diff --git a/backend/crates/gateway-admin/src/model/observability.rs b/backend/crates/gateway-admin/src/model/observability.rs
index 5ec07c46c..719f0dc77 100644
--- a/backend/crates/gateway-admin/src/model/observability.rs
+++ b/backend/crates/gateway-admin/src/model/observability.rs
@@ -740,7 +740,6 @@ pub struct UsageListRecord {
     pub provider_account_authentication_kind: Option<String>,
     pub upstream_model_id: Option<String>,
     pub upstream_transport: Option<String>,
-    pub upstream_response_model: Option<String>,
     pub service_tier: Option<String>,
     pub input_tokens: Option<u64>,
     pub output_tokens: Option<u64>,
@@ -802,7 +801,6 @@ pub struct UsageRecord {
     pub upstream_transport: Option<String>,
     pub http_version: Option<String>,
     pub websocket_pool: Option<String>,
-    pub upstream_response_model: Option<String>,
     pub service_tier: Option<String>,
     /// Provider 已筛选的专有观测 JSON；管理领域保持不透明
     pub provider_metadata_json: Option<String>,
diff --git a/backend/crates/gateway-admin/tests/use_case/observability/mod.rs b/backend/crates/gateway-admin/tests/use_case/observability/mod.rs
index f55ad8dc9..4c4b02a46 100644
--- a/backend/crates/gateway-admin/tests/use_case/observability/mod.rs
+++ b/backend/crates/gateway-admin/tests/use_case/observability/mod.rs
@@ -1361,7 +1361,6 @@ fn total_record(
         provider_account_authentication_kind: None,
         upstream_model_id: Some("gpt-5.5".to_owned()),
         upstream_transport: None,
-        upstream_response_model: None,
         service_tier: None,
         input_tokens: Some(800),
         output_tokens: Some(200),
diff --git a/backend/crates/gateway-api/src/admin/observability/export/archive.rs b/backend/crates/gateway-api/src/admin/observability/export/archive.rs
index 20ce224a9..26b2582e0 100644
--- a/backend/crates/gateway-api/src/admin/observability/export/archive.rs
+++ b/backend/crates/gateway-api/src/admin/observability/export/archive.rs
@@ -28,13 +28,12 @@ pub(super) fn build(document: &Value) -> io::Result<Vec<u8>> {
         let detail = &evidence["detail"]["request"];
         writeln!(
             archive,
-            "\n结果：{}；状态码：{}；尝试数：{}\n模型：请求={}，发送={}，上游报告={}\n传输：{} → {}\n时延：{}",
+            "\n结果：{}；状态码：{}；尝试数：{}\n模型：请求={}，发送={}\n传输：{} → {}\n时延：{}",
             detail["logicalOutcome"],
             detail["statusCode"],
             detail["attemptCount"],
             detail["requestedModel"],
             detail["upstreamModel"],
-            detail["upstreamResponseModel"],
             detail["clientTransport"],
             detail["upstreamTransport"],
             detail["latencyDetails"]
diff --git a/backend/crates/gateway-api/src/admin/observability/presenter.rs b/backend/crates/gateway-api/src/admin/observability/presenter.rs
index fcb949803..e5ddedcd2 100644
--- a/backend/crates/gateway-api/src/admin/observability/presenter.rs
+++ b/backend/crates/gateway-api/src/admin/observability/presenter.rs
@@ -279,7 +279,6 @@ pub(crate) fn usage_list_record_view(
         model,
         requested_model: record.requested_model_id,
         upstream_model: record.upstream_model_id,
-        upstream_response_model: record.upstream_response_model,
         service_tier: record.service_tier,
         client_transport: record.client_transport,
         upstream_transport: record.upstream_transport,
@@ -377,7 +376,6 @@ pub(crate) fn usage_record_view(
         model,
         requested_model: record.requested_model_id,
         upstream_model: record.upstream_model_id,
-        upstream_response_model: record.upstream_response_model,
         service_tier: record.service_tier,
         status_code,
         client_transport: record.client_transport,
diff --git a/backend/crates/gateway-api/src/admin/observability/wire.rs b/backend/crates/gateway-api/src/admin/observability/wire.rs
index 4e4579374..8cabcc265 100644
--- a/backend/crates/gateway-api/src/admin/observability/wire.rs
+++ b/backend/crates/gateway-api/src/admin/observability/wire.rs
@@ -103,7 +103,6 @@ pub struct UsageListRecordView {
     pub model: Option<String>,
     pub requested_model: Option<String>,
     pub upstream_model: Option<String>,
-    pub upstream_response_model: Option<String>,
     pub service_tier: Option<String>,
     pub client_transport: String,
     pub upstream_transport: Option<String>,
@@ -142,7 +141,6 @@ pub struct UsageRecordView {
     pub model: Option<String>,
     pub requested_model: Option<String>,
     pub upstream_model: Option<String>,
-    pub upstream_response_model: Option<String>,
     pub service_tier: Option<String>,
     pub status_code: Option<i64>,
     pub client_transport: String,
diff --git a/backend/crates/gateway-api/tests/admin/observability/response.rs b/backend/crates/gateway-api/tests/admin/observability/response.rs
index 64a8a6d6f..738326453 100644
--- a/backend/crates/gateway-api/tests/admin/observability/response.rs
+++ b/backend/crates/gateway-api/tests/admin/observability/response.rs
@@ -764,7 +764,6 @@ pub(super) fn usage_record_with_account(
         upstream_transport: Some("http_sse".to_owned()),
         http_version: Some("h2".to_owned()),
         websocket_pool: None,
-        upstream_response_model: None,
         service_tier: None,
         provider_metadata_json: None,
         attempt_count: 1,
@@ -909,7 +908,6 @@ async fn usage_route_should_expose_table_facts_without_detail_payload() {
             provider_account_authentication_kind: Some("oauth".to_owned()),
             upstream_model_id: Some("grok-4.5".to_owned()),
             upstream_transport: Some("http_sse".to_owned()),
-            upstream_response_model: Some("grok-4.6-build".to_owned()),
             service_tier: Some("default".to_owned()),
             input_tokens: Some(1),
             output_tokens: Some(1),
@@ -1059,7 +1057,6 @@ async fn usage_route_should_expose_table_facts_without_detail_payload() {
             "imageOutputTokens": value["data"]["items"][0]["tokenDetails"]["imageOutputTokens"],
             "requestedModel": value["data"]["items"][0]["requestedModel"],
             "upstreamModel": value["data"]["items"][0]["upstreamModel"],
-            "upstreamResponseModel": value["data"]["items"][0]["upstreamResponseModel"],
             "reasoningEffort": value["data"]["items"][0]["reasoningEffort"],
             "reasoningPreset": value["data"]["items"][0]["reasoningPreset"],
             "subagentKind": value["data"]["items"][0]["subagentKind"],
@@ -1083,7 +1080,6 @@ async fn usage_route_should_expose_table_facts_without_detail_payload() {
             "imageOutputTokens": 9,
             "requestedModel": "grok-4.5",
             "upstreamModel": "grok-4.5",
-            "upstreamResponseModel": "grok-4.6-build",
             "reasoningEffort": "max",
             "reasoningPreset": "ultra",
             "subagentKind": "worker",
diff --git a/backend/crates/gateway-api/tests/key_usage/fixtures.rs b/backend/crates/gateway-api/tests/key_usage/fixtures.rs
index 674bb6259..318c66f99 100644
--- a/backend/crates/gateway-api/tests/key_usage/fixtures.rs
+++ b/backend/crates/gateway-api/tests/key_usage/fixtures.rs
@@ -110,7 +110,6 @@ fn usage_record() -> UsageListRecord {
         provider_account_authentication_kind: Some("private-sentinel".to_owned()),
         upstream_model_id: Some("private-sentinel".to_owned()),
         upstream_transport: Some("websocket".to_owned()),
-        upstream_response_model: Some("private-sentinel".to_owned()),
         service_tier: Some("private-sentinel".to_owned()),
         input_tokens: Some(1000),
         output_tokens: Some(100),
diff --git a/backend/crates/gateway-core/src/engine/coordinator.rs b/backend/crates/gateway-core/src/engine/coordinator.rs
index 554f6edff..7ea88cfd1 100644
--- a/backend/crates/gateway-core/src/engine/coordinator.rs
+++ b/backend/crates/gateway-core/src/engine/coordinator.rs
@@ -2302,12 +2302,6 @@ where
             http_version,
             websocket_pool,
             service_tier,
-            upstream_response_model: self
-                .current
-                .as_ref()
-                .and_then(|current| current.response_observation.as_ref())
-                .and_then(ProviderResponseObservation::upstream_response_model)
-                .map(str::to_owned),
             provider_metadata_json,
             diagnostic_trace_json: self.trace.snapshot().map(|value| value.to_string()),
             error: None,
@@ -2490,12 +2484,6 @@ where
             http_version,
             websocket_pool,
             service_tier,
-            upstream_response_model: self
-                .current
-                .as_ref()
-                .and_then(|current| current.response_observation.as_ref())
-                .and_then(ProviderResponseObservation::upstream_response_model)
-                .map(str::to_owned),
             provider_metadata_json,
             diagnostic_trace_json: self.trace.snapshot().map(|value| value.to_string()),
             error: Some(finalization.error),
diff --git a/backend/crates/gateway-core/src/engine/mod.rs b/backend/crates/gateway-core/src/engine/mod.rs
index cabee6dc1..fc3386e36 100644
--- a/backend/crates/gateway-core/src/engine/mod.rs
+++ b/backend/crates/gateway-core/src/engine/mod.rs
@@ -1070,7 +1070,6 @@ pub struct ModelRequestFinalization {
     pub http_version: Option<String>,
     pub websocket_pool: Option<String>,
     pub service_tier: Option<String>,
-    pub upstream_response_model: Option<String>,
     /// Provider 已筛选的专有观测 JSON；Core 不解释字段
     pub provider_metadata_json: Option<String>,
     /// 请求全程的有界诊断快照，跨 Provider 与重试保留
diff --git a/backend/crates/gateway-core/src/engine/observation.rs b/backend/crates/gateway-core/src/engine/observation.rs
index d1a1d3b81..91c4c35f8 100644
--- a/backend/crates/gateway-core/src/engine/observation.rs
+++ b/backend/crates/gateway-core/src/engine/observation.rs
@@ -249,7 +249,6 @@ pub struct RequestObservation {
     provider: Option<ProviderKind>,
     account_id: Option<ProviderAccountId>,
     upstream_model: Option<crate::routing::UpstreamModelId>,
-    response_model: Option<String>,
     service_tier: Option<String>,
     outcome: RequestObservationOutcome,
     send_state: UpstreamSendState,
@@ -287,7 +286,6 @@ impl RequestObservation {
             provider: None,
             account_id: None,
             upstream_model: None,
-            response_model: None,
             service_tier: None,
             outcome,
             send_state,
@@ -341,11 +339,6 @@ impl RequestObservation {
         self.upstream_model.as_ref()
     }
 
-    #[must_use]
-    pub fn response_model(&self) -> Option<&str> {
-        self.response_model.as_deref()
-    }
-
     #[must_use]
     pub fn service_tier(&self) -> Option<&str> {
         self.service_tier.as_deref()
@@ -626,7 +619,6 @@ impl RequestObservationDispatch {
             outcome: RequestObservationOutcome::Rejected,
             account_id: None,
             upstream_model: None,
-            response_model: None,
             service_tier: None,
             send_state: UpstreamSendState::NotSent,
             attempt_count: 0,
@@ -699,7 +691,6 @@ impl RequestObservationDispatch {
             provider,
             account_id: attempt.map(|attempt| attempt.provider_account_id().clone()),
             upstream_model: attempt.and_then(|attempt| attempt.upstream_model().cloned()),
-            response_model: finalization.upstream_response_model.clone(),
             service_tier: finalization.service_tier.clone(),
             outcome,
             send_state: finalization.send_state,
diff --git a/backend/crates/gateway-core/src/event.rs b/backend/crates/gateway-core/src/event.rs
index fcf0fa920..d1b1ee268 100644
--- a/backend/crates/gateway-core/src/event.rs
+++ b/backend/crates/gateway-core/src/event.rs
@@ -624,7 +624,6 @@ pub struct ProviderResponseObservation {
     status_code: Option<u16>,
     request_id: Option<OpaqueUpstreamValue>,
     service_tier: Option<String>,
-    upstream_response_model: Option<String>,
     timings: ProviderResponseTimings,
     // 流式事件分别持有快照，共享不可变头集合，避免逐事件复制头名和集合
     client_headers: Arc<[ProviderResponseHeader]>,
@@ -641,7 +640,6 @@ impl ProviderResponseObservation {
             status_code: None,
             request_id: None,
             service_tier: None,
-            upstream_response_model: None,
             timings: ProviderResponseTimings::default(),
             client_headers: Arc::default(),
             provider_metadata: None,
@@ -697,21 +695,6 @@ impl ProviderResponseObservation {
         self
     }
 
