= <19838093+raulcorreia7@users.noreply.github.com> Date: Sun, 5 Oct 2025 02:57:19 +0200 Subject: [PATCH] feature: add GLM-4.6-turbo model to Chutes provider. Adds the missing zai-org/GLM-4.6-turbo model to Chutes. Closes RooCodeInc#8515 --- packages/types/src/providers/chutes.ts | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/packages/types/src/providers/chutes.ts b/packages/types/src/providers/chutes.ts index c90e044570..a7c775a00a 100644 --- a/packages/types/src/providers/chutes.ts +++ b/packages/types/src/providers/chutes.ts @@ -34,6 +34,7 @@ export type ChutesModelId = | "zai-org/GLM-4.5-FP8" | "zai-org/GLM-4.5-turbo" | "zai-org/GLM-4.6-FP8" + | "zai-org/GLM-4.6-turbo" | "moonshotai/Kimi-K2-Instruct-75k" | "moonshotai/Kimi-K2-Instruct-0905" | "Qwen/Qwen3-235B-A22B-Thinking-2507" @@ -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 @@ -326,6 +330,15 @@ export const chutesModels = { description: "GLM-4.6 introduces major upgrades over GLM-4.5, including a longer 200K-token context window for complex tasks, stronger coding performance in benchmarks and real-world tools (such as Claude Code, Cline, Roo Code, and Kilo Code), improved reasoning with tool use during inference, more capable and efficient agent integration, and refined writing that better matches human style, readability, and natural role-play scenarios.", }, + "zai-org/GLM-4.6-turbo": { + maxTokens: 32768, + contextWindow: 202752, + supportsImages: false, + supportsPromptCache: false, + inputPrice: 0, + outputPrice: 0, + description: "GLM-4.6-turbo model with 200K+ token context window, optimized for fast inference.", + }, "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { maxTokens: 32768, contextWindow: 262144, @@ -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