diff --git a/config.example.toml b/config.example.toml
index 20ea5f8e..fee1aecf 100644
--- a/config.example.toml
+++ b/config.example.toml
@@ -340,10 +340,10 @@ max_subagents = 10 # optional (1-20)
 # base_url = "https://openrouter.ai/api/v1"
 # model = "deepseek/deepseek-v4-pro"
 # Recent large model IDs also accepted here include arcee-ai/trinity-large-thinking,
-# xiaomi/mimo-v2.5-pro, qwen/qwen3.6-flash, qwen/qwen3.6-35b-a3b,
-# qwen/qwen3.6-max-preview, qwen/qwen3.6-27b, qwen/qwen3.6-plus,
-# google/gemma-4-31b-it, z-ai/glm-5.1, moonshotai/kimi-k2.6, and
-# nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free.
+# minimax/minimax-m3, minimax/minimax-2.7, xiaomi/mimo-v2.5-pro, qwen/qwen3.6-flash,
+# qwen/qwen3.6-35b-a3b, qwen/qwen3.6-max-preview, qwen/qwen3.6-27b, qwen/qwen3.6-plus,
+# qwen/qwen3.7-max, google/gemma-4-31b-it, z-ai/glm-5.1, moonshotai/kimi-k2.6,
+# nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free, and nvidia/nemotron-3-ultra.
 
 # Xiaomi MiMo OpenAI-compatible endpoint (https://platform.xiaomimimo.com)
 [providers.xiaomi_mimo]
@@ -420,6 +420,14 @@ max_subagents = 10 # optional (1-20)
 # base_url = "https://router.huggingface.co/v1"
 # model = "deepseek-ai/DeepSeek-V4-Pro"     # or deepseek-ai/DeepSeek-V4-Flash
 
+# ─────────────────────────────────────────────────────────────────────────────────
+# Together AI Provider (https://www.together.ai/)
+# Env var aliases: TOGETHER_API_KEY, TOGETHER_BASE_URL, TOGETHER_MODEL
+[providers.together]
+# api_key = "YOUR_TOGETHER_API_KEY"
+# base_url = "https://api.together.xyz/v1"
+# model = "deepseek-ai/DeepSeek-V4-Pro"     # or deepseek-ai/DeepSeek-V4-Flash
+
 # ─────────────────────────────────────────────────────────────────────────────────
 # Web Search Provider
 # ─────────────────────────────────────────────────────────────────────────────────
diff --git a/crates/agent/src/lib.rs b/crates/agent/src/lib.rs
index 1d7640f3..7adea12d 100644
--- a/crates/agent/src/lib.rs
+++ b/crates/agent/src/lib.rs
@@ -569,6 +569,59 @@ impl Default for ModelRegistry {
                 supports_tools: true,
                 supports_reasoning: true,
             },
+            // Together AI provider models
+            ModelInfo {
+                id: "deepseek-ai/DeepSeek-V4-Pro".to_string(),
+                provider: ProviderKind::Together,
+                aliases: vec![
+                    "deepseek-v4-pro".to_string(),
+                    "together-deepseek-v4-pro".to_string(),
+                ],
+                supports_tools: true,
+                supports_reasoning: true,
+            },
+            ModelInfo {
+                id: "deepseek-ai/DeepSeek-V4-Flash".to_string(),
+                provider: ProviderKind::Together,
+                aliases: vec![
+                    "deepseek-v4-flash".to_string(),
+                    "deepseek-chat".to_string(),
+                    "together-deepseek-v4-flash".to_string(),
+                ],
+                supports_tools: true,
+                supports_reasoning: true,
+            },
+            // Qwen 3.7 Max (OpenRouter)
+            ModelInfo {
+                id: "qwen/qwen3.7-max".to_string(),
+                provider: ProviderKind::Openrouter,
+                aliases: vec!["qwen3.7-max".to_string(), "qwen-3.7-max".to_string()],
+                supports_tools: true,
+                supports_reasoning: true,
+            },
+            // MiniMax 2.7 (OpenRouter)
+            ModelInfo {
+                id: "minimax/minimax-2.7".to_string(),
+                provider: ProviderKind::Openrouter,
+                aliases: vec![
+                    "minimax-2.7".to_string(),
+                    "minimax-2-7".to_string(),
+                    "openrouter-minimax-2.7".to_string(),
+                ],
+                supports_tools: true,
+                supports_reasoning: true,
+            },
+            // NVIDIA Nemotron 3 Ultra (OpenRouter)
+            ModelInfo {
+                id: "nvidia/nemotron-3-ultra".to_string(),
+                provider: ProviderKind::Openrouter,
+                aliases: vec![
+                    "nemotron-3-ultra".to_string(),
+                    "nvidia-nemotron-3-ultra".to_string(),
+                ],
+                supports_tools: true,
+                supports_reasoning: true,
+            },
         ];
         Self::new(models)
     }
diff --git a/crates/cli/src/lib.rs b/crates/cli/src/lib.rs
index 1b6cc6ab..8e6bd21e 100644
--- a/crates/cli/src/lib.rs
+++ b/crates/cli/src/lib.rs
@@ -765,11 +765,12 @@ fn provider_slot(provider: ProviderKind) -> &'static str {
         ProviderKind::Vllm => "vllm",
         ProviderKind::Ollama => "ollama",
         ProviderKind::Huggingface => "huggingface",
+        ProviderKind::Together => "together",
     }
 }
 
 /// Provider order used by the `auth list` and `auth status` outputs.
-const PROVIDER_LIST: [ProviderKind; 18] = [
+const PROVIDER_LIST: [ProviderKind; 19] = [
     ProviderKind::Deepseek,
     ProviderKind::NvidiaNim,
     ProviderKind::Openai,
@@ -788,6 +789,7 @@ const PROVIDER_LIST: [ProviderKind; 18] = [
     ProviderKind::Vllm,
     ProviderKind::Ollama,
     ProviderKind::Huggingface,
+    ProviderKind::Together,
 ];
 
