diff --git a/crates/language_models/src/provider/opencode.rs b/crates/language_models/src/provider/opencode.rs
index 2a4e27c3c7ce78..f5281e019f71ec 100644
--- a/crates/language_models/src/provider/opencode.rs
+++ b/crates/language_models/src/provider/opencode.rs
@@ -72,7 +72,6 @@ pub struct OpenCodeSettings {
     pub custom_headers: CustomHeaders,
     pub show_zen_models: bool,
     pub show_go_models: bool,
-    pub show_free_models: bool,
 }
 
 pub struct OpenCodeLanguageModelProvider {
@@ -167,7 +166,6 @@ impl OpenCodeLanguageModelProvider {
         match subscription {
             OpenCodeSubscription::Zen => settings.show_zen_models,
             OpenCodeSubscription::Go => settings.show_go_models,
-            OpenCodeSubscription::Free => settings.show_free_models,
         }
     }
 
@@ -210,13 +208,6 @@ impl LanguageModelProvider for OpenCodeLanguageModelProvider {
             )
         } else if Self::subscription_enabled(OpenCodeSubscription::Zen, cx) {
             Some(self.create_language_model(opencode::Model::default(), OpenCodeSubscription::Zen))
-        } else if Self::subscription_enabled(OpenCodeSubscription::Free, cx) {
-            Some(
-                self.create_language_model(
-                    opencode::Model::default_free(),
-                    OpenCodeSubscription::Free,
-                ),
-            )
         } else {
             None
         }
@@ -236,11 +227,6 @@ impl LanguageModelProvider for OpenCodeLanguageModelProvider {
                     OpenCodeSubscription::Zen,
                 ),
             )
-        } else if Self::subscription_enabled(OpenCodeSubscription::Free, cx) {
-            Some(self.create_language_model(
-                opencode::Model::default_free_fast(),
-                OpenCodeSubscription::Free,
-            ))
         } else {
             None
         }
@@ -273,7 +259,6 @@ impl LanguageModelProvider for OpenCodeLanguageModelProvider {
             };
             let subscription = match model.subscription {
                 Some(settings::OpenCodeModelSubscription::Go) => OpenCodeSubscription::Go,
-                Some(settings::OpenCodeModelSubscription::Free) => OpenCodeSubscription::Free,
                 Some(settings::OpenCodeModelSubscription::Zen) | None => OpenCodeSubscription::Zen,
             };
             if !Self::subscription_enabled(subscription, cx) {
@@ -858,7 +843,6 @@ impl ConfigurationView {
             match subscription {
                 OpenCodeSubscription::Zen => opencode_settings.show_zen_models = Some(is_enabled),
                 OpenCodeSubscription::Go => opencode_settings.show_go_models = Some(is_enabled),
-                OpenCodeSubscription::Free => opencode_settings.show_free_models = Some(is_enabled),
             }
         });
     }
@@ -935,7 +919,6 @@ impl Render for ConfigurationView {
             let settings = OpenCodeLanguageModelProvider::settings(cx);
             let show_zen = settings.show_zen_models;
             let show_go = settings.show_go_models;
-            let show_free = settings.show_free_models;
 
             let subscription_toggles = v_flex()
                 .gap_2()
@@ -943,7 +926,7 @@ impl Render for ConfigurationView {
                 .child(
                     Switch::new("opencode-show-zen-models", show_zen.into())
                         .full_width(true)
-                        .label("Show Zen Models")
+                        .label("Show Zen models")
                         .label_position(SwitchLabelPosition::Start)
                         .on_click(cx.listener(|this, state, window, cx| {
                             this.set_subscription_enabled(
@@ -968,24 +951,9 @@ impl Render for ConfigurationView {
                                 cx,
                             );
                         })),
-                )
-                .child(Divider::horizontal_dashed())
-                .child(
-                    Switch::new("opencode-show-free-models", show_free.into())
-                        .full_width(true)
-                        .label("Show Free models")
-                        .label_position(SwitchLabelPosition::Start)
-                        .on_click(cx.listener(|this, state, window, cx| {
-                            this.set_subscription_enabled(
-                                OpenCodeSubscription::Free,
-                                matches!(state, ToggleState::Selected),
-                                window,
-                                cx,
-                            );
-                        })),
                 );
 
