feat(providers): add AtlasCloud as a first-class provider

AtlasCloud (https://atlascloud.ai) hosts the V4 family on its own DeepSeek-compatible endpoint at `https://api.atlascloud.ai/v1`, and several contributors had been running it through the OpenAI-compatible passthrough with manual `base_url` / model overrides. Selecting `provider = "atlascloud"` in `~/.deepseek/config.toml` (or via `DEEPSEEK_PROVIDER=atlascloud`) now wires up: - documented `DEFAULT_ATLASCLOUD_BASE_URL` / `DEFAULT_ATLASCLOUD_MODEL` defaults so a fresh install needs only the api_key - a `[providers.atlascloud]` config block with the same fields every other named provider exposes (api_key / base_url / model / http_headers) - `ATLASCLOUD_API_KEY` env var path, including the secrets test cleanup loop so per-test env hygiene continues to work - the provider-picker / `/provider` slash command entries so the provider is reachable from the runtime UI, not just config - the env-driven `*_BASE_URL` override branch so users who pin a proxy can still flip it without editing config.toml Trust-boundary pins held: AtlasCloud is opt-in (default remains DeepSeek), no API keys are hardcoded, the api_key resolution flows through the same `secrets` crate path every other provider uses, and the provider-config base_url stays settable per environment. Resolved 3-way merge conflicts in `crates/secrets/src/lib.rs` (env cleanup loop) and `crates/tui/src/config.rs` (per-provider base_url match arm + `provider_passes_model_through` predicate) so the contributor's AtlasCloud branch coexists with the v0.8.x provider expansion already on `main`. Added the missing match arm in `validate_provider_base_url` so the non-exhaustive-pattern check passes after the new variant lands. Harvested from PR #1436 by @lucaszhu-hue Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 00:40:43 -05:00
parent 40df46c73d
commit 8f33e4bd48
13 changed files with 292 additions and 21 deletions
@@ -39,6 +39,21 @@ real world uses."

 ### Added

+- **AtlasCloud is now a first-class provider** (harvested from
+  PR #1436 by **@lucaszhu-hue**). AtlasCloud hosts the V4 family
+  (and other DeepSeek-compatible models) on its own endpoint at
+  `https://api.atlascloud.ai/v1`, and several contributors had
+  been running it through the OpenAI-compatible passthrough with
+  manual `base_url` / model overrides. Selecting
+  `provider = "atlascloud"` in `~/.deepseek/config.toml` (or via
+  `DEEPSEEK_PROVIDER=atlascloud`) now wires up the documented
+  defaults, a `[providers.atlascloud]` config block for per-user
+  api_key / base_url / model / http_headers overrides, the
+  `ATLASCLOUD_API_KEY` env var path, and the
+  provider-picker / `/provider` slash command entries — same
+  shape as the existing NVIDIA NIM / Fireworks / OpenAI provider
+  rows. Default remains DeepSeek; nothing changes for installs
+  that don't opt in.
 - **`web_search` supports Tavily and Bocha as configurable
  backends** (harvested from PR #1294 by **@sandofree**). DuckDuckGo
  with Bing fallback remains the default — no API key required —
@@ -16,10 +16,10 @@
 # `/provider sglang`, `/provider vllm`, `/provider ollama`) toggle without having to
 # re-enter keys. Top-level `api_key` / `base_url` are still read as DeepSeek
 # defaults when `[providers.deepseek]` is absent (backward compatibility).
-provider = "deepseek" # deepseek | deepseek-cn | nvidia-nim | openai | openrouter | novita | fireworks | sglang | vllm | ollama
+provider = "deepseek" # deepseek | deepseek-cn | nvidia-nim | openai | atlascloud | openrouter | novita | fireworks | sglang | vllm | ollama
 api_key = "YOUR_DEEPSEEK_API_KEY" # must be non-empty
 base_url = "https://api.deepseek.com/beta"
-# provider = "deepseek-cn"                       # mainland China preset (official https://api.deepseek.com)
+# provider = "deepseek-cn"                       # legacy alias (official host is still https://api.deepseek.com)
 # base_url = "https://api.deepseek.com"         # opt out of DeepSeek beta features
 # Optional custom model request headers for OpenAI-compatible gateways.
 # Authorization and Content-Type are managed by the client and cannot be overridden here.
@@ -34,6 +34,7 @@ base_url = "https://api.deepseek.com/beta"
 #   deepseek-ai/deepseek-v4-pro   — NVIDIA NIM-hosted Pro model ID
 #   deepseek-ai/deepseek-v4-flash — NVIDIA NIM-hosted Flash model ID
 #   gpt-4.1                         — default generic OpenAI-compatible model ID
+#   deepseek-ai/deepseek-v4-flash   — default AtlasCloud model ID
 #   accounts/fireworks/models/deepseek-v4-pro — Fireworks AI Pro model ID
 #   deepseek-ai/DeepSeek-V4-Pro    — SGLang self-hosted Pro model ID
 #   deepseek-ai/DeepSeek-V4-Flash  — SGLang self-hosted Flash model ID
@@ -183,6 +184,12 @@ max_subagents = 10 # optional (1-20)
 # base_url = "https://api.openai.com/v1"
 # model = "gpt-4.1"