 #[cfg(test)]
@@ -859,6 +861,7 @@ fn provider_env_vars(provider: ProviderKind) -> &'static [&'static str] {
             "WANJIE_API_KEY",
             "WANJIE_MAAS_API_KEY",
         ],
+        ProviderKind::Together => &["TOGETHER_API_KEY"],
     }
 }
 
diff --git a/crates/config/src/lib.rs b/crates/config/src/lib.rs
index b1d2d0bd..269caf6d 100644
--- a/crates/config/src/lib.rs
+++ b/crates/config/src/lib.rs
@@ -47,6 +47,7 @@ const OPENROUTER_QWEN_3_6_35B_A3B_MODEL: &str = "qwen/qwen3.6-35b-a3b";
 const OPENROUTER_QWEN_3_6_MAX_PREVIEW_MODEL: &str = "qwen/qwen3.6-max-preview";
 const OPENROUTER_QWEN_3_6_27B_MODEL: &str = "qwen/qwen3.6-27b";
 const OPENROUTER_QWEN_3_6_PLUS_MODEL: &str = "qwen/qwen3.6-plus";
+const OPENROUTER_QWEN_3_7_MAX_MODEL: &str = "qwen/qwen3.7-max";
 const OPENROUTER_TENCENT_HY3_PREVIEW_MODEL: &str = "tencent/hy3-preview";
 const OPENROUTER_XIAOMI_MIMO_V2_5_PRO_MODEL: &str = "xiaomi/mimo-v2.5-pro";
 const OPENROUTER_XIAOMI_MIMO_V2_5_MODEL: &str = "xiaomi/mimo-v2.5";
@@ -85,6 +86,9 @@ const DEFAULT_ARCEE_BASE_URL: &str = "https://api.arcee.ai/api/v1";
 const DEFAULT_HUGGINGFACE_MODEL: &str = "deepseek-ai/DeepSeek-V4-Pro";
 const DEFAULT_HUGGINGFACE_FLASH_MODEL: &str = "deepseek-ai/DeepSeek-V4-Flash";
 const DEFAULT_HUGGINGFACE_BASE_URL: &str = "https://router.huggingface.co/v1";
+const DEFAULT_TOGETHER_MODEL: &str = "deepseek-ai/DeepSeek-V4-Pro";
+const DEFAULT_TOGETHER_FLASH_MODEL: &str = "deepseek-ai/DeepSeek-V4-Flash";
+const DEFAULT_TOGETHER_BASE_URL: &str = "https://api.together.xyz/v1";
 const DEFAULT_SGLANG_BASE_URL: &str = "http://localhost:30000/v1";
 const DEFAULT_VLLM_MODEL: &str = "deepseek-ai/DeepSeek-V4-Pro";
 const DEFAULT_VLLM_FLASH_MODEL: &str = "deepseek-ai/DeepSeek-V4-Flash";
@@ -135,10 +139,12 @@ pub enum ProviderKind {
     Ollama,
     #[serde(alias = "hugging-face", alias = "hugging_face", alias = "hf")]
     Huggingface,
+    #[serde(alias = "together-ai", alias = "together_ai")]
+    Together,
 }
 
 impl ProviderKind {
-    pub const ALL: [Self; 18] = [
+    pub const ALL: [Self; 19] = [
         Self::Deepseek,
         Self::NvidiaNim,
         Self::Openai,
@@ -157,6 +163,7 @@ impl ProviderKind {
         Self::Vllm,
         Self::Ollama,
         Self::Huggingface,
+        Self::Together,
     ];
 
     #[must_use]
@@ -180,6 +187,7 @@ impl ProviderKind {
             Self::Vllm => "vllm",
             Self::Ollama => "ollama",
             Self::Huggingface => "huggingface",
+            Self::Together => "together",
         }
     }
 
@@ -209,6 +217,7 @@ impl ProviderKind {
             "vllm" | "v-llm" => Some(Self::Vllm),
             "ollama" | "ollama-local" => Some(Self::Ollama),
             "huggingface" | "hugging-face" | "hugging_face" | "hf" => Some(Self::Huggingface),
+            "together" | "together-ai" | "together_ai" => Some(Self::Together),
             _ => None,
         }
     }
@@ -277,6 +286,8 @@ pub struct ProvidersToml {
     pub ollama: ProviderConfigToml,
     #[serde(default)]
     pub huggingface: ProviderConfigToml,
+    #[serde(default)]
+    pub together: ProviderConfigToml,
 }
 
 /// Sibling `permissions.toml` schema.
@@ -324,6 +335,7 @@ impl ProvidersToml {
             ProviderKind::Vllm => &self.vllm,
             ProviderKind::Ollama => &self.ollama,
             ProviderKind::Huggingface => &self.huggingface,
+            ProviderKind::Together => &self.together,
         }
     }
 
@@ -346,6 +358,7 @@ impl ProvidersToml {
             ProviderKind::Vllm => &mut self.vllm,
             ProviderKind::Ollama => &mut self.ollama,
             ProviderKind::Huggingface => &mut self.huggingface,
+            ProviderKind::Together => &mut self.together,
         }
     }
 }
@@ -1207,6 +1220,12 @@ impl ConfigToml {
             "providers.huggingface.http_headers" => {
                 serialize_http_headers(&self.providers.huggingface.http_headers)
             }
+            "providers.together.api_key" => self.providers.together.api_key.clone(),
+            "providers.together.base_url" => self.providers.together.base_url.clone(),
+            "providers.together.model" => self.providers.together.model.clone(),
+            "providers.together.http_headers" => {
+                serialize_http_headers(&self.providers.together.http_headers)
+            }
             _ => self.extras.get(key).map(toml::Value::to_string),
         }
     }
@@ -1458,6 +1477,18 @@ impl ConfigToml {
             "providers.huggingface.http_headers" => {
                 self.providers.huggingface.http_headers = parse_http_headers(value)?;
             }
+            "providers.together.api_key" => {
+                self.providers.together.api_key = Some(value.to_string());
+            }
+            "providers.together.base_url" => {
+                self.providers.together.base_url = Some(value.to_string());
+            }
+            "providers.together.model" => {
+                self.providers.together.model = Some(value.to_string());
+            }
+            "providers.together.http_headers" => {
+                self.providers.together.http_headers = parse_http_headers(value)?;
+            }
             _ => {
                 self.extras
                     .insert(key.to_string(), toml::Value::String(value.to_string()));
@@ -1577,6 +1608,10 @@ impl ConfigToml {
             "providers.huggingface.base_url" => self.providers.huggingface.base_url = None,
             "providers.huggingface.model" => self.providers.huggingface.model = None,
             "providers.huggingface.http_headers" => self.providers.huggingface.http_headers.clear(),
+            "providers.together.api_key" => self.providers.together.api_key = None,
+            "providers.together.base_url" => self.providers.together.base_url = None,
+            "providers.together.model" => self.providers.together.model = None,
+            "providers.together.http_headers" => self.providers.together.http_headers.clear(),
             _ => {
                 self.extras.remove(key);
             }
@@ -1959,6 +1994,7 @@ impl ConfigToml {
                 ProviderKind::Vllm => DEFAULT_VLLM_BASE_URL.to_string(),
                 ProviderKind::Ollama => DEFAULT_OLLAMA_BASE_URL.to_string(),
                 ProviderKind::Huggingface => DEFAULT_HUGGINGFACE_BASE_URL.to_string(),
+                ProviderKind::Together => DEFAULT_TOGETHER_BASE_URL.to_string(),
             })
         };
         // CLI flag wins outright. Otherwise: config-file → injected secrets/env.
@@ -2251,6 +2287,14 @@ fn normalize_model_for_provider(provider: ProviderKind, model: &str) -> String {
             "deepseek-v4-flash" | "deepseek-v4flash" | "deepseek-chat" | "deepseek-reasoner"
             | "deepseek-r1" | "deepseek-v3" | "deepseek-v3.2",
         ) => DEFAULT_HUGGINGFACE_FLASH_MODEL.to_string(),
+        (ProviderKind::Together, "deepseek-v4-pro" | "deepseek-v4pro") => {
+            DEFAULT_TOGETHER_MODEL.to_string()
+        }
+        (
+            ProviderKind::Together,
+            "deepseek-v4-flash" | "deepseek-v4flash" | "deepseek-chat" | "deepseek-reasoner"
+            | "deepseek-r1" | "deepseek-v3" | "deepseek-v3.2",
+        ) => DEFAULT_TOGETHER_FLASH_MODEL.to_string(),
         _ => model.to_string(),
     }
 }
@@ -2342,6 +2386,9 @@ fn canonical_openrouter_recent_model_id(model: &str) -> Option<&'static str> {
         OPENROUTER_QWEN_3_6_PLUS_MODEL | "qwen3.6-plus" | "qwen-3.6-plus" => {
             Some(OPENROUTER_QWEN_3_6_PLUS_MODEL)
         }
+        OPENROUTER_QWEN_3_7_MAX_MODEL | "qwen3.7-max" | "qwen-3.7-max" => {
+            Some(OPENROUTER_QWEN_3_7_MAX_MODEL)
+        }
         OPENROUTER_TENCENT_HY3_PREVIEW_MODEL | "hy3-preview" | "tencent-hy3-preview" => {
             Some(OPENROUTER_TENCENT_HY3_PREVIEW_MODEL)
         }
@@ -2378,6 +2425,7 @@ fn default_model_for_provider(provider: ProviderKind) -> &'static str {
         ProviderKind::Vllm => DEFAULT_VLLM_MODEL,
         ProviderKind::Ollama => DEFAULT_OLLAMA_MODEL,
         ProviderKind::Huggingface => DEFAULT_HUGGINGFACE_MODEL,
+        ProviderKind::Together => DEFAULT_TOGETHER_MODEL,
     }
 }
 
