diff --git a/.changeset/stale-lizards-poke.md b/.changeset/stale-lizards-poke.md
new file mode 100644
index 0000000000..40e3308e8b
--- /dev/null
+++ b/.changeset/stale-lizards-poke.md
@@ -0,0 +1,5 @@
+---
+"claude-dev": minor
+---
+
+qwen platform adds deepseek-r1/v3 support
diff --git a/src/api/providers/qwen.ts b/src/api/providers/qwen.ts
index aa4138d09c..26ca03a898 100644
--- a/src/api/providers/qwen.ts
+++ b/src/api/providers/qwen.ts
@@ -4,6 +4,7 @@ import { ApiHandler } from "../"
 import { ApiHandlerOptions, QwenModelId, ModelInfo, qwenDefaultModelId, qwenModels } from "../../shared/api"
 import { convertToOpenAiMessages } from "../transform/openai-format"
 import { ApiStream } from "../transform/stream"
+import { convertToR1Format } from "../transform/r1-format"
 
 export class QwenHandler implements ApiHandler {
 	private options: ApiHandlerOptions
@@ -34,17 +35,21 @@ export class QwenHandler implements ApiHandler {
 
 	async *createMessage(systemPrompt: string, messages: Anthropic.Messages.MessageParam[]): ApiStream {
 		const model = this.getModel()
+		const isDeepseekReasoner = model.id.includes("deepseek-r1")
 		let openAiMessages: OpenAI.Chat.ChatCompletionMessageParam[] = [
 			{ role: "system", content: systemPrompt },
 			...convertToOpenAiMessages(messages),
 		]
-
+		if (isDeepseekReasoner) {
+			openAiMessages = convertToR1Format([{ role: "user", content: systemPrompt }, ...messages])
+		}
 		const stream = await this.client.chat.completions.create({
 			model: model.id,
 			max_completion_tokens: model.info.maxTokens,
 			messages: openAiMessages,
 			stream: true,
 			stream_options: { include_usage: true },
+			...(model.id === "deepseek-r1" ? {} : { temperature: 0 }),
 		})
 
 		for await (const chunk of stream) {
diff --git a/src/shared/api.ts b/src/shared/api.ts
index 748fb54e09..1297e6b155 100644
--- a/src/shared/api.ts
+++ b/src/shared/api.ts
@@ -529,6 +529,26 @@ export const qwenModels = {
 		cacheWritesPrice: 0.0056,
 		cacheReadsPrice: 0.0224,
 	},
+	"deepseek-v3": {
+		maxTokens: 8_000,
+		contextWindow: 64_000,
+		supportsImages: false,
+		supportsPromptCache: true,
+		inputPrice: 0,
+		outputPrice: 0.28,
+		cacheWritesPrice: 0.14,
+		cacheReadsPrice: 0.014,
+	},
+	"deepseek-r1": {
+		maxTokens: 8_000,
+		contextWindow: 64_000,
+		supportsImages: false,
+		supportsPromptCache: true,
+		inputPrice: 0,
+		outputPrice: 2.19,
+		cacheWritesPrice: 0.55,
+		cacheReadsPrice: 0.14,
+	},
 } as const satisfies Record<string, ModelInfo>
 
 // Mistral