-            let no_subscriptions_warning = if !show_zen && !show_go && !show_free {
+            let no_subscriptions_warning = if !show_zen && !show_go {
                 Some(Banner::new().severity(Severity::Warning).child(Label::new(
                     "No subscriptions enabled. Enable at least one subscription to use OpenCode.",
                 )))
diff --git a/crates/language_models/src/settings.rs b/crates/language_models/src/settings.rs
index 4f360eea95c845..7868b3f16605e7 100644
--- a/crates/language_models/src/settings.rs
+++ b/crates/language_models/src/settings.rs
@@ -158,7 +158,6 @@ impl settings::Settings for AllLanguageModelSettings {
                 ),
                 show_zen_models: opencode.show_zen_models.unwrap_or(true),
                 show_go_models: opencode.show_go_models.unwrap_or(true),
-                show_free_models: opencode.show_free_models.unwrap_or(true),
             },
             open_router: OpenRouterSettings {
                 api_url: open_router.api_url.unwrap(),
diff --git a/crates/opencode/src/opencode.rs b/crates/opencode/src/opencode.rs
index 9558bc8f24b8e5..8e7f998b376790 100644
--- a/crates/opencode/src/opencode.rs
+++ b/crates/opencode/src/opencode.rs
@@ -26,7 +26,6 @@ pub enum ApiProtocol {
 pub enum OpenCodeSubscription {
     Zen,
     Go,
-    Free,
 }
 
 impl OpenCodeSubscription {
@@ -34,7 +33,6 @@ impl OpenCodeSubscription {
         match self {
             Self::Zen => "Zen",
             Self::Go => "Go",
-            Self::Free => "Free",
         }
     }
 
@@ -42,13 +40,12 @@ impl OpenCodeSubscription {
         match self {
             Self::Zen => "zen",
             Self::Go => "go",
-            Self::Free => "free",
         }
     }
 
     pub fn api_path_suffix(&self) -> &'static str {
         match self {
-            Self::Zen | Self::Free => "",
+            Self::Zen => "",
             Self::Go => "/go",
         }
     }
@@ -58,6 +55,8 @@ impl OpenCodeSubscription {
 #[derive(Clone, Debug, Default, Serialize, Deserialize, PartialEq, EnumIter)]
 pub enum Model {
     // -- Anthropic protocol models --
+    #[serde(rename = "claude-opus-5")]
+    ClaudeOpus5,
     #[serde(rename = "claude-opus-4-8")]
     ClaudeOpus4_8,
     #[serde(rename = "claude-opus-4-7")]
@@ -66,8 +65,6 @@ pub enum Model {
     ClaudeOpus4_6,
     #[serde(rename = "claude-opus-4-5")]
     ClaudeOpus4_5,
-    #[serde(rename = "claude-opus-4-1")]
-    ClaudeOpus4_1,
     #[default]
     #[serde(rename = "claude-sonnet-4-6")]
     ClaudeSonnet4_6,
@@ -129,8 +126,14 @@ pub enum Model {
     Gemini3_1Pro,
     #[serde(rename = "gemini-3-flash")]
     Gemini3Flash,
+    #[serde(rename = "gemini-3.5-flash-lite")]
+    Gemini3_5FlashLite,
     #[serde(rename = "gemini-3.5-flash")]
     Gemini3_5Flash,
+    #[serde(rename = "gemini-3.6-flash")]
+    Gemini3_6Flash,
+    #[serde(rename = "gemini-3.7-flash")]
+    Gemini3_7Flash,
 
     // -- OpenAI Chat Completions protocol models --
     #[serde(rename = "deepseek-v4-pro")]
@@ -145,16 +148,24 @@ pub enum Model {
     Glm5_1,
     #[serde(rename = "glm-5.2")]
     Glm5_2,
+    #[serde(rename = "glm-5.3")]
+    Glm5_3,
     #[serde(rename = "grok-build-0.1")]
     GrokBuild0_1,
     #[serde(rename = "grok-4.5")]
     Grok4_5,
+    #[serde(rename = "grok-4.6")]
+    Grok4_6,
+    #[serde(rename = "muse-spark-1.2")]
+    MuseSpark1_2,
     #[serde(rename = "kimi-k2.5")]
     KimiK2_5,
     #[serde(rename = "kimi-k2.6")]
     KimiK2_6,
     #[serde(rename = "kimi-k2.7-code")]
     KimiK2_7Code,
+    #[serde(rename = "kimi-k3")]
+    KimiK3,
     #[serde(rename = "minimax-m2.7")]
     MiniMaxM2_7,
     #[serde(rename = "minimax-m3")]
@@ -163,10 +174,6 @@ pub enum Model {
     MimoV2_5Pro,
     #[serde(rename = "mimo-v2.5")]
     MimoV2_5,
-    #[serde(rename = "big-pickle")]
-    BigPickle,
-    #[serde(rename = "nemotron-3-ultra-free")]
-    Nemotron3UltraFree,
     #[serde(rename = "qwen3.5-plus")]
     Qwen3_5Plus,
     #[serde(rename = "qwen3.6-plus")]
@@ -175,6 +182,10 @@ pub enum Model {
     Qwen3_7Plus,
     #[serde(rename = "qwen3.7-max")]
     Qwen3_7Max,
+    #[serde(rename = "qwen3.8-max")]
+    Qwen3_8Max,
+    #[serde(rename = "hy3")]
+    Hy3,
 