@@ -2401,6 +2449,7 @@ fn default_base_url_for_provider(provider: ProviderKind) -> &'static str {
         ProviderKind::Vllm => DEFAULT_VLLM_BASE_URL,
         ProviderKind::Ollama => DEFAULT_OLLAMA_BASE_URL,
         ProviderKind::Huggingface => DEFAULT_HUGGINGFACE_BASE_URL,
+        ProviderKind::Together => DEFAULT_TOGETHER_BASE_URL,
     }
 }
 
@@ -3149,6 +3198,8 @@ struct EnvRuntimeOverrides {
     ollama_base_url: Option<String>,
     huggingface_base_url: Option<String>,
     huggingface_model: Option<String>,
+    together_base_url: Option<String>,
+    together_model: Option<String>,
 }
 
 impl EnvRuntimeOverrides {
@@ -3298,6 +3349,12 @@ impl EnvRuntimeOverrides {
                 .or_else(|_| std::env::var("HF_MODEL"))
                 .ok()
                 .filter(|v| !v.trim().is_empty()),
+            together_base_url: std::env::var("TOGETHER_BASE_URL")
+                .ok()
+                .filter(|v| !v.trim().is_empty()),
+            together_model: std::env::var("TOGETHER_MODEL")
+                .ok()
+                .filter(|v| !v.trim().is_empty()),
         }
     }
 
@@ -3324,6 +3381,7 @@ impl EnvRuntimeOverrides {
             ProviderKind::Vllm => self.vllm_base_url.clone(),
             ProviderKind::Ollama => self.ollama_base_url.clone(),
             ProviderKind::Huggingface => self.huggingface_base_url.clone(),
+            ProviderKind::Together => self.together_base_url.clone(),
         }
     }
 
@@ -3341,6 +3399,7 @@ impl EnvRuntimeOverrides {
             ProviderKind::Novita => self.novita_model.clone(),
             ProviderKind::Fireworks => self.fireworks_model.clone(),
             ProviderKind::Huggingface => self.huggingface_model.clone(),
+            ProviderKind::Together => self.together_model.clone(),
             _ => None,
         }?;
 
diff --git a/crates/config/src/provider.rs b/crates/config/src/provider.rs
index 73fb96a2..bef2f10b 100644
--- a/crates/config/src/provider.rs
+++ b/crates/config/src/provider.rs
@@ -14,6 +14,7 @@ use super::{
     DEFAULT_OPENAI_BASE_URL, DEFAULT_OPENAI_MODEL, DEFAULT_OPENROUTER_BASE_URL,
     DEFAULT_OPENROUTER_MODEL, DEFAULT_SGLANG_BASE_URL, DEFAULT_SGLANG_MODEL,
     DEFAULT_SILICONFLOW_BASE_URL, DEFAULT_SILICONFLOW_CN_BASE_URL, DEFAULT_SILICONFLOW_MODEL,
+    DEFAULT_TOGETHER_BASE_URL, DEFAULT_TOGETHER_MODEL,
     DEFAULT_VLLM_BASE_URL, DEFAULT_VLLM_MODEL, DEFAULT_VOLCENGINE_BASE_URL,
     DEFAULT_VOLCENGINE_MODEL, DEFAULT_WANJIE_ARK_BASE_URL, DEFAULT_WANJIE_ARK_MODEL,
     DEFAULT_XIAOMI_MIMO_BASE_URL, DEFAULT_XIAOMI_MIMO_MODEL, ProviderKind,
@@ -274,6 +275,15 @@ provider!(
     ["HUGGINGFACE_API_KEY", "HF_TOKEN"],
     "huggingface"
 );
+provider!(
+    Together,
+    Together,
+    "Together AI",
+    DEFAULT_TOGETHER_BASE_URL,
+    DEFAULT_TOGETHER_MODEL,
+    ["TOGETHER_API_KEY"],
+    "together"
+);
 
 static DEEPSEEK: Deepseek = Deepseek;
 static NVIDIA_NIM: NvidiaNim = NvidiaNim;
@@ -293,8 +303,9 @@ static SGLANG: Sglang = Sglang;
 static VLLM: Vllm = Vllm;
 static OLLAMA: Ollama = Ollama;
 static HUGGINGFACE: Huggingface = Huggingface;
+static TOGETHER: Together = Together;
 
-static PROVIDER_REGISTRY: [&dyn Provider; 18] = [
+static PROVIDER_REGISTRY: [&dyn Provider; 19] = [
     &DEEPSEEK,
     &NVIDIA_NIM,
     &OPENAI,
@@ -313,6 +324,7 @@ static PROVIDER_REGISTRY: [&dyn Provider; 18] = [
     &VLLM,
     &OLLAMA,
     &HUGGINGFACE,
+    &TOGETHER,
 ];
 