+# AtlasCloud OpenAI-compatible endpoint (https://www.atlascloud.ai/docs/models/llm)
+[providers.atlascloud]
+# api_key = "YOUR_ATLASCLOUD_API_KEY"
+# base_url = "https://api.atlascloud.ai/v1"
+# model = "deepseek-ai/deepseek-v4-flash"
+
 # Fireworks AI-hosted DeepSeek V4 (https://fireworks.ai)
 [providers.fireworks]
 # api_key = "YOUR_FIREWORKS_API_KEY"
@@ -26,6 +26,7 @@ enum ProviderArg {
    Deepseek,
    NvidiaNim,
    Openai,
+    Atlascloud,
    Openrouter,
    Novita,
    Fireworks,
@@ -40,6 +41,7 @@ impl From<ProviderArg> for ProviderKind {
            ProviderArg::Deepseek => ProviderKind::Deepseek,
            ProviderArg::NvidiaNim => ProviderKind::NvidiaNim,
            ProviderArg::Openai => ProviderKind::Openai,
+            ProviderArg::Atlascloud => ProviderKind::Atlascloud,
            ProviderArg::Openrouter => ProviderKind::Openrouter,
            ProviderArg::Novita => ProviderKind::Novita,
            ProviderArg::Fireworks => ProviderKind::Fireworks,
@@ -673,6 +675,7 @@ fn provider_slot(provider: ProviderKind) -> &'static str {
        ProviderKind::Deepseek => "deepseek",
        ProviderKind::NvidiaNim => "nvidia-nim",
        ProviderKind::Openai => "openai",
+        ProviderKind::Atlascloud => "atlascloud",
        ProviderKind::Openrouter => "openrouter",
        ProviderKind::Novita => "novita",
        ProviderKind::Fireworks => "fireworks",
@@ -683,16 +686,17 @@ fn provider_slot(provider: ProviderKind) -> &'static str {
 }

 /// Provider order used by the `auth list` and `auth status` outputs.
-const PROVIDER_LIST: [ProviderKind; 9] = [
+const PROVIDER_LIST: [ProviderKind; 10] = [
    ProviderKind::Deepseek,
    ProviderKind::NvidiaNim,
+    ProviderKind::Openai,
+    ProviderKind::Atlascloud,
    ProviderKind::Openrouter,
    ProviderKind::Novita,
    ProviderKind::Fireworks,
    ProviderKind::Sglang,
    ProviderKind::Vllm,
    ProviderKind::Ollama,
-    ProviderKind::Openai,
 ];

 #[cfg(test)]
@@ -748,6 +752,7 @@ fn provider_env_vars(provider: ProviderKind) -> &'static [&'static str] {
        ProviderKind::Vllm => &["VLLM_API_KEY"],
        ProviderKind::Ollama => &["OLLAMA_API_KEY"],
        ProviderKind::Openai => &["OPENAI_API_KEY"],
+        ProviderKind::Atlascloud => &["ATLASCLOUD_API_KEY"],
    }
 }

