retell-sdk 6.2.6 → 6.2.7

package/resources/call.d.ts

@@ -125,7 +125,8 @@ export declare class Call extends APIResource {
     /**
      * Take over an in-progress call from the AI agent. The agent stops responding and
      * the specified live-listen participant is allowed to speak directly to the
-     * caller. The call must be in ONGOING status.
+     * caller. The call must be in ONGOING status. Gateway calls cannot be taken over
+     * while a PCI session is active.
      *
      * @example
      * ```ts
@@ -5649,7 +5650,9 @@ export declare namespace CallCreatePhoneCallParams {
     interface AgentOverride {
         /**
          * Override agent configuration settings. Any properties specified here will
-         * override the base agent configuration for this call.
+         * override the base agent configuration for this call. If a Retell LLM or
+         * Conversation Flow response engine is specified without a version, it uses the
+         * latest version.
          */
         agent?: AgentOverride.Agent;
         /**
@@ -5662,7 +5665,7 @@ export declare namespace CallCreatePhoneCallParams {
         /**
          * Override Retell LLM configuration settings. Only applicable when using Retell
          * LLM as the response engine. Supported attributes - model, s2s_model,
-         * model_temperature, model_high_priority, tool_call_strict_mode,
+         * model_temperature, model_high_priority, model_ultrafast, tool_call_strict_mode,
          * knowledge_base_ids, kb_config, start_speaker, begin_after_user_silence_ms,
          * begin_message.
          */
@@ -5671,7 +5674,9 @@ export declare namespace CallCreatePhoneCallParams {
     namespace AgentOverride {
         /**
          * Override agent configuration settings. Any properties specified here will
-         * override the base agent configuration for this call.
+         * override the base agent configuration for this call. If a Retell LLM or
+         * Conversation Flow response engine is specified without a version, it uses the
+         * latest version.
          */
         interface Agent {
             /**
@@ -5908,7 +5913,7 @@ export declare namespace CallCreatePhoneCallParams {
             /**
              * The model to use for post call analysis. Default to gpt-5.6-terra.
              */
-            post_call_analysis_model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | null;
+            post_call_analysis_model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | 'gemini-4-argon' | null;
             /**
              * Integration (Agent Functions) tools run as a dependency graph during teardown,
              * after post-call analysis. Each tool can be gated by a condition. On calls the
@@ -7365,7 +7370,7 @@ export declare namespace CallCreatePhoneCallParams {
                 /**
                  * The LLM model to use
                  */
-                model: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash';
+                model: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | 'gemini-4-argon';
                 /**
                  * Type of model choice
                  */
@@ -7374,6 +7379,12 @@ export declare namespace CallCreatePhoneCallParams {
                  * Whether to use high priority pool with more dedicated resource, default false
                  */
                 high_priority?: boolean;
+                /**
+                 * Whether to use the ultrafast tier for much faster response generation, default
+                 * false. Only supported by gpt-6.1-sol on voice agents; ignored otherwise. Takes
+                 * precedence over high_priority.
+                 */
+                ultrafast?: boolean;
             }
             interface ModelChoiceS2S {
                 /**
@@ -7389,7 +7400,7 @@ export declare namespace CallCreatePhoneCallParams {
         /**
          * Override Retell LLM configuration settings. Only applicable when using Retell
          * LLM as the response engine. Supported attributes - model, s2s_model,
-         * model_temperature, model_high_priority, tool_call_strict_mode,
+         * model_temperature, model_high_priority, model_ultrafast, tool_call_strict_mode,
          * knowledge_base_ids, kb_config, start_speaker, begin_after_user_silence_ms,
          * begin_message.
          */
@@ -7417,7 +7428,7 @@ export declare namespace CallCreatePhoneCallParams {
             /**
              * Select the underlying text LLM. If not set, would default to gpt-5.6-terra.
              */
-            model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | null;
+            model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | 'gemini-4-argon' | null;
             /**
              * If set to true, will use high priority pool with more dedicated resource to
              * ensure lower and more consistent latency, default to false. This feature usually
@@ -7431,6 +7442,13 @@ export declare namespace CallCreatePhoneCallParams {
              * recommended.
              */
             model_temperature?: number;
+            /**
+             * If set to true, will use the ultrafast tier for much faster response generation,
+             * default to false. Only supported by gpt-6.1-sol on voice agents; ignored
+             * otherwise. Takes precedence over model_high_priority. This feature comes with a
+             * higher cost.