-    /// 记录 Provider 从上游响应明确取得的模型，不改写发送模型或计费合同
-    #[must_use]
-    pub fn with_upstream_response_model_if_valid(mut self, model: &str) -> Self {
-        let model = model.trim();
-        if validate_text(model, 256, false, None).is_ok() {
-            self.upstream_response_model = Some(model.to_owned());
-        }
-        self
-    }
-
-    #[must_use]
-    pub fn upstream_response_model(&self) -> Option<&str> {
-        self.upstream_response_model.as_deref()
-    }
-
     #[must_use]
     pub const fn with_timings(mut self, timings: ProviderResponseTimings) -> Self {
         self.timings = timings;
diff --git a/backend/crates/gateway-core/tests/engine/coordinator.rs b/backend/crates/gateway-core/tests/engine/coordinator.rs
index c6ae3a7cb..a547d6ab4 100644
--- a/backend/crates/gateway-core/tests/engine/coordinator.rs
+++ b/backend/crates/gateway-core/tests/engine/coordinator.rs
@@ -491,7 +491,6 @@ struct FinalState {
     http_version: Option<String>,
     websocket_pool: Option<String>,
     service_tier: Option<String>,
-    upstream_response_model: Option<String>,
     upstream_request_id: Option<String>,
     upstream_status_code: Option<u16>,
     transport_decision_wait_ms: Option<u64>,
@@ -682,7 +681,6 @@ impl ExecutionStore for FakeStore {
                 http_version: finalization.http_version,
                 websocket_pool: finalization.websocket_pool,
                 service_tier: finalization.service_tier,
-                upstream_response_model: finalization.upstream_response_model,
                 upstream_request_id: finalization.upstream_request_id,
                 upstream_status_code: finalization.upstream_status_code,
                 transport_decision_wait_ms: finalization.timings.transport_decision_wait_ms,
@@ -1764,7 +1762,6 @@ fn response_observation_is_persisted_but_never_delivered() {
     .with_websocket_pool(WebSocketPoolKind::New)
     .with_status_code(200)
     .with_request_id(OpaqueUpstreamValue::new("upstream-observed"))
-    .with_upstream_response_model_if_valid("gpt-returned")
     .try_with_service_tier("priority")
     .expect("service tier")
     .with_timings(ProviderResponseTimings {
@@ -1804,10 +1801,6 @@ fn response_observation_is_persisted_but_never_delivered() {
     assert_eq!(finalization.http_version.as_deref(), Some("HTTP/2"));
     assert_eq!(finalization.websocket_pool.as_deref(), Some("new"));
     assert_eq!(finalization.service_tier.as_deref(), Some("priority"));
-    assert_eq!(
-        finalization.upstream_response_model.as_deref(),
-        Some("gpt-returned")
-    );
     assert_eq!(
         finalization.upstream_request_id.as_deref(),
         Some("upstream-observed")
@@ -2083,7 +2076,6 @@ fn discarded_attempt_observation_does_not_leak_into_retry_result() {
     .with_http_version(UpstreamHttpVersion::Http11)
     .with_status_code(503)
     .with_request_id(OpaqueUpstreamValue::new("discarded-request"))
-    .with_upstream_response_model_if_valid("discarded-model")
     .with_timings(ProviderResponseTimings {
         transport_decision_wait_ms: Some(7),
         connect_ms: Some(11),
@@ -2146,7 +2138,6 @@ fn discarded_attempt_observation_does_not_leak_into_retry_result() {
 
     let state = store.state.lock().expect("store lock");
     let finalization = &state.finalizations[0];
-    assert_eq!(finalization.upstream_response_model, None);
     let trace: Value =
         serde_json::from_str(finalization.diagnostic_trace_json.as_deref().unwrap()).unwrap();
     let events = trace["events"].as_array().unwrap();
diff --git a/backend/crates/gateway-core/tests/engine/execution/mod.rs b/backend/crates/gateway-core/tests/engine/execution/mod.rs
index e860704cf..3e57bbe8c 100644
--- a/backend/crates/gateway-core/tests/engine/execution/mod.rs
+++ b/backend/crates/gateway-core/tests/engine/execution/mod.rs
@@ -2282,7 +2282,6 @@ impl Provider for ObservationProvider {
                     gateway_core::event::ProviderResponseObservation::new(
                         UpstreamTransport::new("http_sse").unwrap(),
                     )
-                    .with_upstream_response_model_if_valid("gpt-reported")
                     .with_service_tier_if_valid("priority"),
                 );
                 Ok(ProviderStream::new(
@@ -2615,7 +2614,6 @@ fn final_observation_is_emitted_once_for_success_rejection_and_detached_cancella
                     .map(UpstreamModelId::as_str),
                 Some("gpt-start")
             );
-            assert_eq!(observations[0].response_model(), Some("gpt-reported"));
             assert_eq!(observations[0].service_tier(), Some("priority"));
             assert_eq!(
                 observations[0].outcome(),
diff --git a/backend/crates/gateway-plugin/runtime/src/adapter/observer.rs b/backend/crates/gateway-plugin/runtime/src/adapter/observer.rs
index 6aa31818f..8de3437fa 100644
--- a/backend/crates/gateway-plugin/runtime/src/adapter/observer.rs
+++ b/backend/crates/gateway-plugin/runtime/src/adapter/observer.rs
@@ -455,7 +455,6 @@ fn wire_observation(observation: &RequestObservation) -> RequestCompleted {
         upstream_model: observation
             .upstream_model()
             .map(|model| model.as_str().to_owned()),
-        response_model: observation.response_model().map(str::to_owned),
         service_tier: observation.service_tier().map(str::to_owned),
         requested_model: observation
             .requested_model()
diff --git a/backend/crates/gateway-plugin/runtime/src/adapter/upstream_adapter/observation.rs b/backend/crates/gateway-plugin/runtime/src/adapter/upstream_adapter/observation.rs
index 9549a1096..1676b1859 100644
--- a/backend/crates/gateway-plugin/runtime/src/adapter/upstream_adapter/observation.rs
+++ b/backend/crates/gateway-plugin/runtime/src/adapter/upstream_adapter/observation.rs
@@ -47,12 +47,6 @@ pub(super) fn merge(
             .try_with_service_tier(value)
             .map_err(|source| invalid(sent).with_source(source))?;
     }
-    if let Some(value) = update.upstream_response_model {
-        current = current.with_upstream_response_model_if_valid(&value);
-        if current.upstream_response_model() != Some(value.trim()) {
-            return Err(invalid(sent));
-        }
-    }
     if !update.client_headers.is_empty() {
         current = current.with_client_headers(
             update
diff --git a/backend/crates/gateway-plugin/runtime/src/callback/facts.rs b/backend/crates/gateway-plugin/runtime/src/callback/facts.rs
index d10929a9a..856a88b64 100644
--- a/backend/crates/gateway-plugin/runtime/src/callback/facts.rs
+++ b/backend/crates/gateway-plugin/runtime/src/callback/facts.rs
@@ -119,7 +119,6 @@ fn observation(value: &ProviderResponseObservation) -> facts::ResponseObservatio
         status_code: value.status_code(),
         request_id: value.request_id().map(|value| value.as_str().to_owned()),
         service_tier: value.service_tier().map(str::to_owned),
-        upstream_response_model: value.upstream_response_model().map(str::to_owned),
         timings: facts::ResponseTimings {
             transport_decision_wait_ms: timings.transport_decision_wait_ms,
             connect_ms: timings.connect_ms,
diff --git a/backend/crates/gateway-plugin/runtime/tests/generation/policy/facts/mod.rs b/backend/crates/gateway-plugin/runtime/tests/generation/policy/facts/mod.rs
index 5c9366196..e09db0542 100644
--- a/backend/crates/gateway-plugin/runtime/tests/generation/policy/facts/mod.rs
+++ b/backend/crates/gateway-plugin/runtime/tests/generation/policy/facts/mod.rs
@@ -189,7 +189,6 @@ async fn facts_are_readable_without_replacing_or_duplicating_the_original_execut
             .with_status_code(200)
             .with_request_id(OpaqueUpstreamValue::new("response-request-id"))
             .with_service_tier_if_valid("priority")
-            .with_upstream_response_model_if_valid("returned-model")
             .with_client_headers(vec![ProviderResponseHeader::new(
                 "set-cookie",
                 Bytes::from_static(b"fixture=secret"),
diff --git a/backend/crates/gateway-plugin/runtime/tests/generation/upstream_adapter.rs b/backend/crates/gateway-plugin/runtime/tests/generation/upstream_adapter.rs
index e4ac2e4b5..36553cbb7 100644
--- a/backend/crates/gateway-plugin/runtime/tests/generation/upstream_adapter.rs
+++ b/backend/crates/gateway-plugin/runtime/tests/generation/upstream_adapter.rs
@@ -667,7 +667,7 @@ async fn adapter_preserves_observation_updates_and_measures_only_real_output() {
         {"event":{"facts":[{"type":"started","id":"response-one","model":"native-model"},
             {"type":"content_added","index":0,"kind":"reasoning"}]},
          "observation":{"transport":"http_sse","http_version":"HTTP/2","status_code":200,
-            "request_id":"upstream-494","upstream_response_model":"real-model",
+            "request_id":"upstream-494",
             "client_headers":[{"name":"x-bytes","value":[255]},{"name":"x-bytes","value":[254]}],
             "provider_metadata":"{ \"future\": 1e3 }","timings":{"connect_ms":5,"headers_ms":8}}},
         {"event":{"facts":[{"type":"reasoning_delta","index":0,"text":""}]}},
@@ -711,7 +711,6 @@ async fn adapter_preserves_observation_updates_and_measures_only_real_output() {
     assert_eq!(last.status_code(), Some(200));
     assert_eq!(last.http_version().unwrap().as_str(), "HTTP/2");
     assert_eq!(last.request_id().unwrap().as_str(), "upstream-494");
-    assert_eq!(last.upstream_response_model(), Some("real-model"));
     assert_eq!(last.service_tier(), Some("priority"));
     assert_eq!(
         last.provider_metadata().unwrap().as_json(),
@@ -1359,7 +1358,7 @@ async fn cancelling_adapter_body_closes_pending_websocket_and_releases_selected_
 }
 
