diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md
index 6813c6ad4..21e4b0745 100644
--- a/packages/ai/CHANGELOG.md
+++ b/packages/ai/CHANGELOG.md
@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Fixed
+
+- Fixed OpenCode Go DeepSeek V4 thinking-off requests to send the provider's `thinking: { type: "disabled" }` compatibility parameter.
+
 ## [0.79.5] - 2026-06-16
 
 ### Added
diff --git a/packages/ai/scripts/generate-models.ts b/packages/ai/scripts/generate-models.ts
index 7f4f9cf00..3d75a82eb 100644
--- a/packages/ai/scripts/generate-models.ts
+++ b/packages/ai/scripts/generate-models.ts
@@ -1852,10 +1852,7 @@ async function generateModels() {
 
 	for (const candidate of allModels) {
 		if (candidate.api === "openai-completions" && candidate.id.includes("deepseek-v4")) {
-			const preservesNativeReasoningEffort =
-				candidate.provider === "openrouter" ||
-				candidate.provider === "opencode" ||
-				candidate.provider === "opencode-go";
+			const preservesNativeReasoningEffort = candidate.provider === "openrouter" || candidate.provider === "opencode";
 			candidate.compat = {
 				...candidate.compat,
 				...(preservesNativeReasoningEffort
diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts
index 564d92e34..11851721e 100644
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -8572,7 +8572,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "opencode-go",
 			baseUrl: "https://opencode.ai/zen/go/v1",
-			compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true},
+			compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
 			reasoning: true,
 			thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
 			input: ["text"],
@@ -8591,7 +8591,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "opencode-go",
 			baseUrl: "https://opencode.ai/zen/go/v1",
-			compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true},
+			compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
 			reasoning: true,
 			thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
 			input: ["text"],
@@ -9499,13 +9499,13 @@ export const MODELS = {
 			thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh"},
 			input: ["text"],
 			cost: {
-				input: 0.098,
-				output: 0.196,
+				input: 0.09,
+				output: 0.18,
 				cacheRead: 0.02,
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
-			maxTokens: 4096,
+			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
 		"deepseek/deepseek-v4-pro": {
 			id: "deepseek/deepseek-v4-pro",
@@ -10540,13 +10540,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.75,
+				input: 0.74,
 				output: 3.5,
-				cacheRead: 0.16,
+				cacheRead: 0.15,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262144,
+			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"nex-agi/nex-n2-pro:free": {
 			id: "nex-agi/nex-n2-pro:free",
@@ -12985,11 +12985,11 @@ export const MODELS = {
 			cost: {
 				input: 1.4,
 				output: 4.4,
-				cacheRead: 0.26,
+				cacheRead: 0.25,
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
-			maxTokens: 131072,
+			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"~anthropic/claude-fable-latest": {
 			id: "~anthropic/claude-fable-latest",