@@ -1390,6 +1395,7 @@ fn build_tui_command(
        ProviderKind::Deepseek
            | ProviderKind::NvidiaNim
            | ProviderKind::Openai
+            | ProviderKind::Atlascloud
            | ProviderKind::Openrouter
            | ProviderKind::Novita
            | ProviderKind::Fireworks
@@ -1398,7 +1404,7 @@ fn build_tui_command(
            | ProviderKind::Ollama
    ) {
        bail!(
-            "The interactive TUI supports DeepSeek, NVIDIA NIM, OpenAI-compatible, OpenRouter, Novita, Fireworks, SGLang, vLLM, and Ollama providers. Remove --provider {} or use `deepseek model ...` for provider registry inspection.",
+            "The interactive TUI supports DeepSeek, NVIDIA NIM, OpenAI-compatible, AtlasCloud, OpenRouter, Novita, Fireworks, SGLang, vLLM, and Ollama providers. Remove --provider {} or use `deepseek model ...` for provider registry inspection.",
            resolved_runtime.provider.as_str()
        );
    }
@@ -1420,6 +1426,9 @@ fn build_tui_command(
        if resolved_runtime.provider == ProviderKind::Openai {
            cmd.env("OPENAI_API_KEY", api_key);
        }
+        if resolved_runtime.provider == ProviderKind::Atlascloud {
+            cmd.env("ATLASCLOUD_API_KEY", api_key);
+        }
        let source = resolved_runtime
            .api_key_source
            .unwrap_or(RuntimeApiKeySource::Env)
@@ -1453,6 +1462,9 @@ fn build_tui_command(
        if resolved_runtime.provider == ProviderKind::Openai {
            cmd.env("OPENAI_API_KEY", api_key);
        }
+        if resolved_runtime.provider == ProviderKind::Atlascloud {
+            cmd.env("ATLASCLOUD_API_KEY", api_key);
+        }
        cmd.env("DEEPSEEK_API_KEY_SOURCE", "cli");
    }
    if let Some(base_url) = cli.base_url.as_ref() {
@@ -21,6 +21,8 @@ const DEFAULT_OPENAI_MODEL: &str = "gpt-4.1";
 const DEFAULT_DEEPSEEK_BASE_URL: &str = "https://api.deepseek.com/beta";
 const DEFAULT_NVIDIA_NIM_BASE_URL: &str = "https://integrate.api.nvidia.com/v1";
 const DEFAULT_OPENAI_BASE_URL: &str = "https://api.openai.com/v1";
+const DEFAULT_ATLASCLOUD_MODEL: &str = "deepseek-ai/deepseek-v4-flash";
+const DEFAULT_ATLASCLOUD_BASE_URL: &str = "https://api.atlascloud.ai/v1";
 const DEFAULT_OPENROUTER_MODEL: &str = "deepseek/deepseek-v4-pro";
 const DEFAULT_OPENROUTER_FLASH_MODEL: &str = "deepseek/deepseek-v4-flash";
 const DEFAULT_NOVITA_MODEL: &str = "deepseek/deepseek-v4-pro";
@@ -45,6 +47,7 @@ pub enum ProviderKind {
    Deepseek,
    NvidiaNim,
    Openai,
+    Atlascloud,
    Openrouter,
    Novita,
    Fireworks,
@@ -60,6 +63,7 @@ impl ProviderKind {
            Self::Deepseek => "deepseek",
            Self::NvidiaNim => "nvidia-nim",
            Self::Openai => "openai",
+            Self::Atlascloud => "atlascloud",
            Self::Openrouter => "openrouter",
            Self::Novita => "novita",
            Self::Fireworks => "fireworks",
@@ -75,6 +79,7 @@ impl ProviderKind {
            "deepseek" | "deep-seek" => Some(Self::Deepseek),
            "nvidia" | "nvidia-nim" | "nvidia_nim" | "nim" => Some(Self::NvidiaNim),
            "openai" | "open-ai" => Some(Self::Openai),
+            "atlascloud" | "atlas-cloud" | "atlas_cloud" | "atlas" => Some(Self::Atlascloud),
            "openrouter" | "open_router" => Some(Self::Openrouter),
            "novita" => Some(Self::Novita),
            "fireworks" | "fireworks-ai" => Some(Self::Fireworks),
@@ -104,6 +109,8 @@ pub struct ProvidersToml {
    #[serde(default)]
    pub openai: ProviderConfigToml,
    #[serde(default)]
+    pub atlascloud: ProviderConfigToml,
+    #[serde(default)]
    pub openrouter: ProviderConfigToml,
    #[serde(default)]
    pub novita: ProviderConfigToml,
@@ -124,6 +131,7 @@ impl ProvidersToml {
            ProviderKind::Deepseek => &self.deepseek,
            ProviderKind::NvidiaNim => &self.nvidia_nim,
            ProviderKind::Openai => &self.openai,
+            ProviderKind::Atlascloud => &self.atlascloud,
            ProviderKind::Openrouter => &self.openrouter,
            ProviderKind::Novita => &self.novita,
            ProviderKind::Fireworks => &self.fireworks,
@@ -138,6 +146,7 @@ impl ProvidersToml {
            ProviderKind::Deepseek => &mut self.deepseek,
            ProviderKind::NvidiaNim => &mut self.nvidia_nim,
            ProviderKind::Openai => &mut self.openai,
+            ProviderKind::Atlascloud => &mut self.atlascloud,
            ProviderKind::Openrouter => &mut self.openrouter,
            ProviderKind::Novita => &mut self.novita,
            ProviderKind::Fireworks => &mut self.fireworks,
@@ -349,6 +358,10 @@ impl ConfigToml {
            &project.providers.nvidia_nim,
        );
        merge_provider_config(&mut self.providers.openai, &project.providers.openai);