 /// Return all built-in provider metadata entries in `ProviderKind::ALL` order.
@@ -359,5 +371,6 @@ pub fn provider_for_kind(kind: ProviderKind) -> &'static dyn Provider {
         ProviderKind::Vllm => &VLLM,
         ProviderKind::Ollama => &OLLAMA,
         ProviderKind::Huggingface => &HUGGINGFACE,
+        ProviderKind::Together => &TOGETHER,
     }
 }
diff --git a/crates/tui/src/client.rs b/crates/tui/src/client.rs
index a0fa8ca6..a9bdf149 100644
--- a/crates/tui/src/client.rs
+++ b/crates/tui/src/client.rs
@@ -1204,7 +1204,8 @@ pub(super) fn apply_reasoning_effort(
             | ApiProvider::Siliconflow
             | ApiProvider::SiliconflowCn
             | ApiProvider::Sglang
-            | ApiProvider::Volcengine => {
+            | ApiProvider::Volcengine
+            | ApiProvider::Together => {
                 body["thinking"] = json!({ "type": "disabled" });
             }
             ApiProvider::Fireworks => {}
@@ -1246,10 +1247,10 @@ pub(super) fn apply_reasoning_effort(
                 body["reasoning_effort"] = json!("high");
                 body["thinking"] = json!({ "type": "enabled" });
             }
-            // OpenRouter/Novita: pass through the actual user-chosen value.
+            // OpenRouter/Novita/Together: pass through the actual user-chosen value.
             // OpenRouter's unified scale is none/minimal/low/medium/high/xhigh;
             // DeepSeek models hosted there accept those directly.
-            ApiProvider::Openrouter | ApiProvider::Novita => {
+            ApiProvider::Openrouter | ApiProvider::Novita | ApiProvider::Together => {
                 let value = match normalized.as_str() {
                     "low" | "minimal" => "low",
                     "medium" | "mid" => "medium",
@@ -1308,7 +1309,7 @@ pub(super) fn apply_reasoning_effort(
                 body["reasoning_effort"] = json!("max");
                 body["thinking"] = json!({ "type": "enabled" });
             }
-            ApiProvider::Openrouter | ApiProvider::Novita => {
+            ApiProvider::Openrouter | ApiProvider::Novita | ApiProvider::Together => {
                 body["reasoning_effort"] = json!("xhigh");
                 body["thinking"] = json!({ "type": "enabled" });
             }
diff --git a/crates/tui/src/config.rs b/crates/tui/src/config.rs
index be3bd836..56ba7164 100644
--- a/crates/tui/src/config.rs
+++ b/crates/tui/src/config.rs
@@ -75,6 +75,9 @@ pub const OPENROUTER_QWEN_3_6_35B_A3B_MODEL: &str = "qwen/qwen3.6-35b-a3b";
 pub const OPENROUTER_QWEN_3_6_MAX_PREVIEW_MODEL: &str = "qwen/qwen3.6-max-preview";
 pub const OPENROUTER_QWEN_3_6_27B_MODEL: &str = "qwen/qwen3.6-27b";
 pub const OPENROUTER_QWEN_3_6_PLUS_MODEL: &str = "qwen/qwen3.6-plus";
+pub const OPENROUTER_QWEN_3_7_MAX_MODEL: &str = "qwen/qwen3.7-max";
+pub const OPENROUTER_MINIMAX_2_7_MODEL: &str = "minimax/minimax-2.7";
+pub const OPENROUTER_NEMOTRON_3_ULTRA_MODEL: &str = "nvidia/nemotron-3-ultra";
 pub const OPENROUTER_TENCENT_HY3_PREVIEW_MODEL: &str = "tencent/hy3-preview";
 pub const OPENROUTER_XIAOMI_MIMO_V2_5_PRO_MODEL: &str = "xiaomi/mimo-v2.5-pro";
 pub const OPENROUTER_XIAOMI_MIMO_V2_5_MODEL: &str = "xiaomi/mimo-v2.5";
@@ -88,6 +91,9 @@ pub const RECENT_OPENROUTER_LARGE_MODELS: &[&str] = &[
     OPENROUTER_QWEN_3_6_MAX_PREVIEW_MODEL,
     OPENROUTER_QWEN_3_6_27B_MODEL,
     OPENROUTER_QWEN_3_6_PLUS_MODEL,
+    OPENROUTER_QWEN_3_7_MAX_MODEL,
+    OPENROUTER_MINIMAX_2_7_MODEL,
+    OPENROUTER_NEMOTRON_3_ULTRA_MODEL,
     OPENROUTER_KIMI_K2_6_MODEL,
     OPENROUTER_GLM_5_1_MODEL,
     OPENROUTER_TENCENT_HY3_PREVIEW_MODEL,
@@ -136,6 +142,8 @@ pub const DEFAULT_OLLAMA_BASE_URL: &str = "http://localhost:11434/v1";
 pub const DEFAULT_HUGGINGFACE_MODEL: &str = "deepseek-ai/DeepSeek-V4-Pro";
 pub const DEFAULT_HUGGINGFACE_FLASH_MODEL: &str = "deepseek-ai/DeepSeek-V4-Flash";
 pub const DEFAULT_HUGGINGFACE_BASE_URL: &str = "https://router.huggingface.co/v1";
+pub const DEFAULT_TOGETHER_MODEL: &str = "deepseek-ai/DeepSeek-V4-Pro";
+pub const DEFAULT_TOGETHER_BASE_URL: &str = "https://api.together.xyz/v1";
 /// Legacy `deepseek-cn` provider alias.
 ///
 /// DeepSeek's official API host is the same worldwide. Keep this alias for
@@ -176,6 +184,7 @@ pub enum ApiProvider {
     Vllm,
     Ollama,
     Huggingface,
+    Together,
 }
 
 impl ApiProvider {
@@ -224,6 +233,7 @@ impl ApiProvider {
             "vllm" | "v-llm" => Some(Self::Vllm),
             "ollama" | "ollama-local" => Some(Self::Ollama),
             "huggingface" | "hugging-face" | "hugging_face" | "hf" => Some(Self::Huggingface),
+            "together" | "together-ai" | "together_ai" => Some(Self::Together),
             _ => None,
         }
     }
@@ -250,6 +260,7 @@ impl ApiProvider {
             Self::Vllm => "vllm",
             Self::Ollama => "ollama",
             Self::Huggingface => "huggingface",
+            Self::Together => "together",
         }
     }
 
@@ -276,6 +287,7 @@ impl ApiProvider {
             Self::Vllm => "vLLM",
             Self::Ollama => "Ollama",
             Self::Huggingface => "Hugging Face",
+            Self::Together => "Together AI",
         }
     }
 