 #[tokio::test]
-async fn usage_without_response_model_still_uses_native_account_pricing() {
+async fn upstream_adapter_usage_uses_native_account_pricing() {
     let server = MockServer::start().await;
     Mock::given(method("POST"))
         .respond_with(ResponseTemplate::new(200).set_body_string("{}"))
diff --git a/backend/crates/gateway-plugin/sdk/src/call/model/facts.rs b/backend/crates/gateway-plugin/sdk/src/call/model/facts.rs
index 63e327672..8d238775d 100644
--- a/backend/crates/gateway-plugin/sdk/src/call/model/facts.rs
+++ b/backend/crates/gateway-plugin/sdk/src/call/model/facts.rs
@@ -72,7 +72,6 @@ pub struct ResponseObservation {
     pub status_code: Option<u16>,
     pub request_id: Option<String>,
     pub service_tier: Option<String>,
-    pub upstream_response_model: Option<String>,
     #[serde(default)]
     pub timings: ResponseTimings,
     #[serde(default)]
@@ -119,7 +118,6 @@ impl ResponseObservation {
             status_code: None,
             request_id: None,
             service_tier: None,
-            upstream_response_model: None,
             timings: ResponseTimings::default(),
             client_headers: Vec::new(),
             provider_metadata: None,
diff --git a/backend/crates/gateway-plugin/sdk/src/call/observation.rs b/backend/crates/gateway-plugin/sdk/src/call/observation.rs
index 658da10de..194d43b9a 100644
--- a/backend/crates/gateway-plugin/sdk/src/call/observation.rs
+++ b/backend/crates/gateway-plugin/sdk/src/call/observation.rs
@@ -187,9 +187,6 @@ pub struct RequestCompleted {
     /// 本次实际选中账号使用的上游模型，未进入上游时可能不存在
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub upstream_model: Option<String>,
-    /// 上游响应报告的模型，与请求中的模型名称分开保存
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub response_model: Option<String>,
     #[serde(default, skip_serializing_if = "Option::is_none")]
     pub service_tier: Option<String>,
     #[serde(default, skip_serializing_if = "Option::is_none")]
diff --git a/backend/crates/gateway-plugin/sdk/tests/call/observation.rs b/backend/crates/gateway-plugin/sdk/tests/call/observation.rs
index ce16cdfd4..0e4fdc430 100644
--- a/backend/crates/gateway-plugin/sdk/tests/call/observation.rs
+++ b/backend/crates/gateway-plugin/sdk/tests/call/observation.rs
@@ -64,7 +64,6 @@ fn observation() -> RequestCompleted {
         client_key_id: Some("key_fixture".into()),
         account_id: Some("acct_fixture".into()),
         upstream_model: Some("upstream-model".into()),
-        response_model: Some("reported-model".into()),
         service_tier: Some("default".into()),
         provider: None,
         completed_at_ms: 1234,
@@ -114,19 +113,12 @@ fn observation_exposes_selected_and_reported_facts_without_inventing_values() {
     assert_eq!(wire["client_key_id"], "key_fixture");
     assert_eq!(wire["account_id"], "acct_fixture");
     assert_eq!(wire["upstream_model"], "upstream-model");
-    assert_eq!(wire["response_model"], "reported-model");
     assert_eq!(wire["service_tier"], "default");
     request.account_id = None;
     request.upstream_model = None;
-    request.response_model = None;
     request.service_tier = None;
     let wire = serde_json::to_value(request).unwrap();
-    for field in [
-        "account_id",
-        "upstream_model",
-        "response_model",
-        "service_tier",
-    ] {
+    for field in ["account_id", "upstream_model", "service_tier"] {
         assert!(wire.get(field).is_none(), "unknown {field} must be omitted");
     }
 }
diff --git a/backend/crates/gateway-protocol/src/openai/events.rs b/backend/crates/gateway-protocol/src/openai/events.rs
index 18057f62d..845dc3363 100644
--- a/backend/crates/gateway-protocol/src/openai/events.rs
+++ b/backend/crates/gateway-protocol/src/openai/events.rs
@@ -1,4 +1,4 @@
-//! 从 OpenAI 事件与响应头提取模型、用量、额度和重试等待事实
+//! 从 OpenAI 事件与响应头提取用量、额度和重试等待事实
 
 use std::{collections::BTreeMap, time::Duration};
 
@@ -7,56 +7,6 @@ use serde_json::Value;
 
 use super::sse::{SseError, parse_sse_events};
 
-/// 单次 Responses 流明确声明的模型；终态优先，缺失时不使用请求模型补齐
-#[derive(Debug, Default)]
-pub struct ResponseModelObservation {
-    model: Option<String>,
-    terminal: bool,
-}
-
-impl ResponseModelObservation {
-    /// 从原始事件读取响应模型，避免工具转换或 canonical 兜底改写观测事实
-    pub fn observe(&mut self, event_type: Option<&str>, value: &Value) {
-        let terminal = matches!(
-            event_type,
-            Some(
-                "response.completed"
-                    | "response.done"
-                    | "response.incomplete"
-                    | "response.failed"
-                    | "response.cancelled"
-                    | "response.canceled"
-            )
-        );
-        if self.terminal || (self.model.is_some() && !terminal) {
-            return;
-        }
-        let Some(model) = value
-            .pointer("/response/model")
-            .and_then(Value::as_str)
-            .and_then(observed_model_name)
-        else {
-            return;
-        };
-        self.model = Some(model.to_owned());
-        self.terminal = terminal;
-    }
-
-    /// 返回原始响应声明，未声明时保持未知
-    #[must_use]
-    pub fn model(&self) -> Option<&str> {
-        self.model.as_deref()
-    }
-}
-
-/// 规范化可展示的上游模型名，非法值不影响响应交付
-#[must_use]
-pub fn observed_model_name(value: &str) -> Option<&str> {
-    let value = value.trim();
-    (!value.is_empty() && value.len() <= 256 && !value.chars().any(char::is_control))
-        .then_some(value)
-}
-
 /// 从 Codex/OpenAI usage 结构中提取出的标准化 token 用量
 #[derive(Debug, Clone, Copy, Default, PartialEq, Eq, Serialize, Deserialize)]
 #[serde(rename_all = "camelCase")]
diff --git a/backend/crates/gateway-protocol/tests/openai/events.rs b/backend/crates/gateway-protocol/tests/openai/events.rs
index 31b94a422..ec40e6493 100644
--- a/backend/crates/gateway-protocol/tests/openai/events.rs
+++ b/backend/crates/gateway-protocol/tests/openai/events.rs
@@ -7,50 +7,6 @@ use gateway_protocol::openai::events::{
 };
 use serde_json::json;
 
-#[test]
-fn response_model_observation_keeps_first_declaration_until_terminal() {
-    use gateway_protocol::openai::events::ResponseModelObservation;
-
-    let mut observed = ResponseModelObservation::default();
-    observed.observe(
-        Some("response.created"),
-        &json!({"response": {"model": " first "}}),
-    );
-    observed.observe(
-        Some("response.in_progress"),
-        &json!({"response": {"model": "intermediate"}}),
-    );
-    assert_eq!(observed.model(), Some("first"));
-    observed.observe(
-        Some("response.completed"),
-        &json!({"response": {"model": "final"}}),
-    );
-    observed.observe(
-        Some("response.in_progress"),
-        &json!({"response": {"model": "late"}}),
-    );
-    assert_eq!(observed.model(), Some("final"));
-    assert_eq!(ResponseModelObservation::default().model(), None);
-}
-
-#[test]
-fn response_model_observation_ignores_missing_and_invalid_values() {
-    use gateway_protocol::openai::events::ResponseModelObservation;
-
-    for response in [
-        json!({}),
-        json!({"model": null}),
-        json!({"model": 42}),
-        json!({"model": "  "}),
-        json!({"model": "a\nb"}),
-        json!({"model": "a".repeat(257)}),
-    ] {
-        let mut observed = ResponseModelObservation::default();
-        observed.observe(Some("response.completed"), &json!({"response": response}));
-        assert_eq!(observed.model(), None);
-    }
-}
-
 #[test]
 fn billable_usage_should_validate_cache_writes_totals_and_overflow() {
     for (raw, expected) in [
diff --git a/backend/crates/gateway-store/src/postgres/execution/mod.rs b/backend/crates/gateway-store/src/postgres/execution/mod.rs
index 4f13734ad..e44b4f7e0 100644
--- a/backend/crates/gateway-store/src/postgres/execution/mod.rs
+++ b/backend/crates/gateway-store/src/postgres/execution/mod.rs
@@ -248,7 +248,6 @@ pub struct ModelRequestFinalization {
     pub http_version: Option<String>,
     pub websocket_pool: Option<String>,
     pub service_tier: Option<String>,
-    pub upstream_response_model: Option<String>,
     pub provider_metadata_json: Option<Value>,
     pub diagnostic_trace_json: Option<Value>,
     pub error_kind: Option<String>,
@@ -314,12 +313,6 @@ impl ModelRequestFinalization {
                 return Err(invalid("service tier is invalid"));
             }
         }
-        if let Some(model) = self.upstream_response_model.as_deref() {
-            require_nonempty(ENTITY, "upstream_response_model", model)?;
-            if model.len() > 256 || model.chars().any(char::is_control) {
-                return Err(invalid("upstream response model is invalid"));
-            }
-        }
         if self
             .provider_metadata_json
             .as_ref()
@@ -1180,7 +1173,6 @@ impl ExecutionStore for PgExecutionStore {
                 http_version: finalization.http_version,
                 websocket_pool: finalization.websocket_pool,
                 service_tier: finalization.service_tier,
-                upstream_response_model: finalization.upstream_response_model,
                 provider_metadata_json,
                 diagnostic_trace_json: finalization
                     .diagnostic_trace_json
diff --git a/backend/crates/gateway-store/src/postgres/execution/request_observation.rs b/backend/crates/gateway-store/src/postgres/execution/request_observation.rs
index 676d42d7d..2eaa6ac16 100644
--- a/backend/crates/gateway-store/src/postgres/execution/request_observation.rs
+++ b/backend/crates/gateway-store/src/postgres/execution/request_observation.rs
@@ -21,8 +21,6 @@ pub(super) struct RequestObservation {
     #[serde(skip_serializing_if = "Option::is_none")]
     transport: Option<TransportObservation>,
     #[serde(skip_serializing_if = "Option::is_none")]
-    response: Option<ResponseObservation>,
-    #[serde(skip_serializing_if = "Option::is_none")]
     continuation: Option<ContinuationObservation>,
 }
 
@@ -146,13 +144,6 @@ struct ConnectionObservation {
     idle_ms: Option<u64>,
 }
 