     // -- Custom model --
     #[serde(rename = "custom")]
@@ -203,40 +214,36 @@ impl Model {
         Self::MiniMaxM2_7
     }
 
-    pub fn default_free() -> Self {
-        Self::BigPickle
-    }
-
-    pub fn default_free_fast() -> Self {
-        Self::Nemotron3UltraFree
-    }
-
     pub fn available_subscriptions(&self) -> &'static [OpenCodeSubscription] {
         match self {
             // Models available in both Zen and Go
             Self::Glm5_1
             | Self::Glm5_2
+            | Self::Grok4_5
             | Self::KimiK2_6
             | Self::KimiK2_7Code
+            | Self::KimiK3
             | Self::MiniMaxM2_7
             | Self::MiniMaxM3
             | Self::DeepSeekV4Pro
             | Self::DeepSeekV4Flash
+            | Self::Gpt5_6Luna
             | Self::Qwen3_6Plus => &[OpenCodeSubscription::Zen, OpenCodeSubscription::Go],
 
             // Go-only models
-            Self::MimoV2_5Pro | Self::MimoV2_5 | Self::Qwen3_7Plus | Self::Qwen3_7Max => {
-                &[OpenCodeSubscription::Go]
-            }
+            Self::MimoV2_5Pro
+            | Self::MimoV2_5
+            | Self::Glm5_3
+            | Self::Qwen3_7Plus
+            | Self::Qwen3_7Max
+            | Self::Qwen3_8Max
+            | Self::Hy3 => &[OpenCodeSubscription::Go],
 
             // Deprecated on Go (per models.dev); still offered on Zen
             Self::Glm5 | Self::KimiK2_5 | Self::MiniMaxM2_5 | Self::Qwen3_5Plus => {
                 &[OpenCodeSubscription::Zen]
             }
 
-            // Free models
-            Self::Nemotron3UltraFree | Self::BigPickle => &[OpenCodeSubscription::Free],
-
             // Custom models get their subscription from settings, not from here
             Self::Custom { .. } => &[],
 
@@ -247,11 +254,11 @@ impl Model {
 
     pub fn id(&self) -> &str {
         match self {
+            Self::ClaudeOpus5 => "claude-opus-5",
             Self::ClaudeOpus4_8 => "claude-opus-4-8",
             Self::ClaudeOpus4_7 => "claude-opus-4-7",
             Self::ClaudeOpus4_6 => "claude-opus-4-6",
             Self::ClaudeOpus4_5 => "claude-opus-4-5",
-            Self::ClaudeOpus4_1 => "claude-opus-4-1",
             Self::ClaudeSonnet4_6 => "claude-sonnet-4-6",
             Self::ClaudeSonnet4_5 => "claude-sonnet-4-5",
             Self::ClaudeSonnet4 => "claude-sonnet-4",
@@ -282,7 +289,10 @@ impl Model {
 
             Self::Gemini3_1Pro => "gemini-3.1-pro",
             Self::Gemini3Flash => "gemini-3-flash",
+            Self::Gemini3_5FlashLite => "gemini-3.5-flash-lite",
             Self::Gemini3_5Flash => "gemini-3.5-flash",
+            Self::Gemini3_6Flash => "gemini-3.6-flash",
+            Self::Gemini3_7Flash => "gemini-3.7-flash",
 
             Self::DeepSeekV4Pro => "deepseek-v4-pro",
             Self::DeepSeekV4Flash => "deepseek-v4-flash",
@@ -290,11 +300,15 @@ impl Model {
             Self::Glm5 => "glm-5",
             Self::Glm5_1 => "glm-5.1",
             Self::Glm5_2 => "glm-5.2",
+            Self::Glm5_3 => "glm-5.3",
             Self::GrokBuild0_1 => "grok-build-0.1",
             Self::Grok4_5 => "grok-4.5",
+            Self::Grok4_6 => "grok-4.6",
+            Self::MuseSpark1_2 => "muse-spark-1.2",
             Self::KimiK2_5 => "kimi-k2.5",
             Self::KimiK2_6 => "kimi-k2.6",
             Self::KimiK2_7Code => "kimi-k2.7-code",
+            Self::KimiK3 => "kimi-k3",
             Self::MiniMaxM2_7 => "minimax-m2.7",
             Self::MiniMaxM3 => "minimax-m3",
             Self::MimoV2_5Pro => "mimo-v2.5-pro",
@@ -303,8 +317,8 @@ impl Model {
             Self::Qwen3_6Plus => "qwen3.6-plus",
             Self::Qwen3_7Plus => "qwen3.7-plus",
             Self::Qwen3_7Max => "qwen3.7-max",
-            Self::BigPickle => "big-pickle",
-            Self::Nemotron3UltraFree => "nemotron-3-ultra-free",
+            Self::Qwen3_8Max => "qwen3.8-max",
+            Self::Hy3 => "hy3",
 