+             */
+            model_ultrafast?: boolean | null;
             /**
              * Select the underlying speech to speech model. Can only set this or model, not
              * both.
@@ -7516,7 +7534,9 @@ export declare namespace CallCreateWebCallParams {
     interface AgentOverride {
         /**
          * Override agent configuration settings. Any properties specified here will
-         * override the base agent configuration for this call.
+         * override the base agent configuration for this call. If a Retell LLM or
+         * Conversation Flow response engine is specified without a version, it uses the
+         * latest version.
          */
         agent?: AgentOverride.Agent;
         /**
@@ -7529,7 +7549,7 @@ export declare namespace CallCreateWebCallParams {
         /**
          * Override Retell LLM configuration settings. Only applicable when using Retell
          * LLM as the response engine. Supported attributes - model, s2s_model,
-         * model_temperature, model_high_priority, tool_call_strict_mode,
+         * model_temperature, model_high_priority, model_ultrafast, tool_call_strict_mode,
          * knowledge_base_ids, kb_config, start_speaker, begin_after_user_silence_ms,
          * begin_message.
          */
@@ -7538,7 +7558,9 @@ export declare namespace CallCreateWebCallParams {
     namespace AgentOverride {
         /**
          * Override agent configuration settings. Any properties specified here will
-         * override the base agent configuration for this call.
+         * override the base agent configuration for this call. If a Retell LLM or
+         * Conversation Flow response engine is specified without a version, it uses the
+         * latest version.
          */
         interface Agent {
             /**
@@ -7775,7 +7797,7 @@ export declare namespace CallCreateWebCallParams {
             /**
              * The model to use for post call analysis. Default to gpt-5.6-terra.
              */
-            post_call_analysis_model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | null;
+            post_call_analysis_model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | 'gemini-4-argon' | null;
             /**
              * Integration (Agent Functions) tools run as a dependency graph during teardown,
              * after post-call analysis. Each tool can be gated by a condition. On calls the
@@ -9232,7 +9254,7 @@ export declare namespace CallCreateWebCallParams {
                 /**
                  * The LLM model to use
                  */
-                model: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash';
+                model: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | 'gemini-4-argon';
                 /**
                  * Type of model choice
                  */
@@ -9241,6 +9263,12 @@ export declare namespace CallCreateWebCallParams {
                  * Whether to use high priority pool with more dedicated resource, default false
                  */
                 high_priority?: boolean;
+                /**
+                 * Whether to use the ultrafast tier for much faster response generation, default
+                 * false. Only supported by gpt-6.1-sol on voice agents; ignored otherwise. Takes
+                 * precedence over high_priority.
+                 */
+                ultrafast?: boolean;
             }
             interface ModelChoiceS2S {
                 /**
@@ -9256,7 +9284,7 @@ export declare namespace CallCreateWebCallParams {
         /**
          * Override Retell LLM configuration settings. Only applicable when using Retell
          * LLM as the response engine. Supported attributes - model, s2s_model,
-         * model_temperature, model_high_priority, tool_call_strict_mode,
+         * model_temperature, model_high_priority, model_ultrafast, tool_call_strict_mode,
          * knowledge_base_ids, kb_config, start_speaker, begin_after_user_silence_ms,
          * begin_message.
          */
@@ -9284,7 +9312,7 @@ export declare namespace CallCreateWebCallParams {
             /**
              * Select the underlying text LLM. If not set, would default to gpt-5.6-terra.
              */
-            model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | null;
+            model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | 'gemini-4-argon' | null;
             /**
              * If set to true, will use high priority pool with more dedicated resource to
              * ensure lower and more consistent latency, default to false. This feature usually
@@ -9298,6 +9326,13 @@ export declare namespace CallCreateWebCallParams {
              * recommended.
              */
             model_temperature?: number;
+            /**
+             * If set to true, will use the ultrafast tier for much faster response generation,
+             * default to false. Only supported by gpt-6.1-sol on voice agents; ignored
+             * otherwise. Takes precedence over model_high_priority. This feature comes with a
+             * higher cost.
+             */
+            model_ultrafast?: boolean | null;
             /**
              * Select the underlying speech to speech model. Can only set this or model, not
              * both.
@@ -9382,7 +9417,9 @@ export declare namespace CallRegisterPhoneCallParams {
     interface AgentOverride {
         /**
          * Override agent configuration settings. Any properties specified here will
-         * override the base agent configuration for this call.
+         * override the base agent configuration for this call. If a Retell LLM or
+         * Conversation Flow response engine is specified without a version, it uses the
+         * latest version.