-#[derive(Default, Serialize)]
-#[serde(rename_all = "camelCase")]
-struct ResponseObservation {
-    #[serde(skip_serializing_if = "Option::is_none")]
-    response_model: Option<String>,
-}
-
 #[derive(Default, Serialize)]
 #[serde(rename_all = "camelCase")]
 struct ContinuationObservation {
@@ -263,9 +254,6 @@ impl RequestObservation {
                         idle_ms: value.upstream_connection_idle_ms,
                     }),
             }),
-            response: Some(ResponseObservation {
-                response_model: value.upstream_response_model.clone(),
-            }),
             error: Some(ErrorObservation {
                 provider_error_code: value.provider_error_code.clone(),
                 message: value.error_message.clone(),
diff --git a/backend/crates/gateway-store/src/postgres/execution_buffer.rs b/backend/crates/gateway-store/src/postgres/execution_buffer.rs
index 3d2ff596e..0242c4713 100644
--- a/backend/crates/gateway-store/src/postgres/execution_buffer.rs
+++ b/backend/crates/gateway-store/src/postgres/execution_buffer.rs
@@ -849,7 +849,6 @@ impl ExecutionObservationWrite {
                     finalization.http_version.as_deref(),
                     finalization.websocket_pool.as_deref(),
                     finalization.service_tier.as_deref(),
-                    finalization.upstream_response_model.as_deref(),
                     finalization.provider_metadata_json.as_deref(),
                     finalization.diagnostic_trace_json.as_deref(),
                     finalization.provider_error_code.as_deref(),
diff --git a/backend/crates/gateway-store/src/postgres/observability/mapping.rs b/backend/crates/gateway-store/src/postgres/observability/mapping.rs
index adc96d1f2..8a4c3492e 100644
--- a/backend/crates/gateway-store/src/postgres/observability/mapping.rs
+++ b/backend/crates/gateway-store/src/postgres/observability/mapping.rs
@@ -329,7 +329,6 @@ pub(crate) fn usage_list_record_from_row(
         provider_account_authentication_kind: get(row, "provider_account_authentication_kind")?,
         upstream_model_id: get(row, "upstream_model_id")?,
         upstream_transport: get(row, "upstream_transport")?,
-        upstream_response_model: get(row, "upstream_response_model")?,
         service_tier: get(row, "service_tier")?,
         input_tokens: optional_unsigned(row, "input_tokens")?,
         output_tokens: optional_unsigned(row, "output_tokens")?,
@@ -404,7 +403,6 @@ pub(crate) fn usage_record_from_row(row: &sqlx::postgres::PgRow) -> StoreResult<
         upstream_transport: get(row, "upstream_transport")?,
         http_version: get(row, "http_version")?,
         websocket_pool: get(row, "websocket_pool")?,
-        upstream_response_model: get(row, "upstream_response_model")?,
         service_tier: get(row, "service_tier")?,
         provider_metadata_json: get::<Option<serde_json::Value>>(row, "provider_observation_json")?
             .map(|value| serde_json::to_string(&value))
diff --git a/backend/crates/gateway-store/src/postgres/observability/queries/usage.rs b/backend/crates/gateway-store/src/postgres/observability/queries/usage.rs
index 4ef32e36e..47c96ea5c 100644
--- a/backend/crates/gateway-store/src/postgres/observability/queries/usage.rs
+++ b/backend/crates/gateway-store/src/postgres/observability/queries/usage.rs
@@ -146,7 +146,7 @@ pub(crate) const USAGE_LIST_RECORD_SELECT: &str =
             mr.provider_account_plan_type_snapshot as provider_account_plan_type,
             mr.provider_account_authentication_kind_snapshot
               as provider_account_authentication_kind,
-            mr.upstream_model_id, mr.upstream_transport, mr.upstream_response_model, mr.service_tier,
+            mr.upstream_model_id, mr.upstream_transport, mr.service_tier,
             mr.input_tokens, mr.output_tokens, mr.cached_input_tokens, mr.cache_write_input_tokens,
             mr.reasoning_output_tokens, mr.image_input_tokens, mr.image_output_tokens,
             mr.total_tokens, mr.billing_snapshot_json, mr.cost_source, mr.cost_amount::text, mr.cost_currency,
@@ -171,7 +171,7 @@ pub(crate) const USAGE_RECORD_DETAIL_SELECT: &str =
             mr.provider_account_authentication_kind_snapshot
               as provider_account_authentication_kind,
             mr.upstream_model_id, mr.upstream_transport, mr.http_version, mr.websocket_pool,
-            mr.service_tier, mr.upstream_response_model, mr.provider_observation_json, mr.diagnostic_trace_json,
+            mr.service_tier, mr.provider_observation_json, mr.diagnostic_trace_json,
             mr.attempt_count, mr.upstream_send_state, mr.downstream_committed_at,
             mr.outcome, mr.client_status_code, mr.upstream_status_code,
             mr.client_response_id, mr.upstream_request_id, mr.upstream_response_id,
diff --git a/backend/crates/gateway-store/tests/postgres/execution/mod.rs b/backend/crates/gateway-store/tests/postgres/execution/mod.rs
index 2f67c66a2..548ed311e 100644
--- a/backend/crates/gateway-store/tests/postgres/execution/mod.rs
+++ b/backend/crates/gateway-store/tests/postgres/execution/mod.rs
@@ -407,7 +407,6 @@ async fn core_adapter_should_persist_calculated_cost_exactly() {
     finalization.downstream_committed_at = Some(std::time::SystemTime::now());
     finalization.websocket_pool = Some("reuse".to_owned());
     finalization.service_tier = Some("priority".to_owned());
-    finalization.upstream_response_model = Some("grok-4.6-build".to_owned());
     finalization.cost = CalculatedCost::from_usd_ticks(12_345)
         .expect("calculated cost")
         .into_estimate();
@@ -452,10 +451,6 @@ async fn core_adapter_should_persist_calculated_cost_exactly() {
         detail.request.upstream_model_id.as_deref(),
         Some("grok-4.5")
     );
-    assert_eq!(
-        detail.request.upstream_response_model.as_deref(),
-        Some("grok-4.6-build")
-    );
     let page = observation
         .list_usage_records(UsageRecordQuery {
             status: Default::default(),
@@ -471,10 +466,6 @@ async fn core_adapter_should_persist_calculated_cost_exactly() {
         .await
         .expect("request list");
     assert_eq!(page.items.len(), 1);
-    assert_eq!(
-        page.items[0].upstream_response_model.as_deref(),
-        Some("grok-4.6-build")
-    );
     database.close().await;
 }
 
@@ -668,7 +659,6 @@ fn successful_core_finalization(id: &str) -> CoreModelRequestFinalization {
         upstream_transport: Some("websocket".to_owned()),
         http_version: Some("HTTP/2".to_owned()),
         websocket_pool: None,
-        upstream_response_model: None,
         service_tier: None,
         provider_metadata_json: None,
         error: None,
@@ -1589,7 +1579,6 @@ pub(super) fn early_failure(request: &CoreNewModelRequest) -> CoreModelRequestFi
         upstream_transport: None,
         http_version: None,
         websocket_pool: None,
-        upstream_response_model: None,
         service_tier: None,
         provider_metadata_json: None,
         diagnostic_trace_json: trace.snapshot().map(|value| value.to_string()),
diff --git a/backend/crates/providers/openai/src/provider/execution.rs b/backend/crates/providers/openai/src/provider/execution.rs
index 07e21dc3b..055374672 100644
--- a/backend/crates/providers/openai/src/provider/execution.rs
+++ b/backend/crates/providers/openai/src/provider/execution.rs
@@ -966,7 +966,6 @@ pub(super) fn cold_response_stream(response: ColdResponse) -> EventStream {
         let mut decoder = CodexCanonicalDecoder::new(upstream_model.as_str())
             .with_trace(trace.clone())
             .with_pricing(context.pricing().get("openai").and_then(|models| models.get(upstream_model.as_str())).cloned())
-            .with_reported_model(response.response_metadata.effective_model.as_deref())
             .with_requested_service_tier(request.service_tier())
             .with_request_tool_pricing(upstream_model.as_str(), request.tools())
             .with_raw_sse_passthrough();
@@ -1025,7 +1024,6 @@ pub(super) fn cold_response_stream(response: ColdResponse) -> EventStream {
                         response_metadata_updates.as_ref(),
                         &mut session_capture,
                         &mut observation_state,
-                        &mut decoder,
                     )
                     .await;
                     let observation_event = if rate_limits_changed || metadata_merge.is_some()
@@ -1103,12 +1101,9 @@ pub(super) fn cold_response_stream(response: ColdResponse) -> EventStream {
                 response_metadata_updates.as_ref(),
                 &mut session_capture,
                 &mut observation_state,
-                &mut decoder,
             )
             .await;
             let metadata_changed = metadata_merge.unwrap_or(false);
-            let response_model_changed = observation_state
-                .observe_upstream_response_model(decoder.response_model());
             let service_tier_changed = observation_state
                 .observe_upstream_service_tier(decoder.response_service_tier());
             let terminal_failure = canonical_failure.map(|(error, semantic_output_seen)| {
@@ -1196,7 +1191,6 @@ pub(super) fn cold_response_stream(response: ColdResponse) -> EventStream {
                 }));
             }
             if (rate_limits_changed
-                || response_model_changed
                 || service_tier_changed
                 || timing_changed
                 || metadata_changed
@@ -1266,8 +1260,6 @@ pub(super) fn cold_response_stream(response: ColdResponse) -> EventStream {
             )
         });
         let timing_signals = decoder.take_timing_signals();
-        let response_model_changed = observation_state
-            .observe_upstream_response_model(decoder.response_model());
         let service_tier_changed = observation_state
             .observe_upstream_service_tier(decoder.response_service_tier());
         let output_timing_changed = observation_state
@@ -1302,7 +1294,6 @@ pub(super) fn cold_response_stream(response: ColdResponse) -> EventStream {
             response_metadata_updates.as_ref(),
             &mut session_capture,
             &mut observation_state,
-            &mut decoder,
         )
         .await
         .unwrap_or(false);
@@ -1328,8 +1319,7 @@ pub(super) fn cold_response_stream(response: ColdResponse) -> EventStream {
                 .observe_cyber_policy_success(cyber_policy_scope.as_ref())
                 .await;
         }
-        if (response_model_changed
-            || service_tier_changed
+        if (service_tier_changed
             || timing_changed
             || rate_limits_changed
             || metadata_changed
@@ -1371,26 +1361,10 @@ async fn merge_response_metadata_updates(
     updates: Option<&CodexResponseMetadataUpdates>,
     session_capture: &mut Option<OpenAiSessionCapture>,
     observation_state: &mut OpenAiResponseObservationState,
-    decoder: &mut CodexCanonicalDecoder,
 ) -> Option<bool> {
-    let updates = updates?;
-    let mut pending = updates.lock().await;
-    let turn_state = pending.turn_state.take();
-    let reported_model = pending.reported_model.clone();
-    drop(pending);
-    if turn_state.is_none() && reported_model.is_none() {
-        return None;
+    let turn_state = updates?.lock().await.turn_state.take()?;
+    if let Some(capture) = session_capture.as_mut() {
+        capture.turn_state = Some(turn_state.clone());
     }
-    let mut changed = false;
-    if let Some(turn_state) = turn_state {
-        if let Some(capture) = session_capture.as_mut() {
-            capture.turn_state = Some(turn_state.clone());
-        }
-        changed |= observation_state.merge_client_header("x-codex-turn-state", &turn_state);
-    }
-    if let Some(model) = reported_model {
-        decoder.observe_reported_model(&model);
-        changed |= observation_state.observe_upstream_response_model(decoder.response_model());
-    }
-    Some(changed)
+    Some(observation_state.merge_client_header("x-codex-turn-state", &turn_state))
 }
diff --git a/backend/crates/providers/openai/src/provider/observation.rs b/backend/crates/providers/openai/src/provider/observation.rs
index b00e785d9..8b2aeee79 100644
--- a/backend/crates/providers/openai/src/provider/observation.rs
+++ b/backend/crates/providers/openai/src/provider/observation.rs
@@ -33,7 +33,6 @@ pub(super) struct OpenAiResponseObservationState {
     stream: bool,
     requested_service_tier: Option<String>,
     upstream_service_tier: Option<String>,
-    upstream_response_model: Option<String>,
     rate_limit_headers: Vec<(String, String)>,
     timings: ProviderResponseTimings,
     terminal: Option<OpenAiResponseTerminal>,
@@ -80,7 +79,6 @@ impl OpenAiResponseObservationState {
             stream: request.stream(),
             requested_service_tier: normalize_service_tier(request.service_tier()),
             upstream_service_tier: None,
-            upstream_response_model: response.response_metadata.effective_model.clone(),
             rate_limit_headers: selected_observation_headers(&response.rate_limit_headers),
             timings: openai_response_timings(
                 &response.transport_metrics,
@@ -123,23 +121,9 @@ impl OpenAiResponseObservationState {
         if let Some(service_tier) = &self.requested_service_tier {
             observation = observation.with_service_tier_if_valid(service_tier.clone());
         }
-        if let Some(model) = &self.upstream_response_model {
-            observation = observation.with_upstream_response_model_if_valid(model);
-        }
         Some(observation)
     }
 