             Self::Custom { name, .. } => name,
         }
@@ -312,11 +326,11 @@ impl Model {
 
     pub fn display_name(&self) -> &str {
         match self {
+            Self::ClaudeOpus5 => "Claude Opus 5",
             Self::ClaudeOpus4_8 => "Claude Opus 4.8",
             Self::ClaudeOpus4_7 => "Claude Opus 4.7",
             Self::ClaudeOpus4_6 => "Claude Opus 4.6",
             Self::ClaudeOpus4_5 => "Claude Opus 4.5",
-            Self::ClaudeOpus4_1 => "Claude Opus 4.1",
             Self::ClaudeSonnet4_6 => "Claude Sonnet 4.6",
             Self::ClaudeSonnet4_5 => "Claude Sonnet 4.5",
             Self::ClaudeSonnet4 => "Claude Sonnet 4",
@@ -347,7 +361,10 @@ impl Model {
 
             Self::Gemini3_1Pro => "Gemini 3.1 Pro",
             Self::Gemini3Flash => "Gemini 3 Flash",
+            Self::Gemini3_5FlashLite => "Gemini 3.5 Flash Lite",
             Self::Gemini3_5Flash => "Gemini 3.5 Flash",
+            Self::Gemini3_6Flash => "Gemini 3.6 Flash",
+            Self::Gemini3_7Flash => "Gemini 3.7 Flash",
 
             Self::DeepSeekV4Pro => "DeepSeek V4 Pro",
             Self::DeepSeekV4Flash => "DeepSeek V4 Flash",
@@ -355,11 +372,15 @@ impl Model {
             Self::Glm5 => "GLM 5",
             Self::Glm5_1 => "GLM 5.1",
             Self::Glm5_2 => "GLM 5.2",
+            Self::Glm5_3 => "GLM 5.3",
             Self::GrokBuild0_1 => "Grok Build 0.1",
             Self::Grok4_5 => "Grok 4.5",
+            Self::Grok4_6 => "Grok 4.6",
+            Self::MuseSpark1_2 => "Muse Spark 1.2",
             Self::KimiK2_5 => "Kimi K2.5",
             Self::KimiK2_6 => "Kimi K2.6",
             Self::KimiK2_7Code => "Kimi K2.7 Code",
+            Self::KimiK3 => "Kimi K3",
             Self::MiniMaxM2_7 => "MiniMax M2.7",
             Self::MiniMaxM3 => "MiniMax M3",
             Self::MimoV2_5Pro => "MiMo V2.5 Pro",
@@ -368,8 +389,8 @@ impl Model {
             Self::Qwen3_6Plus => "Qwen3.6 Plus",
             Self::Qwen3_7Plus => "Qwen3.7 Plus",
             Self::Qwen3_7Max => "Qwen3.7 Max",
-            Self::BigPickle => "Big Pickle",
-            Self::Nemotron3UltraFree => "Nemotron 3 Ultra Free",
+            Self::Qwen3_8Max => "Qwen3.8 Max",
+            Self::Hy3 => "Hy3",
 
             Self::Custom {
                 name, display_name, ..
@@ -390,11 +411,11 @@ impl Model {
             }
 
             Self::ClaudeFable5
+            | Self::ClaudeOpus5
             | Self::ClaudeOpus4_8
             | Self::ClaudeOpus4_7
             | Self::ClaudeOpus4_6
             | Self::ClaudeOpus4_5
-            | Self::ClaudeOpus4_1
             | Self::ClaudeSonnet5
             | Self::ClaudeSonnet4_6
             | Self::ClaudeSonnet4_5
@@ -422,26 +443,35 @@ impl Model {
             | Self::Gpt5Codex
             | Self::Gpt5Nano => ApiProtocol::OpenAiResponses,
 