+        merge_provider_config(
+            &mut self.providers.atlascloud,
+            &project.providers.atlascloud,
+        );
        merge_provider_config(
            &mut self.providers.openrouter,
            &project.providers.openrouter,
@@ -411,6 +424,12 @@ impl ConfigToml {
            "providers.openai.http_headers" => {
                serialize_http_headers(&self.providers.openai.http_headers)
            }
+            "providers.atlascloud.api_key" => self.providers.atlascloud.api_key.clone(),
+            "providers.atlascloud.base_url" => self.providers.atlascloud.base_url.clone(),
+            "providers.atlascloud.model" => self.providers.atlascloud.model.clone(),
+            "providers.atlascloud.http_headers" => {
+                serialize_http_headers(&self.providers.atlascloud.http_headers)
+            }
            "providers.openrouter.api_key" => self.providers.openrouter.api_key.clone(),
            "providers.openrouter.base_url" => self.providers.openrouter.base_url.clone(),
            "providers.openrouter.model" => self.providers.openrouter.model.clone(),
@@ -509,6 +528,18 @@ impl ConfigToml {
            "providers.openai.http_headers" => {
                self.providers.openai.http_headers = parse_http_headers(value)?;
            }
+            "providers.atlascloud.api_key" => {
+                self.providers.atlascloud.api_key = Some(value.to_string());
+            }
+            "providers.atlascloud.base_url" => {
+                self.providers.atlascloud.base_url = Some(value.to_string());
+            }
+            "providers.atlascloud.model" => {
+                self.providers.atlascloud.model = Some(value.to_string());
+            }
+            "providers.atlascloud.http_headers" => {
+                self.providers.atlascloud.http_headers = parse_http_headers(value)?;
+            }
            "providers.nvidia_nim.api_key" => {
                self.providers.nvidia_nim.api_key = Some(value.to_string());
            }
@@ -637,6 +668,10 @@ impl ConfigToml {
            "providers.openai.base_url" => self.providers.openai.base_url = None,
            "providers.openai.model" => self.providers.openai.model = None,
            "providers.openai.http_headers" => self.providers.openai.http_headers.clear(),
+            "providers.atlascloud.api_key" => self.providers.atlascloud.api_key = None,
+            "providers.atlascloud.base_url" => self.providers.atlascloud.base_url = None,
+            "providers.atlascloud.model" => self.providers.atlascloud.model = None,
+            "providers.atlascloud.http_headers" => self.providers.atlascloud.http_headers.clear(),
            "providers.nvidia_nim.api_key" => self.providers.nvidia_nim.api_key = None,
            "providers.nvidia_nim.base_url" => self.providers.nvidia_nim.base_url = None,
            "providers.nvidia_nim.model" => self.providers.nvidia_nim.model = None,
@@ -740,6 +775,18 @@ impl ConfigToml {
        if let Some(v) = serialize_http_headers(&self.providers.openai.http_headers) {
            out.insert("providers.openai.http_headers".to_string(), v);
        }
+        if let Some(v) = self.providers.atlascloud.api_key.as_ref() {
+            out.insert("providers.atlascloud.api_key".to_string(), redact_secret(v));
+        }
+        if let Some(v) = self.providers.atlascloud.base_url.as_ref() {
+            out.insert("providers.atlascloud.base_url".to_string(), v.clone());
+        }
+        if let Some(v) = self.providers.atlascloud.model.as_ref() {
+            out.insert("providers.atlascloud.model".to_string(), v.clone());
+        }
+        if let Some(v) = serialize_http_headers(&self.providers.atlascloud.http_headers) {
+            out.insert("providers.atlascloud.http_headers".to_string(), v);
+        }
        if let Some(v) = self.providers.nvidia_nim.api_key.as_ref() {
            out.insert("providers.nvidia_nim.api_key".to_string(), redact_secret(v));
        }
@@ -897,6 +944,7 @@ impl ConfigToml {
                ProviderKind::Deepseek => DEFAULT_DEEPSEEK_BASE_URL.to_string(),
                ProviderKind::NvidiaNim => DEFAULT_NVIDIA_NIM_BASE_URL.to_string(),
                ProviderKind::Openai => DEFAULT_OPENAI_BASE_URL.to_string(),
+                ProviderKind::Atlascloud => DEFAULT_ATLASCLOUD_BASE_URL.to_string(),
                ProviderKind::Openrouter => DEFAULT_OPENROUTER_BASE_URL.to_string(),
                ProviderKind::Novita => DEFAULT_NOVITA_BASE_URL.to_string(),
                ProviderKind::Fireworks => DEFAULT_FIREWORKS_BASE_URL.to_string(),
@@ -1009,7 +1057,7 @@ pub fn load_project_config(workspace: &Path) -> Option<ConfigToml> {
 }