@@ -301,6 +313,7 @@ impl ApiProvider {
             Self::Vllm,
             Self::Ollama,
             Self::Huggingface,
+            Self::Together,
         ]
     }
 }
@@ -616,6 +629,9 @@ fn canonical_openrouter_recent_model_id(model: &str) -> Option<&'static str> {
         OPENROUTER_QWEN_3_6_PLUS_MODEL | "qwen3.6-plus" | "qwen-3.6-plus" => {
             Some(OPENROUTER_QWEN_3_6_PLUS_MODEL)
         }
+        OPENROUTER_QWEN_3_7_MAX_MODEL | "qwen3.7-max" | "qwen-3.7-max" => {
+            Some(OPENROUTER_QWEN_3_7_MAX_MODEL)
+        }
         OPENROUTER_TENCENT_HY3_PREVIEW_MODEL | "hy3-preview" | "tencent-hy3-preview" => {
             Some(OPENROUTER_TENCENT_HY3_PREVIEW_MODEL)
         }
@@ -800,6 +816,7 @@ pub fn model_completion_names_for_provider(provider: ApiProvider) -> Vec<&'stati
         ApiProvider::Volcengine => vec![DEFAULT_VOLCENGINE_MODEL, DEFAULT_VOLCENGINE_FLASH_MODEL],
         ApiProvider::Ollama => Vec::new(),
         ApiProvider::Openai | ApiProvider::Atlascloud => OFFICIAL_DEEPSEEK_MODELS.to_vec(),
+        ApiProvider::Together => vec![DEFAULT_TOGETHER_MODEL],
     }
 }
 
@@ -1939,6 +1956,8 @@ pub struct ProvidersConfig {
     pub ollama: ProviderConfig,
     #[serde(default, alias = "hugging-face", alias = "hf")]
     pub huggingface: ProviderConfig,
+    #[serde(default, alias = "together-ai")]
+    pub together: ProviderConfig,
 }
 
 #[derive(Debug, Clone, Deserialize, Default)]
@@ -2102,6 +2121,7 @@ impl Config {
             ApiProvider::Volcengine => "providers.volcengine",
             ApiProvider::Huggingface => "providers.huggingface",
             ApiProvider::NvidiaNim => "providers.nvidia_nim",
+            ApiProvider::Together => "providers.together",
             ApiProvider::Deepseek | ApiProvider::DeepseekCN => return,
         };
         tracing::warn!(
@@ -2249,6 +2269,7 @@ impl Config {
             ApiProvider::Ollama => &providers.ollama,
             ApiProvider::Volcengine => &providers.volcengine,
             ApiProvider::Huggingface => &providers.huggingface,
+            ApiProvider::Together => &providers.together,
         })
     }
 
@@ -2273,6 +2294,7 @@ impl Config {
             ApiProvider::Ollama => &mut providers.ollama,
             ApiProvider::Volcengine => &mut providers.volcengine,
             ApiProvider::Huggingface => &mut providers.huggingface,
+            ApiProvider::Together => &mut providers.together,
         }
     }
 
@@ -2384,6 +2406,7 @@ impl Config {
             ApiProvider::Ollama => DEFAULT_OLLAMA_MODEL,
             ApiProvider::Volcengine => DEFAULT_VOLCENGINE_MODEL,
             ApiProvider::Huggingface => DEFAULT_HUGGINGFACE_MODEL,
+            ApiProvider::Together => DEFAULT_TOGETHER_MODEL,
         }
         .to_string()
     }
@@ -2419,9 +2442,10 @@ impl Config {
             | ApiProvider::Moonshot
             | ApiProvider::Sglang
             | ApiProvider::Vllm
-            | ApiProvider::Ollama
+            |             ApiProvider::Ollama
             | ApiProvider::Volcengine
-            | ApiProvider::Huggingface => None,
+            | ApiProvider::Huggingface
+            | ApiProvider::Together => None,
         };
         let configured_base_url = provider_base.or(root_base);
         let base = if provider == ApiProvider::XiaomiMimo {
@@ -2466,6 +2490,7 @@ impl Config {
                     ApiProvider::Ollama => DEFAULT_OLLAMA_BASE_URL,
                     ApiProvider::Volcengine => DEFAULT_VOLCENGINE_BASE_URL,
                     ApiProvider::Huggingface => DEFAULT_HUGGINGFACE_BASE_URL,
+                    ApiProvider::Together => DEFAULT_TOGETHER_BASE_URL,
                 }
                 .to_string()
             })
@@ -2513,6 +2538,7 @@ impl Config {
             ApiProvider::Ollama => "ollama",
             ApiProvider::Volcengine => "volcengine",
             ApiProvider::Huggingface => "huggingface",
+            ApiProvider::Together => "together",
         };
 
         // 0. DeepSeek compatibility slot. The legacy top-level `api_key`
@@ -2652,6 +2678,10 @@ impl Config {
                  For a Kimi Code plan key, set [providers.moonshot] base_url = \
                  \"https://api.kimi.com/coding/v1\" and model = \"kimi-for-coding\"."
             ),
+            ApiProvider::Together => anyhow::bail!(
+                "Together AI API key not found. Run 'codewhale auth set --provider together', \
+                 set TOGETHER_API_KEY, or add [providers.together] api_key in ~/.codewhale/config.toml."
+            ),
             // Self-hosted deployments commonly run without auth on localhost.
             // Return an empty key and let the client omit the Authorization header.
             ApiProvider::Sglang | ApiProvider::Vllm | ApiProvider::Ollama => Ok(String::new()),
@@ -3451,6 +3481,13 @@ fn apply_env_overrides(config: &mut Config) {
                     .huggingface
                     .base_url = Some(value);
             }
+            ApiProvider::Together => {
+                config
+                    .providers
+                    .get_or_insert_with(ProvidersConfig::default)
+                    .together
+                    .base_url = Some(value);
+            }
         }
     }
     if matches!(config.api_provider(), ApiProvider::NvidiaNim)
@@ -3657,6 +3694,7 @@ fn apply_env_overrides(config: &mut Config) {
             ApiProvider::Ollama => &mut providers.ollama,
             ApiProvider::Volcengine => &mut providers.volcengine,
             ApiProvider::Huggingface => &mut providers.huggingface,
+            ApiProvider::Together => &mut providers.together,
         };
         let mut provider_headers = entry.http_headers.clone().unwrap_or_default();
         provider_headers.extend(headers);
@@ -3851,6 +3889,7 @@ fn apply_env_overrides(config: &mut Config) {
                 ApiProvider::Ollama => &mut providers.ollama,
                 ApiProvider::Volcengine => &mut providers.volcengine,
                 ApiProvider::Huggingface => &mut providers.huggingface,
+                ApiProvider::Together => &mut providers.together,
             };
             entry.model = Some(value);
         }
@@ -4173,6 +4212,7 @@ fn default_base_url_for_provider(provider: ApiProvider) -> &'static str {
         ApiProvider::Ollama => DEFAULT_OLLAMA_BASE_URL,
         ApiProvider::Volcengine => DEFAULT_VOLCENGINE_BASE_URL,
         ApiProvider::Huggingface => DEFAULT_HUGGINGFACE_BASE_URL,
+        ApiProvider::Together => DEFAULT_TOGETHER_BASE_URL,
     }
 }
 
@@ -4594,6 +4634,7 @@ fn merge_providers(
             ollama: merge_provider_config(base.ollama, override_cfg.ollama),
             volcengine: merge_provider_config(base.volcengine, override_cfg.volcengine),
             huggingface: merge_provider_config(base.huggingface, override_cfg.huggingface),
+            together: merge_provider_config(base.together, override_cfg.together),
         }),
     }
 }
@@ -5080,6 +5121,9 @@ pub fn active_provider_has_env_api_key(config: &Config) -> bool {
                 || std::env::var("VOLCENGINE_ARK_API_KEY").is_ok_and(|k| !k.trim().is_empty())
                 || std::env::var("ARK_API_KEY").is_ok_and(|k| !k.trim().is_empty())
         }
+        ApiProvider::Together => {
+            std::env::var("TOGETHER_API_KEY").is_ok_and(|k| !k.trim().is_empty())
+        }
     }
 }
 