-            Self::Gemini3_1Pro | Self::Gemini3Flash | Self::Gemini3_5Flash => ApiProtocol::Google,
+            Self::Gemini3_1Pro
+            | Self::Gemini3Flash
+            | Self::Gemini3_5FlashLite
+            | Self::Gemini3_5Flash
+            | Self::Gemini3_6Flash
+            | Self::Gemini3_7Flash => ApiProtocol::Google,
 
-            Self::Qwen3_7Max | Self::Qwen3_7Plus | Self::Qwen3_6Plus | Self::Qwen3_5Plus => {
-                ApiProtocol::Anthropic
-            }
+            Self::Qwen3_8Max
+            | Self::Qwen3_7Max
+            | Self::Qwen3_7Plus
+            | Self::Qwen3_6Plus
+            | Self::Qwen3_5Plus => ApiProtocol::Anthropic,
 
             Self::Glm5
             | Self::Glm5_1
             | Self::Glm5_2
+            | Self::Glm5_3
             | Self::GrokBuild0_1
-            | Self::Grok4_5
             | Self::KimiK2_5
             | Self::KimiK2_6
             | Self::KimiK2_7Code
+            | Self::KimiK3
             | Self::MimoV2_5Pro
             | Self::MimoV2_5
             | Self::DeepSeekV4Pro
             | Self::DeepSeekV4Flash
-            | Self::BigPickle
-            | Self::Nemotron3UltraFree => ApiProtocol::OpenAiChat,
+            | Self::Hy3 => ApiProtocol::OpenAiChat,
+
+            Self::Grok4_6 | Self::Grok4_5 | Self::MuseSpark1_2 => ApiProtocol::OpenAiResponses,
 
             Self::Custom { protocol, .. } => *protocol,
         }
@@ -454,16 +484,16 @@ impl Model {
             | Self::KimiK2_5
             | Self::KimiK2_6
             | Self::KimiK2_7Code
+            | Self::KimiK3
             | Self::MimoV2_5
             | Self::MimoV2_5Pro
             | Self::Glm5
             | Self::Glm5_1
             | Self::Glm5_2
+            | Self::Glm5_3
             | Self::MiniMaxM2_5
             | Self::MiniMaxM2_7
-            | Self::MiniMaxM3
-            | Self::Nemotron3UltraFree
-            | Self::BigPickle => true,
+            | Self::MiniMaxM3 => true,
 
             Self::Custom {
                 interleaved_reasoning,
@@ -477,11 +507,10 @@ impl Model {
     pub fn max_token_count(&self, subscription: OpenCodeSubscription) -> u64 {
         match self {
             // Anthropic models
-            Self::ClaudeOpus4_8 | Self::ClaudeOpus4_7 => 1_000_000,
+            Self::ClaudeOpus5 | Self::ClaudeOpus4_8 | Self::ClaudeOpus4_7 => 1_000_000,
             Self::ClaudeOpus4_6 | Self::ClaudeSonnet4_6 => 1_000_000,
             Self::ClaudeSonnet4_5 => 1_000_000,
             Self::ClaudeOpus4_5 | Self::ClaudeHaiku4_5 => 200_000,
-            Self::ClaudeOpus4_1 => 200_000,
             Self::ClaudeSonnet4 => 1_000_000,
             Self::ClaudeSonnet5 => 1_000_000,
             Self::ClaudeFable5 => 1_000_000,
@@ -500,9 +529,12 @@ impl Model {
             Self::Gpt5 | Self::Gpt5Codex | Self::Gpt5Nano => 400_000,
 
             // Google models
-            Self::Gemini3_1Pro => 1_048_576,
-            Self::Gemini3Flash => 1_048_576,
-            Self::Gemini3_5Flash => 1_048_576,
+            Self::Gemini3_1Pro
+            | Self::Gemini3Flash
+            | Self::Gemini3_5FlashLite
+            | Self::Gemini3_5Flash
+            | Self::Gemini3_6Flash
+            | Self::Gemini3_7Flash => 1_048_576,
 
             // OpenAI-compatible models
             Self::MiniMaxM2_7 => 204_800,
@@ -521,10 +553,12 @@ impl Model {
                     204_800
                 }
             }
-            Self::Glm5_2 => 1_000_000,
+            Self::Glm5_3 | Self::Glm5_2 => 1_000_000,
             Self::KimiK2_6 | Self::KimiK2_5 | Self::KimiK2_7Code => 262_144,
+            Self::KimiK3 => 1_048_576,
             Self::GrokBuild0_1 => 256_000,
-            Self::Grok4_5 => 500_000,
+            Self::Grok4_6 | Self::Grok4_5 => 500_000,
+            Self::MuseSpark1_2 => 1_048_576,
             Self::MimoV2_5Pro => 1_048_576,
             Self::MimoV2_5 => 1_000_000,
             Self::Qwen3_5Plus => 262_144,
@@ -535,9 +569,8 @@ impl Model {
                     262_144
                 }
             }
-            Self::Qwen3_7Max | Self::Qwen3_7Plus => 1_000_000,
-            Self::BigPickle => 200_000,
-            Self::Nemotron3UltraFree => 1_000_000,
+            Self::Qwen3_8Max | Self::Qwen3_7Max | Self::Qwen3_7Plus => 1_000_000,
+            Self::Hy3 => 256_000,
             Self::DeepSeekV4Pro | Self::DeepSeekV4Flash => 1_000_000,
 