 fn normalize_model_for_provider(provider: ProviderKind, model: &str) -> String {
-    if matches!(provider, ProviderKind::Ollama) {
+    if matches!(provider, ProviderKind::Atlascloud | ProviderKind::Ollama) {
        return model.to_string();
    }

@@ -1067,6 +1115,7 @@ fn default_model_for_provider(provider: ProviderKind) -> &'static str {
        ProviderKind::Deepseek => DEFAULT_DEEPSEEK_MODEL,
        ProviderKind::NvidiaNim => DEFAULT_NVIDIA_NIM_MODEL,
        ProviderKind::Openai => DEFAULT_OPENAI_MODEL,
+        ProviderKind::Atlascloud => DEFAULT_ATLASCLOUD_MODEL,
        ProviderKind::Openrouter => DEFAULT_OPENROUTER_MODEL,
        ProviderKind::Novita => DEFAULT_NOVITA_MODEL,
        ProviderKind::Fireworks => DEFAULT_FIREWORKS_MODEL,
@@ -1081,6 +1130,7 @@ fn default_base_url_for_provider(provider: ProviderKind) -> &'static str {
        ProviderKind::Deepseek => DEFAULT_DEEPSEEK_BASE_URL,
        ProviderKind::NvidiaNim => DEFAULT_NVIDIA_NIM_BASE_URL,
        ProviderKind::Openai => DEFAULT_OPENAI_BASE_URL,
+        ProviderKind::Atlascloud => DEFAULT_ATLASCLOUD_BASE_URL,
        ProviderKind::Openrouter => DEFAULT_OPENROUTER_BASE_URL,
        ProviderKind::Novita => DEFAULT_NOVITA_BASE_URL,
        ProviderKind::Fireworks => DEFAULT_FIREWORKS_BASE_URL,
@@ -1369,6 +1419,7 @@ struct EnvRuntimeOverrides {
    deepseek_base_url: Option<String>,
    nvidia_base_url: Option<String>,
    openai_base_url: Option<String>,
+    atlascloud_base_url: Option<String>,
    openrouter_base_url: Option<String>,
    novita_base_url: Option<String>,
    fireworks_base_url: Option<String>,
@@ -1410,6 +1461,9 @@ impl EnvRuntimeOverrides {
            openai_base_url: std::env::var("OPENAI_BASE_URL")
                .ok()
                .filter(|v| !v.trim().is_empty()),
+            atlascloud_base_url: std::env::var("ATLASCLOUD_BASE_URL")
+                .ok()
+                .filter(|v| !v.trim().is_empty()),
            openrouter_base_url: std::env::var("OPENROUTER_BASE_URL")
                .ok()
                .filter(|v| !v.trim().is_empty()),
@@ -1438,6 +1492,7 @@ impl EnvRuntimeOverrides {
            ProviderKind::Deepseek => self.deepseek_base_url.clone(),
            ProviderKind::NvidiaNim => self.nvidia_base_url.clone(),
            ProviderKind::Openai => self.openai_base_url.clone(),
+            ProviderKind::Atlascloud => self.atlascloud_base_url.clone(),
            ProviderKind::Openrouter => self.openrouter_base_url.clone(),
            ProviderKind::Novita => self.novita_base_url.clone(),
            ProviderKind::Fireworks => self.fireworks_base_url.clone(),
@@ -479,7 +479,8 @@ impl Secrets {
    /// Resolve a secret with `secret store → env → none` precedence.
    ///
    /// `name` is the canonical provider name (`"deepseek"`,
-    /// `"openrouter"`, `"novita"`, `"nvidia"`/`"nvidia-nim"`, `"openai"`).
+    /// `"openrouter"`, `"novita"`, `"nvidia"`/`"nvidia-nim"`, `"openai"`,
+    /// or `"atlascloud"`).
    /// Empty strings on either layer are treated as "not set".
    #[must_use]
    pub fn resolve(&self, name: &str) -> Option<String> {
@@ -532,6 +533,7 @@ pub fn env_for(name: &str) -> Option<String> {
        "vllm" | "v-llm" => &["VLLM_API_KEY"],
        "ollama" | "ollama-local" => &["OLLAMA_API_KEY"],
        "openai" => &["OPENAI_API_KEY"],
+        "atlascloud" | "atlas-cloud" | "atlas_cloud" | "atlas" => &["ATLASCLOUD_API_KEY"],
        _ => return None,
    };
    for var in candidates {
@@ -570,6 +572,7 @@ mod tests {
            "VLLM_API_KEY",
            "OLLAMA_API_KEY",
            "OPENAI_API_KEY",
+            "ATLASCLOUD_API_KEY",
            SECRET_BACKEND_ENV,
        ] {
            // Safety: tests serialise on env_lock(); the broader
@@ -721,6 +724,19 @@ mod tests {
        unsafe { std::env::remove_var("NVIDIA_NIM_API_KEY") };
    }

+    #[test]
+    fn atlascloud_env_aliases_resolve() {
+        let _guard = env_lock();
+        clear_known_envs();
+        unsafe { std::env::set_var("ATLASCLOUD_API_KEY", "atlas-key") };
+
+        assert_eq!(env_for("atlascloud").as_deref(), Some("atlas-key"));
+        assert_eq!(env_for("atlas").as_deref(), Some("atlas-key"));
+        assert_eq!(env_for("atlas-cloud").as_deref(), Some("atlas-key"));
+
+        clear_known_envs();
+    }
+
    #[test]
    fn fireworks_env_aliases_resolve() {
        let _lock = env_lock();
@@ -837,7 +837,7 @@ pub(super) fn apply_reasoning_effort(
            | ApiProvider::Vllm => {
                body["thinking"] = json!({ "type": "disabled" });
            }
-            ApiProvider::Openai | ApiProvider::Ollama => {}
+            ApiProvider::Openai | ApiProvider::Atlascloud | ApiProvider::Ollama => {}
            ApiProvider::NvidiaNim => {
                body["chat_template_kwargs"] = json!({
                    "thinking": false,
@@ -855,7 +855,7 @@ pub(super) fn apply_reasoning_effort(
                body["reasoning_effort"] = json!("high");
                body["thinking"] = json!({ "type": "enabled" });
            }
-            ApiProvider::Openai | ApiProvider::Ollama => {}
+            ApiProvider::Openai | ApiProvider::Atlascloud | ApiProvider::Ollama => {}
            ApiProvider::NvidiaNim => {
                body["chat_template_kwargs"] = json!({
                    "thinking": true,
@@ -874,7 +874,7 @@ pub(super) fn apply_reasoning_effort(
                body["reasoning_effort"] = json!("max");
                body["thinking"] = json!({ "type": "enabled" });
            }
-            ApiProvider::Openai | ApiProvider::Ollama => {}
+            ApiProvider::Openai | ApiProvider::Atlascloud | ApiProvider::Ollama => {}
            ApiProvider::NvidiaNim => {
                body["chat_template_kwargs"] = json!({
                    "thinking": true,
@@ -27,7 +27,7 @@ pub fn provider(app: &mut App, args: Option<&str>) -> CommandResult {

    let Some(target) = ApiProvider::parse(name) else {
        return CommandResult::error(format!(
-            "Unknown provider '{name}'. Expected: deepseek, nvidia-nim, openrouter, novita, fireworks, sglang, vllm, or ollama."
+            "Unknown provider '{name}'. Expected: deepseek, nvidia-nim, openai, atlascloud, openrouter, novita, fireworks, sglang, vllm, or ollama."
        ));
    };

@@ -129,6 +129,19 @@ mod tests {
        }
    }

+    #[test]
+    fn switch_to_atlascloud_emits_action() {
+        let mut app = create_test_app();
+        let result = provider(&mut app, Some("atlascloud"));
+        match result.action {
+            Some(AppAction::SwitchProvider { provider, model }) => {
+                assert_eq!(provider, ApiProvider::Atlascloud);
+                assert_eq!(model, None);
+            }
+            other => panic!("expected SwitchProvider, got {other:?}"),
+        }
+    }
+
    #[test]
    fn switch_to_novita_emits_action() {
        let mut app = create_test_app();
@@ -26,6 +26,8 @@ pub const DEFAULT_NVIDIA_NIM_FLASH_MODEL: &str = "deepseek-ai/deepseek-v4-flash"
 pub const DEFAULT_NVIDIA_NIM_BASE_URL: &str = "https://integrate.api.nvidia.com/v1";
 pub const DEFAULT_OPENAI_MODEL: &str = "gpt-4.1";
 pub const DEFAULT_OPENAI_BASE_URL: &str = "https://api.openai.com/v1";
+pub const DEFAULT_ATLASCLOUD_MODEL: &str = "deepseek-ai/deepseek-v4-flash";
+pub const DEFAULT_ATLASCLOUD_BASE_URL: &str = "https://api.atlascloud.ai/v1";
 pub const DEFAULT_OPENROUTER_MODEL: &str = "deepseek/deepseek-v4-pro";
 pub const DEFAULT_OPENROUTER_FLASH_MODEL: &str = "deepseek/deepseek-v4-flash";
 pub const DEFAULT_OPENROUTER_BASE_URL: &str = "https://openrouter.ai/api/v1";
@@ -66,6 +68,7 @@ pub enum ApiProvider {
    DeepseekCN,
    NvidiaNim,
    Openai,
+    Atlascloud,
    Openrouter,
    Novita,
    Fireworks,
@@ -84,6 +87,7 @@ impl ApiProvider {
            }
            "nvidia" | "nvidia-nim" | "nvidia_nim" | "nim" => Some(Self::NvidiaNim),
            "openai" | "open-ai" => Some(Self::Openai),
+            "atlascloud" | "atlas-cloud" | "atlas_cloud" | "atlas" => Some(Self::Atlascloud),
            "openrouter" | "open_router" => Some(Self::Openrouter),
            "novita" => Some(Self::Novita),
            "fireworks" | "fireworks-ai" => Some(Self::Fireworks),
@@ -101,6 +105,7 @@ impl ApiProvider {
            Self::DeepseekCN => "deepseek-cn",
            Self::NvidiaNim => "nvidia-nim",
            Self::Openai => "openai",
+            Self::Atlascloud => "atlascloud",
            Self::Openrouter => "openrouter",
            Self::Novita => "novita",
            Self::Fireworks => "fireworks",
@@ -118,6 +123,7 @@ impl ApiProvider {
            Self::DeepseekCN => "DeepSeek (legacy alias)",
            Self::NvidiaNim => "NVIDIA NIM",
            Self::Openai => "OpenAI-compatible",
+            Self::Atlascloud => "AtlasCloud",
            Self::Openrouter => "OpenRouter",
            Self::Novita => "Novita AI",
            Self::Fireworks => "Fireworks AI",
@@ -134,6 +140,7 @@ impl ApiProvider {
            Self::Deepseek,
            Self::NvidiaNim,
            Self::Openai,
+            Self::Atlascloud,
            Self::Openrouter,
            Self::Novita,
            Self::Fireworks,
@@ -205,7 +212,7 @@ pub enum RequestPayloadMode {
 /// in the API payload (after normalization / provider-specific mapping).
 #[must_use]
 pub fn provider_capability(provider: ApiProvider, resolved_model: &str) -> ProviderCapability {
-    if matches!(provider, ApiProvider::Openai) {
+    if matches!(provider, ApiProvider::Openai | ApiProvider::Atlascloud) {
        return ProviderCapability {
            provider,
            resolved_model: resolved_model.to_string(),
@@ -1068,6 +1075,8 @@ pub struct ProvidersConfig {
    #[serde(default)]
    pub openai: ProviderConfig,
    #[serde(default)]
+    pub atlascloud: ProviderConfig,
+    #[serde(default)]
    pub openrouter: ProviderConfig,
    #[serde(default)]
    pub novita: ProviderConfig,
@@ -1167,6 +1176,7 @@ impl Config {
        }
        let table = match provider {
            ApiProvider::Openai => "providers.openai",
+            ApiProvider::Atlascloud => "providers.atlascloud",
            ApiProvider::Openrouter => "providers.openrouter",
            ApiProvider::Novita => "providers.novita",
            ApiProvider::Fireworks => "providers.fireworks",
@@ -1189,7 +1199,7 @@ impl Config {
            && ApiProvider::parse(provider).is_none()
        {
            anyhow::bail!(
-                "Invalid provider '{provider}': expected deepseek, deepseek-cn, nvidia-nim, openai, openrouter, novita, fireworks, sglang, vllm, or ollama."
+                "Invalid provider '{provider}': expected deepseek, deepseek-cn, nvidia-nim, openai, atlascloud, openrouter, novita, fireworks, sglang, vllm, or ollama."
            );
        }
        if let Some(ref key) = self.api_key
@@ -1306,6 +1316,7 @@ impl Config {
            ApiProvider::DeepseekCN => &providers.deepseek_cn,
            ApiProvider::NvidiaNim => &providers.nvidia_nim,
            ApiProvider::Openai => &providers.openai,
+            ApiProvider::Atlascloud => &providers.atlascloud,
            ApiProvider::Openrouter => &providers.openrouter,
            ApiProvider::Novita => &providers.novita,
            ApiProvider::Fireworks => &providers.fireworks,
@@ -1369,6 +1380,7 @@ impl Config {
            ApiProvider::Deepseek | ApiProvider::DeepseekCN => DEFAULT_TEXT_MODEL,
            ApiProvider::NvidiaNim => DEFAULT_NVIDIA_NIM_MODEL,
            ApiProvider::Openai => DEFAULT_OPENAI_MODEL,
+            ApiProvider::Atlascloud => DEFAULT_ATLASCLOUD_MODEL,
            ApiProvider::Openrouter => DEFAULT_OPENROUTER_MODEL,
            ApiProvider::Novita => DEFAULT_NOVITA_MODEL,
            ApiProvider::Fireworks => DEFAULT_FIREWORKS_MODEL,
@@ -1398,6 +1410,7 @@ impl Config {
                .filter(|base| base.contains("integrate.api.nvidia.com"))
                .cloned(),
            ApiProvider::Openai
+            | ApiProvider::Atlascloud
            | ApiProvider::Openrouter
            | ApiProvider::Novita
            | ApiProvider::Fireworks
@@ -1411,6 +1424,7 @@ impl Config {
                ApiProvider::DeepseekCN => DEFAULT_DEEPSEEKCN_BASE_URL,
                ApiProvider::NvidiaNim => DEFAULT_NVIDIA_NIM_BASE_URL,
                ApiProvider::Openai => DEFAULT_OPENAI_BASE_URL,
+                ApiProvider::Atlascloud => DEFAULT_ATLASCLOUD_BASE_URL,
                ApiProvider::Openrouter => DEFAULT_OPENROUTER_BASE_URL,
                ApiProvider::Novita => DEFAULT_NOVITA_BASE_URL,
                ApiProvider::Fireworks => DEFAULT_FIREWORKS_BASE_URL,
@@ -1442,6 +1456,7 @@ impl Config {
            ApiProvider::Deepseek | ApiProvider::DeepseekCN => "deepseek",
            ApiProvider::NvidiaNim => "nvidia-nim",
            ApiProvider::Openai => "openai",
+            ApiProvider::Atlascloud => "atlascloud",
            ApiProvider::Openrouter => "openrouter",
            ApiProvider::Novita => "novita",
            ApiProvider::Fireworks => "fireworks",
@@ -1502,6 +1517,10 @@ impl Config {
                "OpenAI-compatible API key not found. Run 'deepseek auth set --provider openai', \
                 set OPENAI_API_KEY, or add [providers.openai] api_key in ~/.deepseek/config.toml."
            ),
+            ApiProvider::Atlascloud => anyhow::bail!(
+                "AtlasCloud API key not found. Run 'deepseek auth set --provider atlascloud', \
+                 set ATLASCLOUD_API_KEY, or add [providers.atlascloud] api_key in ~/.deepseek/config.toml."
+            ),
            ApiProvider::Openrouter => anyhow::bail!(
                "OpenRouter API key not found. Run 'deepseek auth set --provider openrouter', \
                 set OPENROUTER_API_KEY, or add [providers.openrouter] api_key in ~/.deepseek/config.toml."
@@ -2039,6 +2058,13 @@ fn apply_env_overrides(config: &mut Config) {
                    .ollama
                    .base_url = Some(value);
            }
+            ApiProvider::Atlascloud => {
+                config
+                    .providers
+                    .get_or_insert_with(ProvidersConfig::default)
+                    .atlascloud
+                    .base_url = Some(value);
+            }
        }
    }
    if matches!(config.api_provider(), ApiProvider::NvidiaNim)
@@ -2065,6 +2091,16 @@ fn apply_env_overrides(config: &mut Config) {
            .openai
            .base_url = Some(value);
    }
+    if matches!(config.api_provider(), ApiProvider::Atlascloud)
+        && let Ok(value) = std::env::var("ATLASCLOUD_BASE_URL")
+        && !value.trim().is_empty()
+    {
+        config
+            .providers
+            .get_or_insert_with(ProvidersConfig::default)
+            .atlascloud
+            .base_url = Some(value);
+    }
    if matches!(config.api_provider(), ApiProvider::Openrouter)
        && let Ok(value) = std::env::var("OPENROUTER_BASE_URL")
        && !value.trim().is_empty()
@@ -2132,6 +2168,7 @@ fn apply_env_overrides(config: &mut Config) {
            ApiProvider::DeepseekCN => &mut providers.deepseek_cn,
            ApiProvider::NvidiaNim => &mut providers.nvidia_nim,
            ApiProvider::Openai => &mut providers.openai,
+            ApiProvider::Atlascloud => &mut providers.atlascloud,
            ApiProvider::Openrouter => &mut providers.openrouter,
            ApiProvider::Novita => &mut providers.novita,
            ApiProvider::Fireworks => &mut providers.fireworks,
@@ -2177,6 +2214,11 @@ fn apply_env_overrides(config: &mut Config) {
            .openai
            .model = Some(value);
    }
+    if matches!(config.api_provider(), ApiProvider::Atlascloud)
+        && let Ok(value) = std::env::var("ATLASCLOUD_MODEL")
+    {
+        config.default_text_model = Some(value);
+    }
    if let Ok(value) =
        std::env::var("DEEPSEEK_MODEL").or_else(|_| std::env::var("DEEPSEEK_DEFAULT_TEXT_MODEL"))
    {
@@ -2425,7 +2467,10 @@ fn normalize_model_for_provider(provider: ApiProvider, model: &str) -> Option<St
 }