@@ -5106,6 +5150,7 @@ pub fn has_api_key_for(config: &Config, provider: ApiProvider) -> bool {
         ApiProvider::Siliconflow | ApiProvider::SiliconflowCn => "SILICONFLOW_API_KEY",
         ApiProvider::Arcee => "ARCEE_API_KEY",
         ApiProvider::Huggingface => "HUGGINGFACE_API_KEY",
+        ApiProvider::Together => "TOGETHER_API_KEY",
         ApiProvider::Moonshot => "MOONSHOT_API_KEY",
         ApiProvider::Sglang => "SGLANG_API_KEY",
         ApiProvider::Vllm => "VLLM_API_KEY",
@@ -5227,6 +5272,7 @@ pub fn save_api_key_for(provider: ApiProvider, api_key: &str) -> Result<PathBuf>
         ApiProvider::Vllm => "providers.vllm",
         ApiProvider::Ollama => "providers.ollama",
         ApiProvider::Volcengine => "providers.volcengine",
+        ApiProvider::Together => "providers.together",
     };
 
     // Parse existing TOML (or start fresh) so we can edit the right table
@@ -5270,6 +5316,7 @@ pub fn save_api_key_for(provider: ApiProvider, api_key: &str) -> Result<PathBuf>
         ApiProvider::Vllm => "vllm",
         ApiProvider::Ollama => "ollama",
         ApiProvider::Volcengine => "volcengine",
+        ApiProvider::Together => "together",
     };
     let entry = providers
         .entry(key_inside.to_string())
@@ -5365,6 +5412,7 @@ fn provider_config_key(provider: ApiProvider) -> Result<&'static str> {
         ApiProvider::Sglang => Ok("sglang"),
         ApiProvider::Vllm => Ok("vllm"),
         ApiProvider::Ollama => Ok("ollama"),
+        ApiProvider::Together => Ok("together"),
     }
 }
 
diff --git a/crates/tui/src/config_persistence.rs b/crates/tui/src/config_persistence.rs
index aa79793c..8c97cb82 100644
--- a/crates/tui/src/config_persistence.rs
+++ b/crates/tui/src/config_persistence.rs
@@ -218,6 +218,7 @@ fn provider_base_url_table_key(provider: ApiProvider) -> anyhow::Result<&'static
         ApiProvider::Sglang => Ok("sglang"),
         ApiProvider::Vllm => Ok("vllm"),
         ApiProvider::Ollama => Ok("ollama"),
+        ApiProvider::Together => Ok("together"),
     }
 }
 
diff --git a/crates/tui/src/core/engine.rs b/crates/tui/src/core/engine.rs
index 86c146b4..2a4b6f9e 100644
--- a/crates/tui/src/core/engine.rs
+++ b/crates/tui/src/core/engine.rs
@@ -614,6 +614,7 @@ impl Engine {
             ApiProvider::Vllm => "VLLM_API_KEY",
             ApiProvider::Ollama => "OLLAMA_API_KEY",
             ApiProvider::Huggingface => "HUGGINGFACE_API_KEY/HF_TOKEN",
+            ApiProvider::Together => "TOGETHER_API_KEY",
         };
 
         Some(format!(
diff --git a/crates/tui/src/main.rs b/crates/tui/src/main.rs
index 0c4f2f0a..db897bc2 100644
--- a/crates/tui/src/main.rs
+++ b/crates/tui/src/main.rs
@@ -2044,6 +2044,10 @@ fn run_setup_status(config: &Config, workspace: &Path) -> Result<()> {
                     "HUGGINGFACE_API_KEY/HF_TOKEN",
                     "codewhale auth set --provider huggingface",
                 ),
+                crate::config::ApiProvider::Together => (
+                    "TOGETHER_API_KEY",
+                    "codewhale auth set --provider together --api-key \"...\"",
+                ),
                 crate::config::ApiProvider::Deepseek | crate::config::ApiProvider::DeepseekCN => {
                     ("DEEPSEEK_API_KEY", "codewhale auth set --provider deepseek")
                 }
@@ -2069,6 +2073,7 @@ fn run_setup_status(config: &Config, workspace: &Path) -> Result<()> {
                     crate::config::ApiProvider::Vllm => "vllm",
                     crate::config::ApiProvider::Ollama => "ollama",
                     crate::config::ApiProvider::Huggingface => "huggingface",
+                    crate::config::ApiProvider::Together => "together",
                     crate::config::ApiProvider::Deepseek
                     | crate::config::ApiProvider::DeepseekCN => "deepseek",
                 }
diff --git a/crates/tui/src/tui/provider_picker.rs b/crates/tui/src/tui/provider_picker.rs
index 5cdfc3f2..accc52ab 100644
--- a/crates/tui/src/tui/provider_picker.rs
+++ b/crates/tui/src/tui/provider_picker.rs
@@ -118,6 +118,7 @@ impl ProviderPickerView {
             ApiProvider::Vllm => "VLLM_API_KEY",
             ApiProvider::Ollama => "OLLAMA_API_KEY",
             ApiProvider::Huggingface => "HUGGINGFACE_API_KEY / HF_TOKEN",
+            ApiProvider::Together => "TOGETHER_API_KEY",
         }
     }
 
@@ -508,7 +509,8 @@ mod tests {
                 "SGLang",
                 "vLLM",
                 "Ollama",
-                "Hugging Face"
+                "Hugging Face",
+                "Together AI"
             ]
         );
     }
@@ -543,7 +545,7 @@ mod tests {
         let mut picker = ProviderPickerView::new(ApiProvider::Deepseek, &config);
 
         picker.handle_key(key(KeyCode::Up));
-        assert_eq!(picker.selected_provider(), ApiProvider::Huggingface);
+        assert_eq!(picker.selected_provider(), ApiProvider::Together);
 
         picker.handle_key(key(KeyCode::Down));
         assert_eq!(picker.selected_provider(), ApiProvider::Deepseek);
diff --git a/crates/tui/src/tui/ui.rs b/crates/tui/src/tui/ui.rs
index 9320f7d9..97c44341 100644
--- a/crates/tui/src/tui/ui.rs
+++ b/crates/tui/src/tui/ui.rs
@@ -7173,6 +7173,7 @@ fn render(f: &mut Frame, app: &mut App) {
             crate::config::ApiProvider::Vllm => Some("vLLM"),
             crate::config::ApiProvider::Ollama => Some("Ollama"),
             crate::config::ApiProvider::Huggingface => Some("HF"),
+            crate::config::ApiProvider::Together => Some("Together"),
         };
         let status_indicator_started_at = if app.low_motion {
             None
@@ -8213,6 +8214,7 @@ async fn apply_provider_picker_api_key(
             ApiProvider::Vllm => &mut providers.vllm,
             ApiProvider::Ollama => &mut providers.ollama,
             ApiProvider::Huggingface => &mut providers.huggingface,
+            ApiProvider::Together => &mut providers.together,
         };
         entry.api_key = Some(api_key);
     }
@@ -8270,6 +8272,7 @@ fn set_provider_auth_mode_in_memory(config: &mut Config, provider: ApiProvider,
         ApiProvider::Vllm => &mut providers.vllm,
         ApiProvider::Ollama => &mut providers.ollama,
         ApiProvider::Huggingface => &mut providers.huggingface,
+        ApiProvider::Together => &mut providers.together,
     };
     entry.auth_mode = Some(auth_mode);
 }
diff --git a/docs/CONFIGURATION.md b/docs/CONFIGURATION.md
index 01e38485..b9b2620e 100644
--- a/docs/CONFIGURATION.md
+++ b/docs/CONFIGURATION.md
@@ -860,7 +860,7 @@ If you are upgrading from older releases:
 - `base_url` (string, optional): defaults to `https://api.deepseek.com/beta` for DeepSeek's OpenAI-compatible Chat Completions API, including legacy `provider = "deepseek-cn"` configs. Other defaults are `https://integrate.api.nvidia.com/v1` for `nvidia-nim`, `https://api.openai.com/v1` for `openai`, `https://api.atlascloud.ai/v1` for `atlascloud`, `https://maas-openapi.wanjiedata.com/api/v1` for `wanjie-ark`, `https://ark.cn-beijing.volces.com/api/coding/v3` for `volcengine`, `https://openrouter.ai/api/v1` for `openrouter`, `https://token-plan-sgp.xiaomimimo.com/v1` for `xiaomi-mimo` when the API key starts with `tp-...` and `https://api.xiaomimimo.com/v1` otherwise, `https://api.novita.ai/v1` for `novita`, `https://api.fireworks.ai/inference/v1` for `fireworks`, `https://api.siliconflow.com/v1` for `siliconflow`, `https://api.siliconflow.cn/v1` for `siliconflow-CN`, `https://api.arcee.ai/api/v1` for `arcee`, `https://api.moonshot.ai/v1` for `moonshot`, `http://localhost:30000/v1` for `sglang`, `http://localhost:8000/v1` for `vllm`, and `http://localhost:11434/v1` for `ollama`. Set `base_url = "https://token-plan-cn.xiaomimimo.com/v1"` explicitly if your Xiaomi MiMo Token Plan account is provisioned in the China region. Set `https://api.deepseek.com` or `https://api.deepseek.com/v1` explicitly to opt out of DeepSeek beta features.
 - `path_suffix` (string, optional provider-table key): override the chat-completions path for OpenAI-compatible gateways that do not serve `/v1/chat/completions`. For example, `[providers.openai] path_suffix = "/chat/completions"` sends chat requests to the unversioned base URL plus `/chat/completions`; `models` and `beta/*` requests keep their normal routing.
 - `insecure_skip_tls_verify` (bool, optional provider-table key): disabled by default. When true on the active provider table, only the LLM provider HTTP client skips TLS certificate verification. Prefer `SSL_CERT_FILE` for corporate or private CA bundles; `codewhale doctor` reports this setting when enabled.
-- `default_text_model` (string, optional): defaults to `deepseek-v4-pro` for DeepSeek and generic OpenAI-compatible endpoints, `deepseek-ai/deepseek-v4-pro` for NVIDIA NIM, `deepseek-ai/deepseek-v4-flash` for AtlasCloud, `deepseek-reasoner` for Wanjie Ark, `DeepSeek-V4-Pro` for Volcengine Ark, `deepseek/deepseek-v4-pro` for OpenRouter and Novita, `mimo-v2.5-pro` for Xiaomi MiMo, `accounts/fireworks/models/deepseek-v4-pro` for Fireworks, `deepseek-ai/DeepSeek-V4-Pro` for SiliconFlow, `trinity-large-thinking` for Arcee AI, `kimi-k2.6` for Moonshot, `deepseek-ai/DeepSeek-V4-Pro` for SGLang/vLLM, and `deepseek-coder:1.3b` for Ollama. Current public DeepSeek IDs are `deepseek-v4-pro` and `deepseek-v4-flash`, both with 1M context windows, 384K max output, and thinking mode enabled by default. Legacy `deepseek-chat` and `deepseek-reasoner` remain compatibility aliases for `deepseek-v4-flash` until July 24, 2026, except SiliconFlow maps `deepseek-reasoner` and `deepseek-r1` to its Pro model while `deepseek-chat` and `deepseek-v3` map to Flash. Provider-specific mappings translate `deepseek-v4-pro` / `deepseek-v4-flash` to each provider's model ID where supported. OpenRouter also recognizes recent large IDs such as `arcee-ai/trinity-large-thinking`, `minimax/minimax-m3`, `xiaomi/mimo-v2.5-pro`, `qwen/qwen3.6-flash`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.6-max-preview`, `qwen/qwen3.6-27b`, `qwen/qwen3.6-plus`, `google/gemma-4-31b-it`, and `moonshotai/kimi-k2.6`; direct Arcee uses bare IDs such as `trinity-large-thinking` and `trinity-large-preview`; direct Xiaomi MiMo recognizes chat IDs `mimo-v2.5-pro` and `mimo-v2.5`, while TTS IDs are selected through `codewhale speech` / `tts`. Generic `openai`, `atlascloud`, `wanjie-ark`, `xiaomi-mimo`, `arcee`, and Ollama model IDs are passed through unchanged after known aliases are normalized. OpenRouter and SiliconFlow provider configs with a custom `base_url` also preserve explicit model values, which lets OpenAI-compatible gateways accept bare model IDs. Use `/models` or `codewhale models` to discover live IDs from your configured endpoint. `CODEWHALE_MODEL` overrides this for a single process; `DEEPSEEK_MODEL` is the legacy alias.
+- `default_text_model` (string, optional): defaults to `deepseek-v4-pro` for DeepSeek and generic OpenAI-compatible endpoints, `deepseek-ai/deepseek-v4-pro` for NVIDIA NIM, `deepseek-ai/deepseek-v4-flash` for AtlasCloud, `deepseek-reasoner` for Wanjie Ark, `DeepSeek-V4-Pro` for Volcengine Ark, `deepseek/deepseek-v4-pro` for OpenRouter and Novita, `mimo-v2.5-pro` for Xiaomi MiMo, `accounts/fireworks/models/deepseek-v4-pro` for Fireworks, `deepseek-ai/DeepSeek-V4-Pro` for SiliconFlow, `trinity-large-thinking` for Arcee AI, `kimi-k2.6` for Moonshot, `deepseek-ai/DeepSeek-V4-Pro` for SGLang/vLLM, and `deepseek-coder:1.3b` for Ollama. Hugging Face and Together AI both default to `deepseek-ai/DeepSeek-V4-Pro`. Current public DeepSeek IDs are `deepseek-v4-pro` and `deepseek-v4-flash`, both with 1M context windows, 384K max output, and thinking mode enabled by default. Legacy `deepseek-chat` and `deepseek-reasoner` remain compatibility aliases for `deepseek-v4-flash` until July 24, 2026, except SiliconFlow maps `deepseek-reasoner` and `deepseek-r1` to its Pro model while `deepseek-chat` and `deepseek-v3` map to Flash. Provider-specific mappings translate `deepseek-v4-pro` / `deepseek-v4-flash` to each provider's model ID where supported. OpenRouter also recognizes recent large IDs such as `arcee-ai/trinity-large-thinking`, `minimax/minimax-m3`, `minimax/minimax-2.7`, `xiaomi/mimo-v2.5-pro`, `qwen/qwen3.6-flash`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.6-max-preview`, `qwen/qwen3.6-27b`, `qwen/qwen3.6-plus`, `qwen/qwen3.7-max`, `google/gemma-4-31b-it`, `moonshotai/kimi-k2.6`, `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`, and `nvidia/nemotron-3-ultra`; direct Arcee uses bare IDs such as `trinity-large-thinking` and `trinity-large-preview`; direct Xiaomi MiMo recognizes chat IDs `mimo-v2.5-pro` and `mimo-v2.5`, while TTS IDs are selected through `codewhale speech` / `tts`. Generic `openai`, `atlascloud`, `wanjie-ark`, `xiaomi-mimo`, `arcee`, and Ollama model IDs are passed through unchanged after known aliases are normalized. OpenRouter and SiliconFlow provider configs with a custom `base_url` also preserve explicit model values, which lets OpenAI-compatible gateways accept bare model IDs. Use `/models` or `codewhale models` to discover live IDs from your configured endpoint. `CODEWHALE_MODEL` overrides this for a single process; `DEEPSEEK_MODEL` is the legacy alias.
 - `reasoning_effort` (string, optional): `off`, `low`, `medium`, `high`, or `max`; defaults to the configured UI tier. DeepSeek Platform receives top-level `thinking` / `reasoning_effort` fields. NVIDIA NIM receives equivalent settings through `chat_template_kwargs`.
 - `allow_shell` (bool, optional): defaults to `false`; shell tools must be explicitly enabled.
 - `approval_policy` (string, optional): `on-request`, `untrusted`, or `never`. Runtime `approval_mode` editing in `/config` also accepts `on-request` and `untrusted` aliases.
diff --git a/docs/PROVIDERS.md b/docs/PROVIDERS.md
index 1a947f3b..83b0e4b1 100644
--- a/docs/PROVIDERS.md
+++ b/docs/PROVIDERS.md
@@ -135,6 +135,7 @@ endpoint.
 | `vllm` | `[providers.vllm]` | Optional `VLLM_API_KEY` | `VLLM_BASE_URL`; default `http://localhost:8000/v1` | `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | Self-hosted vLLM OpenAI-compatible route. Localhost deployments commonly omit auth. `VLLM_MODEL` is accepted. |
 | `ollama` | `[providers.ollama]` | Optional `OLLAMA_API_KEY` | `OLLAMA_BASE_URL`; default `http://localhost:11434/v1` | `deepseek-coder:1.3b`; provider-hinted custom tags pass through | Self-hosted Ollama OpenAI-compatible route. Localhost deployments commonly omit auth. `OLLAMA_MODEL` is accepted. |
 | `huggingface` | `[providers.huggingface]` | `HUGGINGFACE_API_KEY`, `HF_TOKEN` | `HUGGINGFACE_BASE_URL`; default `https://router.huggingface.co/v1` | `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | Hugging Face Inference Providers OpenAI-compatible route. Org-prefixed model IDs pass through. |
+| `together` | `[providers.together]` | `TOGETHER_API_KEY` | `TOGETHER_BASE_URL`; default `https://api.together.xyz/v1` | `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | Together AI OpenAI-compatible route. `TOGETHER_MODEL` is accepted. Model aliases `deepseek-v4-pro` and `deepseek-v4-flash` normalize to Together's org-prefixed IDs. |
 