-    pub(super) fn observe_upstream_response_model(&mut self, model: Option<&str>) -> bool {
-        let Some(model) = model else {
-            return false;
-        };
-        if self.upstream_response_model.as_deref() == Some(model) {
-            return false;
-        }
-        self.upstream_response_model = Some(model.to_owned());
-        true
-    }
-
     pub(super) fn observe_stream_chunk(&mut self, chunk: &[u8], started_at: Instant) -> bool {
         if chunk.is_empty() {
             return false;
@@ -263,17 +247,6 @@ impl OpenAiResponseObservationState {
         {
             metadata.insert("websocketOpeningRequestId".to_owned(), json!(request_id));
         }
-        if let Some(model) = self
-            .response_metadata
-            .effective_model
-            .as_deref()
-            .filter(|model| !model.is_empty())
-        {
-            metadata.insert(
-                "upstreamReportedModel".to_owned(),
-                Value::String(model.to_owned()),
-            );
-        }
         metadata.insert(
             "modelsEtag".to_owned(),
             self.response_metadata
diff --git a/backend/crates/providers/openai/src/transport/canonical.rs b/backend/crates/providers/openai/src/transport/canonical.rs
index 533ba58ce..f1b209a42 100644
--- a/backend/crates/providers/openai/src/transport/canonical.rs
+++ b/backend/crates/providers/openai/src/transport/canonical.rs
@@ -14,10 +14,7 @@ use gateway_core::event::{
 };
 use gateway_core::metering::Usage;
 use gateway_core::upstream::UpstreamSendState;
-use gateway_protocol::openai::events::{
-    ResponseModelObservation, TokenUsage, billable_usage_is_complete, extract_usage,
-    observed_model_name,
-};
+use gateway_protocol::openai::events::{TokenUsage, billable_usage_is_complete, extract_usage};
 use gateway_protocol::openai::sse::{SseEvent, SseEventDecoder, SseFrame, sse_frame_is_done};
 use serde_json::Value;
 use thiserror::Error;
@@ -59,8 +56,6 @@ pub struct CodexCanonicalDecoder {
     response_service_tier: Option<String>,
     upstream_response_ms: Option<u64>,
     upstream_timing_metrics: ResponseTimingMetrics,
-    response_model: ResponseModelObservation,
-    reported_model: Option<String>,
     web_search_pricing: Option<WebSearchPricing>,
     timing_signals: ResponseEventSignals,
     raw_sse_passthrough: bool,
@@ -171,8 +166,6 @@ impl CodexCanonicalDecoder {
             response_service_tier: None,
             upstream_response_ms: None,
             upstream_timing_metrics: ResponseTimingMetrics::default(),
-            response_model: ResponseModelObservation::default(),
-            reported_model: None,
             web_search_pricing: None,
             pricing: None,
             timing_signals: ResponseEventSignals::default(),
@@ -288,28 +281,6 @@ impl CodexCanonicalDecoder {
         self.upstream_timing_metrics
     }
 
-    /// 真实 HTTP 响应头提供初始报告；流内请求级报告可覆盖它
-    #[must_use]
-    pub fn with_reported_model(mut self, model: Option<&str>) -> Self {
-        self.reported_model = model.and_then(observed_model_name).map(str::to_owned);
-        self
-    }
-
-    /// 接收 transport 已解析的内部 metadata 报告，内部帧无需交付客户端
-    pub(crate) fn observe_reported_model(&mut self, model: &str) {
-        if let Some(model) = observed_model_name(model) {
-            self.reported_model = Some(model.to_owned());
-        }
-    }
-
-    /// 官方服务端报告优先；缺少报告时仅使用正文明确声明，不使用请求兜底值
-    #[must_use]
-    pub fn response_model(&self) -> Option<&str> {
-        self.reported_model
-            .as_deref()
-            .or_else(|| self.response_model.model())
-    }
-
     fn decode(&mut self, events: Vec<SseEvent>) -> CodexCanonicalOutcome {
         let mut output = Vec::new();
         for event in events {
@@ -419,10 +390,6 @@ impl CodexCanonicalDecoder {
             }
         }
         self.observe_response_service_tier(&value);
-        self.response_model.observe(event_type, &value);
-        if let Some(model) = super::response_meta::reported_model_from_event(&value) {
-            self.reported_model = Some(model.to_owned());
-        }
         let signals = response_event_signals(event_type, &value);
         self.merge_timing_signals(signals);
         if matches!(event_type, Some("response.failed" | "error")) {
diff --git a/backend/crates/providers/openai/src/transport/response_meta.rs b/backend/crates/providers/openai/src/transport/response_meta.rs
index 4f64a01da..b260deb45 100644
--- a/backend/crates/providers/openai/src/transport/response_meta.rs
+++ b/backend/crates/providers/openai/src/transport/response_meta.rs
@@ -11,8 +11,6 @@ use super::diagnostics::CodexUpstreamDiagnostics;
 /// Codex Responses 上游响应元数据
 #[derive(Clone, Default, PartialEq, Eq)]
 pub struct CodexResponseMetadata {
-    /// 上游实际选用的模型
-    pub effective_model: Option<String>,
     /// 模型目录版本
     pub models_etag: Option<String>,
     /// 上游是否声明响应包含 reasoning
@@ -25,7 +23,6 @@ impl fmt::Debug for CodexResponseMetadata {
     fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
         formatter
             .debug_struct("CodexResponseMetadata")
-            .field("effective_model", &self.effective_model)
             .field("models_etag", &self.models_etag)
             .field("reasoning_included", &self.reasoning_included)
             .field("client_header_count", &self.client_headers.len())
@@ -119,37 +116,12 @@ fn observe_typed_response_header(metadata: &mut CodexResponseMetadata, name: &st
         return;
     }
     match name.trim().to_ascii_lowercase().as_str() {
-        "openai-model" | "x-openai-model" => {
-            metadata.effective_model =
-                gateway_protocol::openai::events::observed_model_name(value).map(str::to_owned)
-        }
         "x-models-etag" => metadata.models_etag = Some(value.to_string()),
         "x-reasoning-included" => metadata.reasoning_included = true,
         _ => {}
     }
 }
 
-/// 与官方 Codex 一致，优先读取 response.headers，再读取 WS metadata 的顶层 headers
-pub(super) fn reported_model_from_event(value: &serde_json::Value) -> Option<&str> {
-    [value.pointer("/response/headers"), value.get("headers")]
-        .into_iter()
-        .flatten()
-        .filter_map(serde_json::Value::as_object)
-        .find_map(|headers| {
-            headers.iter().find_map(|(name, value)| {
-                if !name.eq_ignore_ascii_case("openai-model")
-                    && !name.eq_ignore_ascii_case("x-openai-model")
-                {
-                    return None;
-                }
-                value
-                    .as_str()
-                    .or_else(|| value.as_array()?.first()?.as_str())
-                    .and_then(gateway_protocol::openai::events::observed_model_name)
-            })
-        })
-}
-
 fn filter_client_headers(
     headers: impl IntoIterator<Item = (String, Bytes)>,
 ) -> Vec<(String, Bytes)> {
diff --git a/backend/crates/providers/openai/src/transport/websocket/exchange/mod.rs b/backend/crates/providers/openai/src/transport/websocket/exchange/mod.rs
index 278fd1f01..50ce7b8b7 100644
--- a/backend/crates/providers/openai/src/transport/websocket/exchange/mod.rs
+++ b/backend/crates/providers/openai/src/transport/websocket/exchange/mod.rs
@@ -59,8 +59,6 @@ pub type CodexWebSocketRateLimitUpdates = Arc<Mutex<Vec<ParsedRateLimits>>>;
 pub struct CodexWebSocketResponseMetadataUpdate {
     /// 当前响应首次声明的会话续接状态
     pub turn_state: Option<String>,
-    /// 当前响应最新的服务端模型报告
-    pub reported_model: Option<String>,
 }
 
 pub type CodexWebSocketResponseMetadataUpdates = Arc<Mutex<CodexWebSocketResponseMetadataUpdate>>;
@@ -72,8 +70,7 @@ pub(super) fn reusable_websocket_metadata(
     metadata.set_cookie_headers.clear();
     metadata.rate_limit_headers.clear();
     metadata.turn_state = None;
-    // 模型报告属于上一轮请求，池中连接不能把它带到下一轮缺失报告的响应
-    metadata.response_metadata.effective_model = None;
+    // 请求级响应头不能随池中连接带到下一轮响应
     metadata
         .response_metadata
         .client_headers
diff --git a/backend/crates/providers/openai/src/transport/websocket/exchange/reducer.rs b/backend/crates/providers/openai/src/transport/websocket/exchange/reducer.rs
index 7735185d0..fca8d3b3f 100644
--- a/backend/crates/providers/openai/src/transport/websocket/exchange/reducer.rs
+++ b/backend/crates/providers/openai/src/transport/websocket/exchange/reducer.rs
@@ -62,9 +62,6 @@ pub(super) fn reduce_websocket_event(
         &mut metadata.response_metadata,
         websocket_metadata_headers(&value),
     );
-    if let Some(model) = response_meta::reported_model_from_event(&value) {
-        metadata.response_metadata.effective_model = Some(model.to_owned());
-    }
     let turn_state_update = websocket_metadata_turn_state(&value).and_then(|turn_state| {
         if metadata.turn_state.is_some() {
             return None;
diff --git a/backend/crates/providers/openai/src/transport/websocket/exchange/stream.rs b/backend/crates/providers/openai/src/transport/websocket/exchange/stream.rs
index 6da84fd67..6cf896ac9 100644
--- a/backend/crates/providers/openai/src/transport/websocket/exchange/stream.rs
+++ b/backend/crates/providers/openai/src/transport/websocket/exchange/stream.rs
@@ -75,7 +75,6 @@ pub(in crate::transport::websocket) fn stream_websocket_response(
     let rate_limit_updates_for_task = Arc::clone(&rate_limit_updates);
     let response_metadata_updates = Arc::new(Mutex::new(CodexWebSocketResponseMetadataUpdate {
         turn_state: metadata.turn_state.clone(),
-        reported_model: None,
     }));
     let response_metadata_updates_for_task = Arc::clone(&response_metadata_updates);
     let (tx, rx) = mpsc::channel(WEBSOCKET_STREAM_BUFFER);
@@ -306,9 +305,6 @@ async fn forward_websocket_response_stream(state: WebSocketStreamForwardState) {
                 pending.turn_state = Some(turn_state);
             }
         }
-        if let Some(model) = metadata.response_metadata.effective_model.as_ref() {
-            response_metadata_updates.lock().await.reported_model = Some(model.clone());
-        }
         let terminal = match reduced.action {
             ExchangeAction::RateLimits(rate_limits) => {
                 rate_limit_updates.lock().await.push(rate_limits);
diff --git a/backend/crates/providers/openai/tests/provider/contract/mod.rs b/backend/crates/providers/openai/tests/provider/contract/mod.rs
index 9882433fb..69c174fb7 100644
--- a/backend/crates/providers/openai/tests/provider/contract/mod.rs
+++ b/backend/crates/providers/openai/tests/provider/contract/mod.rs
@@ -618,7 +618,7 @@ async fn attempt_middleware_can_change_reasoning_before_native_encoding() {
 }
 
 #[tokio::test]
-async fn responses_bill_sent_model_and_observe_unpriced_response_without_rewriting_it() {
+async fn responses_bill_sent_model_and_preserve_returned_model() {
     let store = Arc::new(MemoryAccountStore::default());
     create_account(&store, "acct_provider_contract").await;
     let server = MockServer::start().await;
@@ -655,7 +655,6 @@ async fn responses_bill_sent_model_and_observe_unpriced_response_without_rewriti
         )
         .await
         .unwrap();
-    let mut observed = None;
     let mut returned = None;
     let mut costs = Vec::new();
     while let Some(event) = stream.next().await {
@@ -665,9 +664,6 @@ async fn responses_bill_sent_model_and_observe_unpriced_response_without_rewriti
                 costs.push(cost.total().amount().scaled());
             }
         }
-        if let Some(observation) = event.response_observation() {
-            observed = observation.upstream_response_model().map(str::to_owned);
-        }
         if let Some(wire) = event.wire_event()
             && wire.data().get("type").and_then(Value::as_str) == Some("response.completed")
         {
@@ -681,12 +677,11 @@ async fn responses_bill_sent_model_and_observe_unpriced_response_without_rewriti
     let requests = server.received_requests().await.expect("upstream requests");
     assert_eq!(captured_request_body(&requests[0])["model"], "gpt-5.4");
     assert_eq!(costs, vec![3_437_500]);
-    assert_eq!(observed.as_deref(), Some("gpt-6-sol"));
-    assert_eq!(returned, observed);
+    assert_eq!(returned.as_deref(), Some("gpt-6-sol"));
 }
 