             Self::Custom { max_tokens, .. } => *max_tokens,
@@ -547,13 +580,14 @@ impl Model {
     pub fn max_output_tokens(&self, subscription: OpenCodeSubscription) -> Option<u64> {
         match self {
             // Anthropic models
-            Self::ClaudeOpus4_8 | Self::ClaudeOpus4_7 | Self::ClaudeOpus4_6 => Some(128_000),
+            Self::ClaudeOpus5 | Self::ClaudeOpus4_8 | Self::ClaudeOpus4_7 | Self::ClaudeOpus4_6 => {
+                Some(128_000)
+            }
             Self::ClaudeOpus4_5
             | Self::ClaudeSonnet4_6
             | Self::ClaudeSonnet4_5
             | Self::ClaudeHaiku4_5
             | Self::ClaudeSonnet4 => Some(64_000),
-            Self::ClaudeOpus4_1 => Some(32_000),
             Self::ClaudeSonnet5 => Some(128_000),
             Self::ClaudeFable5 => Some(128_000),
 
@@ -580,7 +614,12 @@ impl Model {
             | Self::Gpt5Nano => Some(128_000),
 
             // Google models
-            Self::Gemini3_1Pro | Self::Gemini3Flash | Self::Gemini3_5Flash => Some(65_536),
+            Self::Gemini3_1Pro
+            | Self::Gemini3Flash
+            | Self::Gemini3_5FlashLite
+            | Self::Gemini3_5Flash
+            | Self::Gemini3_6Flash
+            | Self::Gemini3_7Flash => Some(65_536),
 
             // OpenAI-compatible models
             Self::MiniMaxM2_7 => Some(131_072),
@@ -605,18 +644,20 @@ impl Model {
                     Some(131_072)
                 }
             }
-            Self::Glm5_2 => Some(131_072),
-            Self::BigPickle => Some(32_000),
+            Self::Glm5_3 | Self::Glm5_2 => Some(131_072),
             Self::KimiK2_6 | Self::KimiK2_5 => Some(65_536),
             Self::KimiK2_7Code => Some(262_144),
+            Self::KimiK3 => Some(131_072),
             Self::GrokBuild0_1 => Some(256_000),
-            Self::Grok4_5 => Some(500_000),
+            Self::Grok4_6 | Self::Grok4_5 => Some(500_000),
+            Self::MuseSpark1_2 => Some(131_072),
             Self::Qwen3_7Max | Self::Qwen3_7Plus | Self::Qwen3_6Plus | Self::Qwen3_5Plus => {
                 Some(65_536)
             }
+            Self::Qwen3_8Max => Some(131_072),
             Self::DeepSeekV4Pro | Self::DeepSeekV4Flash => Some(384_000),
-            Self::Nemotron3UltraFree => Some(128_000),
             Self::MimoV2_5Pro | Self::MimoV2_5 => Some(128_000),
+            Self::Hy3 => Some(64_000),
 
             Self::Custom {
                 max_output_tokens, ..
@@ -631,11 +672,11 @@ impl Model {
     pub fn supports_images(&self) -> bool {
         match self {
             // Anthropic models support images
-            Self::ClaudeOpus4_8
+            Self::ClaudeOpus5
+            | Self::ClaudeOpus4_8
             | Self::ClaudeOpus4_7
             | Self::ClaudeOpus4_6
             | Self::ClaudeOpus4_5
-            | Self::ClaudeOpus4_1
             | Self::ClaudeSonnet4_6
             | Self::ClaudeSonnet4_5
             | Self::ClaudeSonnet4
@@ -668,18 +709,27 @@ impl Model {
             Self::Gpt5_3Spark => false,
 
             // Google models support images
-            Self::Gemini3_1Pro | Self::Gemini3Flash | Self::Gemini3_5Flash => true,
+            Self::Gemini3_1Pro
+            | Self::Gemini3Flash
+            | Self::Gemini3_5FlashLite
+            | Self::Gemini3_5Flash
+            | Self::Gemini3_6Flash
+            | Self::Gemini3_7Flash => true,
 