 ### Hugging Face Provider vs MCP vs Hub
 
@@ -204,7 +205,7 @@ endpoint when the endpoint supports model listing.
 | `atlascloud` | `deepseek-ai/deepseek-v4-flash`, `deepseek-ai/deepseek-v4-pro` | yes | yes |
 | `wanjie-ark` | `deepseek-reasoner` | yes | yes |
 | `volcengine` | `DeepSeek-V4-Pro`, `DeepSeek-V4-Flash` | yes | yes |
-| `openrouter` | `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-flash`, `arcee-ai/trinity-large-thinking`, `minimax/minimax-m3`, `xiaomi/mimo-v2.5-pro`, `xiaomi/mimo-v2.5`, `qwen/qwen3.6-flash`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.6-max-preview`, `qwen/qwen3.6-27b`, `qwen/qwen3.6-plus`, `moonshotai/kimi-k2.6`, `z-ai/glm-5.1`, `tencent/hy3-preview`, `google/gemma-4-31b-it`, `google/gemma-4-26b-a4b-it`, `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | yes | yes |
+| `openrouter` | `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-flash`, `arcee-ai/trinity-large-thinking`, `minimax/minimax-m3`, `minimax/minimax-2.7`, `xiaomi/mimo-v2.5-pro`, `xiaomi/mimo-v2.5`, `qwen/qwen3.6-flash`, `qwen/qwen3.6-35b-a3b`, `qwen/qwen3.6-max-preview`, `qwen/qwen3.6-27b`, `qwen/qwen3.6-plus`, `qwen/qwen3.7-max`, `moonshotai/kimi-k2.6`, `z-ai/glm-5.1`, `tencent/hy3-preview`, `google/gemma-4-31b-it`, `google/gemma-4-26b-a4b-it`, `nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`, `nvidia/nemotron-3-ultra` | yes | yes |
 | `xiaomi-mimo` | `mimo-v2.5-pro`, `mimo-v2.5`; speech/TTS IDs are selected through `codewhale speech` / `tts` | yes | yes for chat models; no for speech/TTS models |
 | `novita` | `deepseek/deepseek-v4-pro`, `deepseek/deepseek-v4-flash` | yes | yes |
 | `fireworks` | `accounts/fireworks/models/deepseek-v4-pro` | yes | yes |
@@ -215,6 +216,7 @@ endpoint when the endpoint supports model listing.
 | `vllm` | `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | yes | yes |
 | `ollama` | `deepseek-coder:1.3b`; custom tags pass through when provider hint is `ollama` | yes | no |
 | `huggingface` | `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | yes | no |
+| `together` | `deepseek-ai/DeepSeek-V4-Pro`, `deepseek-ai/DeepSeek-V4-Flash` | yes | yes |
 
 AtlasCloud keeps the same default model as the config layer and adds
 provider-scoped aliases for the Pro and Flash rows. Other AtlasCloud model IDs