docs: clarify openai usage normalization

docs/concepts/model-providers.md

@@ -107,7 +107,8 @@ Current bundled examples:
   fetching
 - `openai`: GPT-5.4 forward-compat fallback, direct OpenAI transport
   normalization, Codex-aware missing-auth hints, Spark suppression, synthetic
-  OpenAI/Codex catalog rows, thinking/live-model policy, and
+  OpenAI/Codex catalog rows, thinking/live-model policy, usage-token alias
+  normalization (`input` / `output` and `prompt` / `completion` families), and
   provider-family metadata
 - `google` and `google-gemini-cli`: Gemini 3.1 forward-compat fallback and
   modern-model matching; Gemini CLI OAuth also owns auth-profile token

docs/gateway/openresponses-http-api.md

@@ -278,6 +278,9 @@ Event types currently emitted:
 ## Usage
 
 `usage` is populated when the underlying provider reports token counts.
+OpenClaw normalizes common OpenAI-style aliases before those counters reach
+downstream status/session surfaces, including `input_tokens` / `output_tokens`
+and `prompt_tokens` / `completion_tokens`.
 
 ## Errors
 

docs/providers/openai.md

@@ -198,6 +198,12 @@ OpenAI Responses), OpenClaw also attaches stable session and turn identity state
 to requests so retries, reconnects, and SSE fallback stay aligned to the same
 conversation identity.
 
+OpenClaw also normalizes OpenAI usage counters across transport variants before
+they reach session/status surfaces. Native OpenAI/Codex Responses traffic may
+report usage as either `input_tokens` / `output_tokens` or
+`prompt_tokens` / `completion_tokens`; OpenClaw treats those as the same input
+and output counters for `/status`, `/usage`, and session logs.
+
 You can set `agents.defaults.models.<provider/model>.params.transport`:
 
 - `"sse"`: force SSE

docs/reference/token-use.md

@@ -61,6 +61,11 @@ Other surfaces:
 - **CLI:** `openclaw status --usage` and `openclaw channels list` show
   normalized provider quota windows (`X% left`, not per-response costs).
 
+Usage surfaces normalize common provider-native field aliases before display.
+For OpenAI-family Responses traffic, that includes both `input_tokens` /
+`output_tokens` and `prompt_tokens` / `completion_tokens`, so transport-specific
+field names do not change `/status`, `/usage`, or session summaries.
+
 ## Cost estimation (when shown)
 
 Costs are estimated from your model pricing config: