diff --git a/src/main/java/com/williamcallahan/javachat/service/OpenAIStreamingService.java b/src/main/java/com/williamcallahan/javachat/service/OpenAIStreamingService.java
index 3c93394..217d039 100644
--- a/src/main/java/com/williamcallahan/javachat/service/OpenAIStreamingService.java
+++ b/src/main/java/com/williamcallahan/javachat/service/OpenAIStreamingService.java
@@ -168,7 +168,6 @@ public Mono<StreamingResult> streamResponse(StructuredPrompt structuredPrompt, d
      * @return completion text from the first successful provider attempt
      */
     public Mono<String> complete(String prompt, double temperature) {
-        String truncatedPrompt = requestFactory.truncatePromptForCompletion(prompt);
         return Mono.<String>defer(() -> {
                     List<OpenAiProviderCandidate> availableProviders =
                             providerRoutingService.selectAvailableProviderCandidates(clientPrimary, clientSecondary);
@@ -185,7 +184,7 @@ public Mono<String> complete(String prompt, double temperature) {
                         RateLimitService.ApiProvider activeProvider = providerCandidate.provider();
 
                         ResponseCreateParams requestParameters =
-                                requestFactory.buildCompletionRequest(truncatedPrompt, temperature, activeProvider);
+                                requestFactory.buildCompletionRequest(prompt, temperature, activeProvider);
                         try {
                             log.info("[LLM] Complete started (providerId={})", activeProvider.ordinal());
                             RequestOptions requestOptions = RequestOptions.builder()
diff --git a/src/main/java/com/williamcallahan/javachat/service/OpenAiRequestFactory.java b/src/main/java/com/williamcallahan/javachat/service/OpenAiRequestFactory.java
index f331a24..aa353e1 100644
--- a/src/main/java/com/williamcallahan/javachat/service/OpenAiRequestFactory.java
+++ b/src/main/java/com/williamcallahan/javachat/service/OpenAiRequestFactory.java
@@ -114,7 +114,8 @@ public ResponseCreateParams buildCompletionRequest(
             String prompt, double temperature, RateLimitService.ApiProvider provider) {
         boolean useGitHubModels = provider == RateLimitService.ApiProvider.GITHUB_MODELS;
         String modelId = normalizedModelId(useGitHubModels);
-        return buildResponseParams(prompt, temperature, modelId);
+        String truncatedPrompt = truncatePromptForCompletion(prompt, modelId);
+        return buildResponseParams(truncatedPrompt, temperature, modelId);
     }
 
     /**
@@ -124,16 +125,29 @@ public ResponseCreateParams buildCompletionRequest(
      * @return original prompt when no truncation is required, otherwise a notice-prefixed prompt
      */
     public String truncatePromptForCompletion(String prompt) {
+        return truncatePromptForCompletion(prompt, RateLimitService.ApiProvider.OPENAI);
+    }
+
+    /**
+     * Truncates completion prompts to token limits for the selected provider's model.
+     *
+     * @param prompt full completion prompt
+     * @param provider provider chosen for this request attempt
+     * @return original prompt when no truncation is required, otherwise a notice-prefixed prompt
+     */
+    public String truncatePromptForCompletion(String prompt, RateLimitService.ApiProvider provider) {
+        boolean useGitHubModels = provider == RateLimitService.ApiProvider.GITHUB_MODELS;
+        String modelId = normalizedModelId(useGitHubModels);
+        return truncatePromptForCompletion(prompt, modelId);
+    }
+
+    private String truncatePromptForCompletion(String prompt, String modelId) {
         if (prompt == null || prompt.isEmpty()) {
             return prompt;
         }
 
-        String openaiModelId = normalizedModelId(false);
-        String githubModelId = normalizedModelId(true);
-        boolean gpt5Family = isGpt5Family(openaiModelId) || isGpt5Family(githubModelId);
-        boolean reasoningModel = gpt5Family
-                || canonicalModelName(openaiModelId).startsWith("o")
-                || canonicalModelName(githubModelId).startsWith("o");
+        boolean gpt5Family = isGpt5Family(modelId);
+        boolean reasoningModel = gpt5Family || canonicalModelName(modelId).startsWith("o");
 
         int tokenLimit = reasoningModel ? MAX_TOKENS_GPT5_INPUT : MAX_TOKENS_DEFAULT_INPUT;
         String truncatedPrompt = chunker.keepLastTokens(prompt, tokenLimit);
diff --git a/src/test/java/com/williamcallahan/javachat/service/OpenAiRequestFactoryTest.java b/src/test/java/com/williamcallahan/javachat/service/OpenAiRequestFactoryTest.java
index f1032af..643d6ec 100644
--- a/src/test/java/com/williamcallahan/javachat/service/OpenAiRequestFactoryTest.java
+++ b/src/test/java/com/williamcallahan/javachat/service/OpenAiRequestFactoryTest.java
@@ -48,4 +48,29 @@ void buildCompletionRequestRetainsQualifiedGitHubModelIdentifier() {
         assertTrue(responseCreateParams.maxOutputTokens().isEmpty());
         assertEquals(0.25, responseCreateParams.temperature().orElseThrow(), 0.000_001);
     }
+
+    @Test
+    void truncatePromptForCompletionUsesSelectedOpenAiModelLimit() {
+        OpenAiRequestFactory requestFactory =
+                new OpenAiRequestFactory(new Chunker(), new PromptTruncator(), "gpt-4o", "openai/gpt-5", "");
+        String prompt = "context ".repeat(8_000);
+
+        String truncatedPrompt =
+                requestFactory.truncatePromptForCompletion(prompt, RateLimitService.ApiProvider.OPENAI);
+
+        assertEquals(prompt, truncatedPrompt);
+    }
+
+    @Test
+    void truncatePromptForCompletionUsesSelectedGitHubModelsLimit() {
+        OpenAiRequestFactory requestFactory =
+                new OpenAiRequestFactory(new Chunker(), new PromptTruncator(), "gpt-4o", "gpt-5", "");
+        String prompt = "context ".repeat(8_000);
+
+        String truncatedPrompt =
+                requestFactory.truncatePromptForCompletion(prompt, RateLimitService.ApiProvider.GITHUB_MODELS);
+
+        assertTrue(truncatedPrompt.startsWith("[Context truncated due to GPT-5 8K input limit]"));
+        assertTrue(truncatedPrompt.length() < prompt.length());
+    }
 }