 #[tokio::test]
-async fn websocket_bills_sent_model_and_observes_internal_model_report() {
+async fn websocket_bills_sent_model_and_preserves_response_metadata() {
     for metadata_type in ["response.metadata", "codex.response.metadata"] {
         let store = Arc::new(MemoryAccountStore::default());
         create_account(&store, "acct_provider_contract").await;
@@ -729,7 +724,6 @@ async fn websocket_bills_sent_model_and_observes_internal_model_report() {
             )
             .await
             .expect("provider stream");
-        let mut observed = None;
         let mut returned = None;
         let mut costs = Vec::new();
         while let Some(event) = stream.next().await {
@@ -739,9 +733,6 @@ async fn websocket_bills_sent_model_and_observes_internal_model_report() {
                     costs.push(cost.total().amount().scaled());
                 }
             }
-            if let Some(observation) = event.response_observation() {
-                observed = observation.upstream_response_model().map(str::to_owned);
-            }
             if let Some(wire) = event.wire_event()
                 && wire.data().get("type").and_then(Value::as_str) == Some("response.completed")
             {
@@ -754,11 +745,6 @@ async fn websocket_bills_sent_model_and_observes_internal_model_report() {
         }
         server.await.expect("server task");
         assert_eq!(costs, vec![3_437_500]);
-        assert_eq!(
-            observed.as_deref(),
-            Some("gpt-server-report"),
-            "{metadata_type}"
-        );
         assert_eq!(returned.as_deref(), Some("gpt-6-astra"));
     }
 }
@@ -4116,10 +4102,6 @@ async fn websocket_fast_path_miss_uses_http_and_keeps_background_preconnect() {
                     );
                 }
                 assert_eq!(metadata["upstreamStatus"], 200);
-                assert_eq!(
-                    metadata["upstreamReportedModel"],
-                    "gpt-reported-by-upstream"
-                );
                 assert!(metadata["requestSummary"].is_object());
                 assert!(metadata["upstreamTraceHeaders"].is_array());
                 first_decision = metadata
diff --git a/backend/crates/providers/openai/tests/transport/canonical.rs b/backend/crates/providers/openai/tests/transport/canonical.rs
index 169faf726..3df42dbbc 100644
--- a/backend/crates/providers/openai/tests/transport/canonical.rs
+++ b/backend/crates/providers/openai/tests/transport/canonical.rs
@@ -83,56 +83,6 @@ fn diagnostic_parse_failure_keeps_raw_passthrough_without_persisting_plaintext()
     assert!(!snapshot.to_string().contains("private-invalid-json"));
 }
 
-#[test]
-fn response_model_observation_prefers_reported_headers_without_changing_wire() {
-    for websocket in [false, true] {
-        let mut decoder = CodexCanonicalDecoder::new("requested")
-            .with_reported_model(Some("opening-model"))
-            .with_raw_sse_passthrough();
-        for (value, expected) in [
-            (
-                json!({"type":"response.created","response":{"id":"resp_model","model":"body-model"}}),
-                "opening-model",
-            ),
-            (
-                json!({"type":"codex.response.metadata","headers":{"X-OpenAI-Model":["metadata-model"]}}),
-                "metadata-model",
-            ),
-            (
-                json!({"type":"response.completed","headers":{"openai-model":"top-level"},"response":{"id":"resp_model","model":"final-body-model","headers":{"OpenAI-Model":"terminal-model"}}}),
-                "terminal-model",
-            ),
-        ] {
-            let raw = value.to_string();
-            let frame = if websocket {
-                websocket_event_to_sse_frame(&raw).expect("WS event")
-            } else {
-                format!("data: {raw}\n\n")
-            };
-            let events = decoder
-                .push(frame.as_bytes())
-                .expect("decode model observation");
-            assert_eq!(decoder.response_model(), Some(expected));
-            assert!(
-                events
-                    .iter()
-                    .any(|event| event.wire_event().is_some_and(|wire| wire.data() == &value))
-            );
-        }
-    }
-}
-
-#[test]
-fn response_model_observation_uses_explicit_body_and_never_request_fallback() {
-    let mut decoder = CodexCanonicalDecoder::new("requested");
-    decoder
-        .push(b"data: {\"type\":\"response.created\",\"response\":{\"id\":\"resp_model\"}}\n\n")
-        .expect("response model event");
-    assert_eq!(decoder.response_model(), None);
-    decoder.push(b"data: {\"type\":\"response.completed\",\"response\":{\"id\":\"resp_model\",\"model\":\"returned\"}}\n\n").expect("response model event");
-    assert_eq!(decoder.response_model(), Some("returned"));
-}
-
 const METADATA_PREFIX_FIXTURE: &str = include_str!("fixtures/metadata_only_prefix.sse");
 
 #[test]
@@ -475,7 +425,6 @@ fn decoder_should_bill_the_sent_model_independently_of_the_response_model() {
                 _ => None,
             });
         assert_eq!(cost, expected_cost, "{sent} -> {returned:?}");
-        assert_eq!(decoder.response_model(), returned);
         assert!(canonical_facts(&events).into_iter().any(|event| matches!(
             event,
             GatewayEvent::Completed(meta) if meta.model() == Some(returned.unwrap_or(sent))
diff --git a/backend/crates/providers/openai/tests/transport/http_client.rs b/backend/crates/providers/openai/tests/transport/http_client.rs
index f1b64917d..fa8cc4f0b 100644
--- a/backend/crates/providers/openai/tests/transport/http_client.rs
+++ b/backend/crates/providers/openai/tests/transport/http_client.rs
@@ -431,10 +431,6 @@ async fn codex_backend_client_should_capture_forwardable_response_metadata() {
         .await
         .expect("response should succeed");
 
-    assert_eq!(
-        response.response_metadata.effective_model.as_deref(),
-        Some("gpt-5.5-2026-07-01")
-    );
     assert_eq!(
         response.response_metadata.models_etag.as_deref(),
         Some("models-v2")
diff --git a/backend/crates/providers/openai/tests/transport/mod.rs b/backend/crates/providers/openai/tests/transport/mod.rs
index 4f7209b1b..5594fe1c9 100644
--- a/backend/crates/providers/openai/tests/transport/mod.rs
+++ b/backend/crates/providers/openai/tests/transport/mod.rs
@@ -180,7 +180,6 @@ struct CollectedBackendResponse {
     rate_limit_headers: Vec<(String, String)>,
     websocket_pool_decision: Option<WebSocketPoolDecision>,
     response_metadata: CodexResponseMetadata,
-    reported_model: Option<String>,
     transport_metrics: CodexTransportMetrics,
     connection_local_continuation: bool,
 }
@@ -286,11 +285,9 @@ async fn collect_backend_response(
             rate_limit_headers.extend(rate_limits_to_header_pairs(update));
         }
     }
-    let mut reported_model = response_metadata.effective_model.clone();
     if let Some(update) = response_metadata_updates {
         let update = update.lock().await;
         turn_state = update.turn_state.clone().or(turn_state);
-        reported_model = update.reported_model.clone().or(reported_model);
     }
     let body = String::from_utf8_lossy(&body_bytes).into_owned();
     let usage = extract_sse_usage(&body).map_err(CodexClientError::InvalidSse)?;
@@ -303,7 +300,6 @@ async fn collect_backend_response(
         rate_limit_headers,
         websocket_pool_decision,
         response_metadata,
-        reported_model,
         transport_metrics,
         connection_local_continuation,
     })
diff --git a/backend/crates/providers/openai/tests/transport/websocket/metadata.rs b/backend/crates/providers/openai/tests/transport/websocket/metadata.rs
index 0e0b5341c..320887d05 100644
--- a/backend/crates/providers/openai/tests/transport/websocket/metadata.rs
+++ b/backend/crates/providers/openai/tests/transport/websocket/metadata.rs
@@ -80,7 +80,6 @@ async fn reused_websocket_should_keep_response_metadata_scoped_to_each_exchange(
         .expect("response within timeout")
         .expect("response should complete on the same socket");
         assert_eq!(response.response_metadata, expected, "exchange {round}");
-        assert_eq!(response.reported_model, Some(format!("model-{round}")));
         assert!(response.body.contains(&format!("etag-{round}")));
         assert_eq!(response.turn_state, Some(format!("turn-{round}")));
         if round > 0 {
diff --git a/backend/crates/providers/openai/tests/transport/websocket/mod.rs b/backend/crates/providers/openai/tests/transport/websocket/mod.rs
index c77af8cb8..ae5b89fcb 100644
--- a/backend/crates/providers/openai/tests/transport/websocket/mod.rs
+++ b/backend/crates/providers/openai/tests/transport/websocket/mod.rs
@@ -993,10 +993,6 @@ async fn websocket_execute_response_create_request_should_capture_internal_metad
     server.await.unwrap();
 
     assert_eq!(response.turn_state.as_deref(), Some("turn-from-metadata"));
-    assert_eq!(
-        response.reported_model.as_deref(),
-        Some("gpt-internal-report")
-    );
     assert!(!response.body.contains("codex.rate_limits"));
     assert!(response.body.contains("response.metadata"));
     assert!(response.body.contains("event: response.completed"));
@@ -1132,11 +1128,6 @@ async fn reused_websocket_should_not_leak_turn_state_into_the_next_response() {
             .websocket_pool_decision
             .is_some_and(WebSocketPoolDecision::is_reuse)
     );
-    assert_eq!(
-        first.reported_model.as_deref(),
-        Some("first-response-model")
-    );
-    assert_eq!(second.reported_model, None);
     assert_eq!(second.turn_state, None);
     assert!(
         second
diff --git a/backend/crates/providers/xai/src/provider/stream.rs b/backend/crates/providers/xai/src/provider/stream.rs
index 53664d298..5073ad7e3 100644
--- a/backend/crates/providers/xai/src/provider/stream.rs
+++ b/backend/crates/providers/xai/src/provider/stream.rs
@@ -322,10 +322,6 @@ pub(super) fn cold_compaction_http_sse_stream(
             }
         }
 
-        if let Some(model) = canonical.response_model() {
-            observation = observation.with_upstream_response_model_if_valid(model);
-            yield ProviderEvent::observation(observation.clone());
-        }
         if let Some(tier) = canonical.response_service_tier() {
             observation = observation.with_service_tier_if_valid(tier.to_owned());
             yield ProviderEvent::observation(observation);
@@ -606,12 +602,6 @@ pub(super) fn cold_http_sse_stream(
             if observe_output_timings(&mut observation, &events, context.timing_started_at()) {
                 yield ProviderEvent::observation(observation.clone());
             }
-            if let Some(model) = decoder.response_model()
-                && observation.upstream_response_model() != Some(model)
-            {
-                observation = observation.with_upstream_response_model_if_valid(model);
-                yield ProviderEvent::observation(observation.clone());
-            }
             if let Some(tier) = decoder.response_service_tier()
                 && observation.service_tier() != Some(tier)
             {
@@ -667,12 +657,6 @@ pub(super) fn cold_http_sse_stream(
             .iter()
             .flat_map(ProviderEvent::canonical_facts)
             .any(|event| matches!(event, GatewayEvent::Completed(_)));
-        if let Some(model) = decoder.response_model()
-            && observation.upstream_response_model() != Some(model)
-        {
-            observation = observation.with_upstream_response_model_if_valid(model);
-            yield ProviderEvent::observation(observation.clone());
-        }
         if let Some(tier) = decoder.response_service_tier()
             && observation.service_tier() != Some(tier)
         {
diff --git a/backend/crates/providers/xai/src/transport/canonical.rs b/backend/crates/providers/xai/src/transport/canonical.rs
index 9891e5ff0..9b9cfdd82 100644
--- a/backend/crates/providers/xai/src/transport/canonical.rs
+++ b/backend/crates/providers/xai/src/transport/canonical.rs
@@ -15,9 +15,7 @@ use gateway_core::metering::{
     CurrencyCode, Decimal, Money, ProviderReportedCost, Usage,
 };
 use gateway_core::upstream::UpstreamSendState;
-use gateway_protocol::openai::events::{
-    ResponseModelObservation, TokenUsage, billable_usage_is_complete, extract_usage,
-};
+use gateway_protocol::openai::events::{TokenUsage, billable_usage_is_complete, extract_usage};
 use gateway_protocol::openai::sse::{SseEvent, SseEventDecoder};
 use serde_json::Value;
 
@@ -295,7 +293,6 @@ pub struct GrokCanonicalDecoder {
     tool_arguments_seen: BTreeSet<u32>,
     usage_emitted: bool,
     response_service_tier: Option<String>,
-    response_model: ResponseModelObservation,
     requires_provider_cost: bool,
 }
 