             // OpenAI-compatible models with image support
             Self::KimiK2_6
+            | Self::KimiK3
             | Self::KimiK2_7Code
             | Self::KimiK2_5
             | Self::GrokBuild0_1
             | Self::Grok4_5
+            | Self::Grok4_6
+            | Self::MuseSpark1_2
             | Self::MimoV2_5
             | Self::Qwen3_5Plus
             | Self::Qwen3_6Plus
             | Self::Qwen3_7Plus
+            | Self::Qwen3_8Max
             | Self::MiniMaxM3 => true,
 
             // OpenAI-compatible models without image support
@@ -687,13 +737,13 @@ impl Model {
             | Self::Glm5
             | Self::Glm5_1
             | Self::Glm5_2
+            | Self::Glm5_3
             | Self::MiniMaxM2_7
             | Self::MimoV2_5Pro
             | Self::DeepSeekV4Pro
             | Self::DeepSeekV4Flash
             | Self::Qwen3_7Max
-            | Self::BigPickle
-            | Self::Nemotron3UltraFree => false,
+            | Self::Hy3 => false,
 
             Self::Custom { protocol, .. } => matches!(
                 protocol,
@@ -709,6 +759,7 @@ impl Model {
         match self {
             // Anthropic models
             Self::ClaudeFable5
+            | Self::ClaudeOpus5
             | Self::ClaudeOpus4_8
             | Self::ClaudeOpus4_7
             | Self::ClaudeSonnet5 => Some(vec![
@@ -789,14 +840,17 @@ impl Model {
             ]),
 
             // Google models
-            Self::Gemini3Flash | Self::Gemini3_5Flash => Some(vec![
+            Self::Gemini3Flash
+            | Self::Gemini3_5FlashLite
+            | Self::Gemini3_5Flash
+            | Self::Gemini3_6Flash => Some(vec![
                 ReasoningEffort::Minimal,
                 ReasoningEffort::Low,
                 ReasoningEffort::Medium,
                 ReasoningEffort::High,
             ]),
 
-            Self::Gemini3_1Pro => Some(vec![
+            Self::Gemini3_7Flash | Self::Gemini3_1Pro => Some(vec![
                 ReasoningEffort::Low,
                 ReasoningEffort::Medium,
                 ReasoningEffort::High,
@@ -809,16 +863,12 @@ impl Model {
                 ReasoningEffort::Max,
             ]),
 
+            // Moonshot AI models
+            Self::KimiK3 => Some(vec![ReasoningEffort::Max]),
+
             // MiniMax models
             Self::MiniMaxM3 => Some(vec![ReasoningEffort::None]),
 
-            // NVIDIA models
-            Self::Nemotron3UltraFree => Some(vec![
-                ReasoningEffort::Low,
-                ReasoningEffort::Medium,
-                ReasoningEffort::High,
-            ]),
-
             // Xiaomi MiMo models
             Self::MimoV2_5Pro | Self::MimoV2_5 => Some(vec![
                 ReasoningEffort::Low,
@@ -829,13 +879,42 @@ impl Model {
             // Z AI models
             Self::Glm5_2 => Some(vec![ReasoningEffort::High, ReasoningEffort::Max]),
 
+            Self::Glm5_3 => Some(vec![
+                ReasoningEffort::Low,
+                ReasoningEffort::High,
+                ReasoningEffort::Max,
+            ]),
+
+            // Tencent models
+            Self::Hy3 => Some(vec![
+                ReasoningEffort::None,
+                ReasoningEffort::Low,
+                ReasoningEffort::High,
+            ]),
+
             // SpaceXAI models
+            Self::Grok4_6 => Some(vec![
+                ReasoningEffort::Low,
+                ReasoningEffort::Medium,
+                ReasoningEffort::High,
+                ReasoningEffort::XHigh,
+            ]),
+
             Self::Grok4_5 => Some(vec![
                 ReasoningEffort::Low,
                 ReasoningEffort::Medium,
                 ReasoningEffort::High,
             ]),
 
+            // Meta AI models
+            Self::MuseSpark1_2 => Some(vec![
+                ReasoningEffort::Minimal,
+                ReasoningEffort::Low,
+                ReasoningEffort::Medium,
+                ReasoningEffort::High,
+                ReasoningEffort::XHigh,
+            ]),
+
             Self::Custom {
                 reasoning_effort_levels,
                 ..
diff --git a/crates/settings_content/src/language_model.rs b/crates/settings_content/src/language_model.rs
index 735c3d20e1609d..06239c76c2b386 100644
--- a/crates/settings_content/src/language_model.rs
+++ b/crates/settings_content/src/language_model.rs
@@ -245,8 +245,6 @@ pub struct OpenCodeSettingsContent {
     pub show_zen_models: Option<bool>,
     /// Whether to show OpenCode Go models. Defaults to true.
     pub show_go_models: Option<bool>,
-    /// Whether to show OpenCode Free models. Defaults to true.
-    pub show_free_models: Option<bool>,
 }
 
