diff --git a/src/config.rs b/src/config.rs
index 5ea636d8..b273c413 100644
--- a/src/config.rs
+++ b/src/config.rs
@@ -417,6 +417,8 @@ pub enum LlmBackend {
     Ollama,
     /// Any OpenAI-compatible endpoint (e.g. vLLM, LiteLLM, Together)
     OpenAiCompatible,
+    /// Tinfoil private inference
+    Tinfoil,
 }
 
 impl std::str::FromStr for LlmBackend {
@@ -429,8 +431,9 @@ impl std::str::FromStr for LlmBackend {
             "anthropic" | "claude" => Ok(Self::Anthropic),
             "ollama" => Ok(Self::Ollama),
             "openai_compatible" | "openai-compatible" | "compatible" => Ok(Self::OpenAiCompatible),
+            "tinfoil" => Ok(Self::Tinfoil),
             _ => Err(format!(
-                "invalid LLM backend '{}', expected one of: nearai, openai, anthropic, ollama, openai_compatible",
+                "invalid LLM backend '{}', expected one of: nearai, openai, anthropic, ollama, openai_compatible, tinfoil",
                 s
             )),
         }
@@ -445,6 +448,7 @@ impl std::fmt::Display for LlmBackend {
             Self::Anthropic => write!(f, "anthropic"),
             Self::Ollama => write!(f, "ollama"),
             Self::OpenAiCompatible => write!(f, "openai_compatible"),
+            Self::Tinfoil => write!(f, "tinfoil"),
         }
     }
 }
@@ -478,6 +482,13 @@ pub struct OpenAiCompatibleConfig {
     pub model: String,
 }
 
+/// Configuration for Tinfoil private inference.
+#[derive(Debug, Clone)]
+pub struct TinfoilConfig {
+    pub api_key: SecretString,
+    pub model: String,
+}
+
 /// LLM provider configuration.
 ///
 /// NEAR AI remains the default backend. Users can switch to other providers
@@ -496,6 +507,8 @@ pub struct LlmConfig {
     pub ollama: Option<OllamaConfig>,
     /// OpenAI-compatible config (populated when backend=openai_compatible)
     pub openai_compatible: Option<OpenAiCompatibleConfig>,
+    /// Tinfoil config (populated when backend=tinfoil)
+    pub tinfoil: Option<TinfoilConfig>,
 }
 
 /// API mode for NEAR AI.
@@ -702,6 +715,19 @@ impl LlmConfig {
             None
         };
 
+        let tinfoil = if backend == LlmBackend::Tinfoil {
+            let api_key = optional_env("TINFOIL_API_KEY")?
+                .map(SecretString::from)
+                .ok_or_else(|| ConfigError::MissingRequired {
+                    key: "TINFOIL_API_KEY".to_string(),
+                    hint: "Set TINFOIL_API_KEY when LLM_BACKEND=tinfoil".to_string(),
+                })?;
+            let model = optional_env("TINFOIL_MODEL")?.unwrap_or_else(|| "kimi-k2-5".to_string());
+            Some(TinfoilConfig { api_key, model })
+        } else {
+            None
+        };
+
         Ok(Self {
             backend,
             nearai,
@@ -709,6 +735,7 @@ impl LlmConfig {
             anthropic,
             ollama,
             openai_compatible,
+            tinfoil,
         })
     }
 }
diff --git a/src/llm/mod.rs b/src/llm/mod.rs
index 198d57c7..ef91f8e2 100644
--- a/src/llm/mod.rs
+++ b/src/llm/mod.rs
@@ -58,6 +58,7 @@ pub fn create_llm_provider(
         LlmBackend::Anthropic => create_anthropic_provider(config),
         LlmBackend::Ollama => create_ollama_provider(config),
         LlmBackend::OpenAiCompatible => create_openai_compatible_provider(config),
+        LlmBackend::Tinfoil => create_tinfoil_provider(config),
     }
 }
 
@@ -154,6 +155,35 @@ fn create_ollama_provider(config: &LlmConfig) -> Result<Arc<dyn LlmProvider>, Ll
     Ok(Arc::new(RigAdapter::new(model, &oll.model)))
 }
 
+const TINFOIL_BASE_URL: &str = "https://inference.tinfoil.sh/v1";
+
+fn create_tinfoil_provider(config: &LlmConfig) -> Result<Arc<dyn LlmProvider>, LlmError> {
+    let tf = config
+        .tinfoil
+        .as_ref()
+        .ok_or_else(|| LlmError::AuthFailed {
+            provider: "tinfoil".to_string(),
+        })?;
+
+    use rig::providers::openai;
+
+    let client: openai::Client = openai::Client::builder()
+        .base_url(TINFOIL_BASE_URL)
+        .api_key(tf.api_key.expose_secret())
+        .build()
+        .map_err(|e| LlmError::RequestFailed {
+            provider: "tinfoil".to_string(),
+            reason: format!("Failed to create Tinfoil client: {}", e),
+        })?;
+
+    // Tinfoil currently only supports the Chat Completions API and not the newer Responses API,
+    // so we must explicitly select the completions API here (unlike other OpenAI-compatible providers).
+    let client = client.completions_api();
+    let model = client.completion_model(&tf.model);
+    tracing::info!("Using Tinfoil private inference (model: {})", tf.model);
+    Ok(Arc::new(RigAdapter::new(model, &tf.model)))
+}
+
 fn create_openai_compatible_provider(config: &LlmConfig) -> Result<Arc<dyn LlmProvider>, LlmError> {
     let compat = config
         .openai_compatible
@@ -257,6 +287,7 @@ mod tests {
             anthropic: None,
             ollama: None,
             openai_compatible: None,
+            tinfoil: None,
         }
     }
 
diff --git a/src/setup/wizard.rs b/src/setup/wizard.rs
index 11a8d1e4..2625537e 100644
--- a/src/setup/wizard.rs
+++ b/src/setup/wizard.rs
@@ -1034,6 +1034,7 @@ impl SetupWizard {
             anthropic: None,
             ollama: None,
             openai_compatible: None,
+            tinfoil: None,
         };
 
         match create_llm_provider(&config, session) {