          */
         agent?: AgentOverride.Agent;
         /**
@@ -9395,7 +9432,7 @@ export declare namespace CallRegisterPhoneCallParams {
         /**
          * Override Retell LLM configuration settings. Only applicable when using Retell
          * LLM as the response engine. Supported attributes - model, s2s_model,
-         * model_temperature, model_high_priority, tool_call_strict_mode,
+         * model_temperature, model_high_priority, model_ultrafast, tool_call_strict_mode,
          * knowledge_base_ids, kb_config, start_speaker, begin_after_user_silence_ms,
          * begin_message.
          */
@@ -9404,7 +9441,9 @@ export declare namespace CallRegisterPhoneCallParams {
     namespace AgentOverride {
         /**
          * Override agent configuration settings. Any properties specified here will
-         * override the base agent configuration for this call.
+         * override the base agent configuration for this call. If a Retell LLM or
+         * Conversation Flow response engine is specified without a version, it uses the
+         * latest version.
          */
         interface Agent {
             /**
@@ -9641,7 +9680,7 @@ export declare namespace CallRegisterPhoneCallParams {
             /**
              * The model to use for post call analysis. Default to gpt-5.6-terra.
              */
-            post_call_analysis_model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | null;
+            post_call_analysis_model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | 'gemini-4-argon' | null;
             /**
              * Integration (Agent Functions) tools run as a dependency graph during teardown,
              * after post-call analysis. Each tool can be gated by a condition. On calls the
@@ -11098,7 +11137,7 @@ export declare namespace CallRegisterPhoneCallParams {
                 /**
                  * The LLM model to use
                  */
-                model: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash';
+                model: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | 'gemini-4-argon';
                 /**
                  * Type of model choice
                  */
@@ -11107,6 +11146,12 @@ export declare namespace CallRegisterPhoneCallParams {
                  * Whether to use high priority pool with more dedicated resource, default false
                  */
                 high_priority?: boolean;
+                /**
+                 * Whether to use the ultrafast tier for much faster response generation, default
+                 * false. Only supported by gpt-6.1-sol on voice agents; ignored otherwise. Takes
+                 * precedence over high_priority.
+                 */
+                ultrafast?: boolean;
             }
             interface ModelChoiceS2S {
                 /**
@@ -11122,7 +11167,7 @@ export declare namespace CallRegisterPhoneCallParams {
         /**
          * Override Retell LLM configuration settings. Only applicable when using Retell
          * LLM as the response engine. Supported attributes - model, s2s_model,
-         * model_temperature, model_high_priority, tool_call_strict_mode,
+         * model_temperature, model_high_priority, model_ultrafast, tool_call_strict_mode,
          * knowledge_base_ids, kb_config, start_speaker, begin_after_user_silence_ms,
          * begin_message.
          */
@@ -11150,7 +11195,7 @@ export declare namespace CallRegisterPhoneCallParams {
             /**
              * Select the underlying text LLM. If not set, would default to gpt-5.6-terra.
              */
-            model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | null;
+            model?: 'gpt-4.1' | 'gpt-4.1-mini' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.1' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.4-nano' | 'gpt-5.5' | 'gpt-5.6-terra' | 'gpt-5.6-luna' | 'gpt-6-astra' | 'gpt-6-sol' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'claude-4.6-sonnet' | 'claude-5-opus' | 'claude-5.5-opus' | 'claude-5-sonnet' | 'claude-5.5-sonnet' | 'claude-5.5-haiku' | 'claude-4.5-haiku' | 'gemini-3.0-flash' | 'gemini-3.1-flash-lite' | 'gemini-3.5-flash' | 'gemini-3.5-flash-lite' | 'gemini-3.6-flash' | 'gemini-3.7-flash' | 'gemini-3.8-flash' | 'gemini-4-argon' | null;
             /**
              * If set to true, will use high priority pool with more dedicated resource to
              * ensure lower and more consistent latency, default to false. This feature usually
@@ -11164,6 +11209,13 @@ export declare namespace CallRegisterPhoneCallParams {
              * recommended.
              */
             model_temperature?: number;
+            /**
+             * If set to true, will use the ultrafast tier for much faster response generation,
+             * default to false. Only supported by gpt-6.1-sol on voice agents; ignored
+             * otherwise. Takes precedence over model_high_priority. This feature comes with a
+             * higher cost.
+             */
+            model_ultrafast?: boolean | null;
             /**
              * Select the underlying speech to speech model. Can only set this or model, not
              * both.