 #[derive(Clone, Copy, Debug, PartialEq, Eq, Serialize, Deserialize, JsonSchema, MergeFrom)]
@@ -266,7 +264,6 @@ pub enum OpenCodeApiProtocol {
 pub enum OpenCodeModelSubscription {
     Zen,
     Go,
-    Free,
 }
 
 #[with_fallible_options]
@@ -278,7 +275,7 @@ pub struct OpenCodeAvailableModel {
     pub max_output_tokens: Option<u64>,
     /// The API protocol to use for this model: "anthropic", "openai_responses", "openai_chat", or "google". Defaults to "openai_chat".
     pub protocol: Option<OpenCodeApiProtocol>,
-    /// The subscription for this model: "zen", "go", or "free". Defaults to Zen.
+    /// The subscription for this model: "zen" or "go". Defaults to Zen.
     pub subscription: Option<OpenCodeModelSubscription>,
     /// Custom Model API URL to use for this model.
     pub custom_model_api_url: Option<String>,
diff --git a/docs/src/ai/use-api-access.md b/docs/src/ai/use-api-access.md
index 7af0c0e68a3948..2064fce9c1d754 100644
--- a/docs/src/ai/use-api-access.md
+++ b/docs/src/ai/use-api-access.md
@@ -349,7 +349,10 @@ Use OpenCode API access when you have an OpenCode API key. OpenCode Zen and Go a
 Zed does not sign in to OpenCode with OAuth or detect your OpenCode subscription; it uses an OpenCode API key saved in the system keychain or `OPENCODE_API_KEY`.
 
 1. Visit [OpenCode Console](https://opencode.ai/auth) and create an account.
-2. Free models are available without payment. To use Zen or Go models, make sure you have enough credits or an active subscription.
+2. To use Zen or Go models, make sure you have enough credits or an active
+   subscription. OpenCode Free models are not available when using OpenCode as a
+   provider in Zed's Agent. You can use them in Zed by running OpenCode as an
+   [external agent through ACP](https://zed.dev/acp/agent/opencode).
 3. Generate an API key from the API Keys section in the OpenCode Console.
 4. Open Agent Settings with {#action agent::OpenSettings} and go to the OpenCode section.
 5. Enter your OpenCode API key.
@@ -362,19 +365,16 @@ By default, models from all OpenCode subscription types are shown. You can hide
 {
   "language_models": {
     "opencode": {
-      "show_zen_models": true,
-      "show_go_models": false,
-      "show_free_models": false
+      "show_zen_models": false,
+      "show_go_models": true
     }
   }
 }
 ```
 
-**Note:** Zed only bundles configuration for long-term OpenCode Free models. Free models that are available for a limited time are not included in Zed. To use those models, add a custom OpenCode model with configuration from [the OpenCode website](https://opencode.ai/docs/zen#pricing) and [models.dev](https://github.com/anomalyco/models.dev/tree/dev/providers/opencode/models).
-
 #### Custom OpenCode Models {#opencode-custom-models}
 
-The Zed Agent comes preconfigured with OpenCode models. Add custom OpenCode models when you need newer models, limited-time Free models, or models with custom endpoints.
+The Zed Agent comes preconfigured with OpenCode models. Add custom OpenCode models when you need newer models or models with custom endpoints.
 
 Add custom models in your settings file:
 
@@ -409,7 +409,7 @@ The available configuration options for custom OpenCode models are:
 - `protocol` (optional, default `"openai_chat"`): model API protocol, one of `"anthropic"`, `"openai_responses"`, `"openai_chat"`, or `"google"`
 - `reasoning_effort_levels` (optional): list of supported reasoning effort levels, such as `["none", "low", "medium", "high", "xhigh", "max"]`. The last value in the list is used as the default
 - `interleaved_reasoning` (optional, default `false`): whether thinking tokens are sent as a dedicated `reasoning_content` field. Applies only when using the `openai_chat` protocol
-- `subscription` (optional): `"zen"`, `"go"`, or `"free"`; defaults to `"zen"`
+- `subscription` (optional): `"zen"` or `"go"`; defaults to `"zen"`
 - `custom_model_api_url` (optional): custom API base URL to use instead of the default OpenCode API
 
 Custom OpenCode models are listed in the model dropdown in the Agent Panel.