@@ -372,7 +369,6 @@ impl GrokCanonicalDecoder {
             tool_arguments_seen: BTreeSet::new(),
             usage_emitted: false,
             response_service_tier: None,
-            response_model: ResponseModelObservation::default(),
             requires_provider_cost: false,
         }
     }
@@ -416,12 +412,6 @@ impl GrokCanonicalDecoder {
         self.response_service_tier.as_deref()
     }
 
-    /// 返回原始上游响应声明的模型，缺失时不使用请求模型补齐
-    #[must_use]
-    pub fn response_model(&self) -> Option<&str> {
-        self.response_model.model()
-    }
-
     pub fn push(&mut self, chunk: &[u8]) -> Result<Vec<ProviderEvent>, ProviderError> {
         let events = self.decoder.push(chunk).map_err(protocol_error)?;
         self.decode(events).map(|batch| batch.projected_events)
@@ -522,9 +512,6 @@ impl GrokCanonicalDecoder {
                 event.retry,
             )
             .map_err(|_| protocol_error_marker())?;
-            if !event_type.is_empty() {
-                self.response_model.observe(Some(&event_type), &value);
-            }
             // 工具转换可能隐藏注入的调用，计费事实必须从转换前的上游事件读取
             if let Some(response) = value.get("response") {
                 if let Some(tier) = response.get("service_tier").and_then(Value::as_str) {
diff --git a/backend/crates/providers/xai/tests/transport/canonical.rs b/backend/crates/providers/xai/tests/transport/canonical.rs
index d710d20f8..bc966c5fd 100644
--- a/backend/crates/providers/xai/tests/transport/canonical.rs
+++ b/backend/crates/providers/xai/tests/transport/canonical.rs
@@ -50,7 +50,6 @@ fn decoder_should_bill_the_sent_model_independently_of_the_response_model() {
             provider_cost_ticks(&facts),
             reported_cost.filter(|ticks| *ticks > 0)
         );
-        assert_eq!(decoder.response_model(), returned);
         assert!(facts.iter().any(|event| matches!(
             event,
             GatewayEvent::Completed(meta) if meta.model() == Some(returned.unwrap_or(sent))
@@ -58,18 +57,6 @@ fn decoder_should_bill_the_sent_model_independently_of_the_response_model() {
     }
 }
 
-#[test]
-fn response_model_observation_preserves_raw_model_and_missing_values() {
-    for model in [None, Some("grok-4.6-build")] {
-        let mut decoder = GrokCanonicalDecoder::new("grok-4.6");
-        let body = serde_json::json!({"type":"response.created","response":{"id":"resp_model","model":model}});
-        decoder
-            .push(format!("data: {body}\n\n").as_bytes())
-            .expect("decode created");
-        assert_eq!(decoder.response_model(), model);
-    }
-}
-
 fn terminal_cost_events(
     model: &str,
     input_tokens: u64,
diff --git a/docs/api.md b/docs/api.md
index 624b892b2..a25c80408 100644
--- a/docs/api.md
+++ b/docs/api.md
@@ -2099,12 +2099,7 @@ Dashboard 返回原始 `asOf` 及 `asOfDisplay`，作为当前数据的查询锚
 详情不出现在 Key 用量接口和普通错误信封中；[诊断导出](#诊断与恢复关联)在服务端重新脱敏后包含已存详情。
 记录仍受异步观测写入与保留周期约束
 
-管理端请求列表与详情分别保留 `requestedModel`（客户端请求）、`upstreamModel`（网关发送）与
-`upstreamResponseModel`（上游返回）。返回模型缺失时为 `null`，不使用请求或映射模型补齐。
-OpenAI 优先采用服务端 `openai-model` / `x-openai-model` 报告（流内报告可覆盖初始响应头），
-没有报告时采用正文明确声明的 `response.model`；xAI 采用原始正文声明。正文模型以终态优先，
-缺少终态声明时保留首次声明。这些值仅表示上游报告，不作为模型真实性证明，也不参与路由、
-聚合或本地计价模型选择。没有保存上游模型报告的记录保持未知
+管理端请求列表与详情保留 `requestedModel`（客户端请求）与 `upstreamModel`（网关发送）
 
 请求明细的 `clientApiKeyName`、`accountName` 按字面量包含匹配请求保存的历史名称快照，区分大小写，
 不解析为 ID，也不依赖当前配置是否存在。`model` 按字面量包含匹配请求模型或上游模型，`%`、`_` 和 `\` 按普通字符处理
diff --git a/frontend/src/api/modules/usage.ts b/frontend/src/api/modules/usage.ts
index 7bd585d81..a48b00b23 100644
--- a/frontend/src/api/modules/usage.ts
+++ b/frontend/src/api/modules/usage.ts
@@ -98,7 +98,6 @@ export interface UsageListRecord {
   model: string | null
   requestedModel: string | null
   upstreamModel: string | null
-  upstreamResponseModel: string | null
   serviceTier: string | null
   clientTransport: string
   upstreamTransport: string | null
@@ -131,7 +130,6 @@ export interface UsageRecord {
   model: string | null
   requestedModel: string | null
   upstreamModel: string | null
-  upstreamResponseModel: string | null
   serviceTier: string | null
   statusCode: number | null
   clientTransport: string
diff --git a/frontend/src/components/AppLanguageMenu.vue b/frontend/src/components/AppLanguageMenu.vue
index 1b1b1e30e..c4d667757 100644
--- a/frontend/src/components/AppLanguageMenu.vue
+++ b/frontend/src/components/AppLanguageMenu.vue
@@ -2,7 +2,7 @@
 import type { IconButtonProps } from '@codex-proxy/ui'
 import type { Locale } from '@/i18n/locale'
 import { ZIconButton, ZMenuItem, ZPopover } from '@codex-proxy/ui'
-import { Check, Languages } from '@lucide/vue'
+import { Check, Languages, LoaderCircle } from '@lucide/vue'
 import chineseFlag from 'circle-flags/flags/cn.svg?url&no-inline'
 import englishFlag from 'circle-flags/flags/us.svg?url&no-inline'
 import { computed, shallowRef, useTemplateRef } from 'vue'
@@ -61,7 +61,8 @@ async function selectLocale(value: Locale, close: () => void) {
           v-for="option in localeOptions"
           :key="option.value"
           :aria-pressed="option.value === locale"
-          :loading="pendingLocale === option.value"
+          :disabled="pendingLocale === option.value"
+          :aria-busy="pendingLocale === option.value || undefined"
           class="aria-pressed:bg-cp-control-item-bg-active aria-pressed:text-cp-primary-text aria-pressed:hover:bg-cp-control-item-bg-active"
           @click="selectLocale(option.value, close)"
         >
@@ -70,7 +71,10 @@ async function selectLocale(value: Locale, close: () => void) {
           </template>
           <span class="flex items-center justify-between gap-3">
             <span :lang="option.value">{{ option.label }}</span>
-            <Check v-if="option.value === locale" class="size-4 shrink-0" aria-hidden="true" />
+            <span class="inline-grid size-4 shrink-0 place-items-center" aria-hidden="true">
+              <LoaderCircle v-if="pendingLocale === option.value" class="size-4 animate-spin motion-reduce:animate-none" />
+              <Check v-else-if="option.value === locale" class="size-4" />
+            </span>
           </span>
         </ZMenuItem>
       </div>
diff --git a/frontend/src/components/usage/UsageModelCell.vue b/frontend/src/components/usage/UsageModelCell.vue
index b79e14405..ae1bdfd72 100644
--- a/frontend/src/components/usage/UsageModelCell.vue
+++ b/frontend/src/components/usage/UsageModelCell.vue
@@ -24,19 +24,17 @@ const { t } = useI18n({ useScope: 'global' })
       {{ modelDisplay.primary }}
     </code>
     <div
-      v-for="route in modelDisplay.routes"
-      :key="route.kind"
+      v-if="modelDisplay.secondary"
       class="flex min-w-0 max-w-full items-center gap-1.25 text-cp-text-secondary"
-      :title="route.description"
+      :title="t('usage.status.mappedModel', { secondary: modelDisplay.secondary })"
     >
       <CornerDownRight
-        class="size-3.25 shrink-0"
-        :class="route.kind === 'returned' ? 'text-cp-orange-text' : 'text-cp-blue-text'"
+        class="size-3.25 shrink-0 text-cp-blue-text"
         stroke-width="2.4"
         aria-hidden="true"
       />
       <code class="block truncate font-mono text-cp-xs leading-none font-bold">
-        {{ route.model }}
+        {{ modelDisplay.secondary }}
       </code>
     </div>
   </div>
diff --git a/frontend/src/components/usage/shared/columns.ts b/frontend/src/components/usage/shared/columns.ts
index 88d5609ba..85e1a64c4 100644
--- a/frontend/src/components/usage/shared/columns.ts
+++ b/frontend/src/components/usage/shared/columns.ts
@@ -6,7 +6,7 @@ import { t } from '@/i18n'
 import { formatProviderLabel } from '@/utils/providers'
 
 export const usageDataColumns = computed(() => ([
-  { key: 'model', label: t('usage.fields.model'), kind: 'custom', size: 'xl' },
+  { key: 'model', label: t('usage.fields.model'), kind: 'custom', size: 'lg' },
   { key: 'reasoningEffort', label: t('usage.fields.reasoningEffort'), kind: 'status', size: 'md', align: 'left' },
   { key: 'route', label: t('usage.fields.endpoint'), kind: 'mono' },
   { key: 'upstreamTransport', label: t('usage.fields.upstream'), kind: 'status', size: 'md' },
diff --git a/frontend/src/components/usage/shared/presenter.ts b/frontend/src/components/usage/shared/presenter.ts
index c928dea7c..fdfb2b852 100644
--- a/frontend/src/components/usage/shared/presenter.ts
+++ b/frontend/src/components/usage/shared/presenter.ts
@@ -10,7 +10,7 @@ export type UsagePerformanceRecord = Pick<UsageCommonRecord, 'latencyDetails' |
   tokenDetails: Pick<UsageListRecord['tokenDetails'], 'outputTokens'> | null
 }
 
-export type UsageModelRecord = Pick<UsageCommonRecord, 'model'> & Partial<Pick<UsageCommonRecord, 'requestedModel' | 'upstreamModel' | 'upstreamResponseModel'>>
+export type UsageModelRecord = Pick<UsageCommonRecord, 'model'> & Partial<Pick<UsageCommonRecord, 'requestedModel' | 'upstreamModel'>>
 export type UsageReasoningRecord = Pick<UsageCommonRecord, 'reasoningEffort'> & Partial<Pick<UsageCommonRecord, 'reasoningPreset' | 'subagentKind'>>
 
 interface UsageTimingItem {
@@ -93,27 +93,7 @@ export function usageModelDisplay(record: UsageModelRecord) {
         ? storedModel
         : ''
 
-  const responseModel = record.upstreamResponseModel || ''
-  const returned = responseModel && responseModel !== primary ? responseModel : ''
-  const routes = []
-  if (secondary && secondary !== returned) {
-    routes.push({
-      model: secondary,
-      kind: 'mapped' as const,
-      description: t('usage.status.mappedModel', { secondary }),
-    })
-  }
-  if (returned) {
-    routes.push({
-      model: returned,
-      kind: 'returned' as const,
-      description: returned === secondary
-        ? t('usage.status.returnedModel', { returned })
-        : t('usage.status.returnedModelHelp', { returned }),
-    })
-  }
-
-  return { primary, secondary, routes }
+  return { primary, secondary }
 }
 
 export function usagePerformanceDetails(record: UsagePerformanceRecord) {
diff --git a/frontend/src/i18n/locales/en/usage.json b/frontend/src/i18n/locales/en/usage.json
index 9c7df9a0a..f0d4a3b89 100644
--- a/frontend/src/i18n/locales/en/usage.json
+++ b/frontend/src/i18n/locales/en/usage.json
@@ -82,6 +82,7 @@
       "reviewSubagentRequest": "Review subagent request"
     },
     "filters": {
+      "modelPlaceholder": "Filter by model",
       "error": "Error",
       "requestDetailType": "Request detail type",
       "label": "Usage record filters and actions",
@@ -127,8 +128,6 @@
     "future": "Future",
     "status": {
       "mappedModel": "Model sent upstream after gateway mapping: {secondary}",
-      "returnedModel": "Upstream response model: {returned} (matches the mapped request model)",
-      "returnedModelHelp": "Model returned by upstream: {returned}",
       "firstOutputWaiting": "First output",
       "reasoningToText": "Reasoning → Text",
       "firstOneIsOutputToText": "First output → Text",
@@ -168,6 +167,7 @@
       "requestsPerMinute": "RPM"
     },
     "header": {
+      "title": "Analytics",
       "currentKey": "Current key",
       "keyPrefix": "Key prefix",
       "keyConfiguration": "Key configuration",
@@ -201,8 +201,8 @@
       "clickRefreshAtTopToTryAgain": ", please click refresh at the top to try again",
       "description": "View usage, performance trends, and request errors",
       "dateRangeLabel": "Statistics date range, limited to the last 31 days",
-      "requestDetails": "Request details",
-      "recordsDescription": "Successful and failed request details",
+      "requestDetails": "Request log",
+      "recordsDescription": "Successful and failed request records",
       "failedToLoad": "Failed to load: {error}",
       "noRequestsMatchTheseFilters": "No requests match these filters",
       "viewErrorDetails": "View error details",
@@ -310,7 +310,6 @@
       "message": "Message",
       "upstreamTimeConsumption": "Upstream time consumption",
       "storageModel": "Storage model",
-      "upstreamReturnModel": "Upstream return model",
       "clientIp": "Client IP",
       "eventType": "Event type",
       "trySerialNumber": "Try serial number",
diff --git a/frontend/src/i18n/locales/zh-Hans/usage.json b/frontend/src/i18n/locales/zh-Hans/usage.json
index d0a626c28..e8327a7bf 100644
--- a/frontend/src/i18n/locales/zh-Hans/usage.json
+++ b/frontend/src/i18n/locales/zh-Hans/usage.json
@@ -82,6 +82,7 @@
       "reviewSubagentRequest": "Review 子代理请求"
     },
     "filters": {
+      "modelPlaceholder": "按模型筛选",
       "error": "错误",
       "requestDetailType": "请求明细类型",
       "label": "使用记录筛选与操作",
@@ -127,8 +128,6 @@
     "future": "未来",
     "status": {
       "mappedModel": "网关映射后发送给上游的模型：{secondary}",
-      "returnedModel": "上游返回模型：{returned}（与网关映射后发送的模型一致）",
-      "returnedModelHelp": "上游返回模型：{returned}",
       "firstOutputWaiting": "首个输出等待",
       "reasoningToText": "推理到正文",
       "firstOneIsOutputToText": "首个输出到正文",
@@ -168,6 +167,7 @@
       "requestsPerMinute": "RPM"
     },
     "header": {
+      "title": "使用统计",
       "currentKey": "当前密钥",
       "keyPrefix": "密钥前缀",
       "keyConfiguration": "密钥配置",
@@ -201,8 +201,8 @@
       "clickRefreshAtTopToTryAgain": "，请点击顶部刷新重试",
       "description": "查看请求用量、性能趋势与调用错误记录",
       "dateRangeLabel": "统计日期范围，仅可选择最近 31 天",
-      "requestDetails": "请求明细",
-      "recordsDescription": "成功请求与失败请求明细",
+      "requestDetails": "请求记录",
+      "recordsDescription": "成功请求与失败请求记录",
       "failedToLoad": "加载失败：{error}",
       "noRequestsMatchTheseFilters": "所选条件下暂无请求记录",
       "viewErrorDetails": "查看错误详情",
@@ -310,7 +310,6 @@
       "message": "消息",
       "upstreamTimeConsumption": "上游耗时",
       "storageModel": "存储模型",
-      "upstreamReturnModel": "上游返回模型",
       "clientIp": "客户端 IP",
       "eventType": "事件类型",
       "trySerialNumber": "尝试序号",
diff --git a/frontend/src/i18n/locales/zh-Hant/usage.json b/frontend/src/i18n/locales/zh-Hant/usage.json
index 663072b89..30b9d4217 100644
--- a/frontend/src/i18n/locales/zh-Hant/usage.json
+++ b/frontend/src/i18n/locales/zh-Hant/usage.json
@@ -82,6 +82,7 @@
       "reviewSubagentRequest": "Review 子代理請求"
     },
     "filters": {
+      "modelPlaceholder": "按模型篩選",
       "error": "錯誤",
       "requestDetailType": "請求明細類型",
       "label": "使用記錄篩選與操作",
@@ -127,8 +128,6 @@
     "future": "未來",
     "status": {
       "mappedModel": "網關映射後發送給上游的模型：{secondary}",
-      "returnedModel": "上游返回模型：{returned}（與網關映射後發送的模型一致）",
-      "returnedModelHelp": "上游返回模型：{returned}",
       "firstOutputWaiting": "首個輸出等待",
       "reasoningToText": "推理到正文",
       "firstOneIsOutputToText": "首個輸出到正文",
@@ -168,6 +167,7 @@
       "requestsPerMinute": "RPM"
     },
     "header": {
+      "title": "使用統計",
       "currentKey": "當前密鑰",
       "keyPrefix": "密鑰前綴",
       "keyConfiguration": "密鑰配置",
@@ -201,8 +201,8 @@
       "clickRefreshAtTopToTryAgain": "，請點擊頂部刷新重試",
       "description": "查看請求用量、性能趨勢與調用錯誤記錄",
       "dateRangeLabel": "統計日期範圍，僅可選擇最近 31 天",
-      "requestDetails": "請求明細",
-      "recordsDescription": "成功請求與失敗請求明細",
+      "requestDetails": "請求記錄",
+      "recordsDescription": "成功請求與失敗請求記錄",
       "failedToLoad": "加載失敗：{error}",
       "noRequestsMatchTheseFilters": "所選條件下暫無請求記錄",
       "viewErrorDetails": "查看錯誤詳情",
@@ -310,7 +310,6 @@
       "message": "消息",
       "upstreamTimeConsumption": "上游耗時",
       "storageModel": "存儲模型",
-      "upstreamReturnModel": "上游返回模型",
       "clientIp": "客戶端 IP",
       "eventType": "事件類型",
       "trySerialNumber": "嘗試序號",
diff --git a/frontend/src/layout/components/AppSidebar.vue b/frontend/src/layout/components/AppSidebar.vue
index a9bb59143..72e4e17f6 100644
--- a/frontend/src/layout/components/AppSidebar.vue
+++ b/frontend/src/layout/components/AppSidebar.vue
@@ -440,7 +440,7 @@ onBeforeUnmount(() => {
           </span>
           <template v-for="item in navItems" :key="item.label">
             <div v-if="item.path === '/plugins'" class="relative z-10 grid min-w-0">
-              <ZPopover trigger="hover" placement="right" role="tooltip" :disabled="!isCollapsed" :enterable="false" class="w-full">
+              <ZPopover trigger="hover" placement="right" role="tooltip" :show-after="800" :disabled="!isCollapsed" :enterable="false" class="w-full">
                 <template #reference="{ close }">
                   <button
                     type="button"
@@ -529,7 +529,7 @@ onBeforeUnmount(() => {
               </div>
             </div>
 
-            <ZPopover v-else trigger="hover" placement="right" role="tooltip" :disabled="!isCollapsed" :enterable="false" class="relative z-10 w-full">
+            <ZPopover v-else trigger="hover" placement="right" role="tooltip" :show-after="800" :disabled="!isCollapsed" :enterable="false" class="relative z-10 w-full">
               <template #reference="{ close }">
                 <button
                   type="button"
diff --git a/frontend/src/views/key-usage/components/KeyUsageHeader.vue b/frontend/src/views/key-usage/components/KeyUsageHeader.vue
index 793886aed..7cfdd7706 100644
--- a/frontend/src/views/key-usage/components/KeyUsageHeader.vue
+++ b/frontend/src/views/key-usage/components/KeyUsageHeader.vue
@@ -35,7 +35,7 @@ async function logout() {
 </script>
 
 <template>
-  <ZPageHeader :title="t('usage.usage')">
+  <ZPageHeader :title="t('usage.header.title')">
     <template #description>
       <span class="flex min-w-0 flex-wrap items-center gap-x-3 gap-y-1.5">
         <span class="min-w-0 truncate text-cp font-semibold text-cp-text" :title="name">
diff --git a/frontend/src/views/key-usage/index.vue b/frontend/src/views/key-usage/index.vue
index 28b46a4f8..0a8bd2542 100644
--- a/frontend/src/views/key-usage/index.vue
+++ b/frontend/src/views/key-usage/index.vue
@@ -28,14 +28,11 @@ const { showConfig, configKey, configuring, apiBaseUrl, openConfig, copyConfig }
           <KeyUsageHeader v-model:period="period" v-model:refresh-interval="refreshInterval" :name="overview?.key.name" :prefix="overview?.key.prefix" :refreshing="refreshing || overviewLoading" :configuring="configuring" @refresh="refresh" @configure="openConfig" />
           <div class="flex flex-wrap items-center justify-between gap-3">
             <span v-if="overview" class="text-cp-sm text-cp-text-tertiary">{{ t('usage.page.updated', { asOfDisplay: overview.asOfDisplay }) }}</span>
-            <div class="ml-auto flex w-full min-w-0 items-center gap-3 sm:w-md sm:flex-none">
-              <span id="key-usage-model-label" class="shrink-0 text-cp-sm text-cp-text-secondary">{{ t('usage.fields.model') }}</span>
-              <ZInput id="key-usage-model" v-model="model" class="min-w-0 flex-1" :placeholder="t('usage.filters.enterFilterValue')" aria-labelledby="key-usage-model-label" :maxlength="128">
-                <template #prefix>
-                  <Search class="size-4.5 text-cp-text-tertiary" />
-                </template>
-              </ZInput>
-            </div>
+            <ZInput id="key-usage-model" v-model="model" class="ml-auto w-full min-w-0 sm:w-md sm:flex-none" :placeholder="t('usage.filters.modelPlaceholder')" :aria-label="t('usage.filters.modelPlaceholder')" :maxlength="128">
+              <template #prefix>
+                <Search class="size-4.5 text-cp-text-tertiary" />
+              </template>
+            </ZInput>
           </div>
         </div>
         <p v-if="overviewError" role="alert" class="m-0 rounded-cp-lg bg-cp-error-container px-4 py-3 text-cp-sm text-cp-error-text">
diff --git a/frontend/src/views/theme/fixtures/dashboard.ts b/frontend/src/views/theme/fixtures/dashboard.ts
index 82d249039..a801bf013 100644
--- a/frontend/src/views/theme/fixtures/dashboard.ts
+++ b/frontend/src/views/theme/fixtures/dashboard.ts
@@ -121,7 +121,6 @@ function previewUsageRecord(options: PreviewUsageRecordOptions): UsageListRecord
     model: options.model,
     requestedModel: options.model,
     upstreamModel: options.model,
-    upstreamResponseModel: null,
     serviceTier: options.provider === 'openai' ? 'priority' : 'standard',
     clientTransport: options.clientTransport,
     upstreamTransport: options.upstreamTransport,
diff --git a/frontend/src/views/usage/components/UsageRecordDetailModal.vue b/frontend/src/views/usage/components/UsageRecordDetailModal.vue
index 2ee10efe5..ac26e3c55 100644
--- a/frontend/src/views/usage/components/UsageRecordDetailModal.vue
+++ b/frontend/src/views/usage/components/UsageRecordDetailModal.vue
@@ -85,7 +85,6 @@ const modelRouteItems = computed(() => [
     mono: true,
   },
   { label: t('usage.request.storageModel'), value: props.record?.model, mono: true },
-  { label: t('usage.request.upstreamReturnModel'), value: props.record?.upstreamResponseModel, mono: true },
 ])
 
 const clientUpstreamItems = computed(() => [