 pub(crate) fn provider_passes_model_through(provider: ApiProvider) -> bool {
-    matches!(provider, ApiProvider::Openai | ApiProvider::Ollama)
+    matches!(
+        provider,
+        ApiProvider::Openai | ApiProvider::Atlascloud | ApiProvider::Ollama
+    )
 }

 fn provider_entry_uses_custom_base_url(provider: ApiProvider, entry: &ProviderConfig) -> bool {
@@ -2441,6 +2486,7 @@ fn default_base_url_for_provider(provider: ApiProvider) -> &'static str {
        ApiProvider::DeepseekCN => DEFAULT_DEEPSEEKCN_BASE_URL,
        ApiProvider::NvidiaNim => DEFAULT_NVIDIA_NIM_BASE_URL,
        ApiProvider::Openai => DEFAULT_OPENAI_BASE_URL,
+        ApiProvider::Atlascloud => DEFAULT_ATLASCLOUD_BASE_URL,
        ApiProvider::Openrouter => DEFAULT_OPENROUTER_BASE_URL,
        ApiProvider::Novita => DEFAULT_NOVITA_BASE_URL,
        ApiProvider::Fireworks => DEFAULT_FIREWORKS_BASE_URL,
@@ -2645,6 +2691,7 @@ fn merge_providers(
            deepseek_cn: merge_provider_config(base.deepseek_cn, override_cfg.deepseek_cn),
            nvidia_nim: merge_provider_config(base.nvidia_nim, override_cfg.nvidia_nim),
            openai: merge_provider_config(base.openai, override_cfg.openai),
+            atlascloud: merge_provider_config(base.atlascloud, override_cfg.atlascloud),
            openrouter: merge_provider_config(base.openrouter, override_cfg.openrouter),
            novita: merge_provider_config(base.novita, override_cfg.novita),
            fireworks: merge_provider_config(base.fireworks, override_cfg.fireworks),
@@ -3047,6 +3094,9 @@ pub fn active_provider_has_env_api_key(config: &Config) -> bool {
                || std::env::var("NVIDIA_NIM_API_KEY").is_ok_and(|k| !k.trim().is_empty())
        }
        ApiProvider::Openai => std::env::var("OPENAI_API_KEY").is_ok_and(|k| !k.trim().is_empty()),
+        ApiProvider::Atlascloud => {
+            std::env::var("ATLASCLOUD_API_KEY").is_ok_and(|k| !k.trim().is_empty())
+        }
        ApiProvider::Openrouter => {
            std::env::var("OPENROUTER_API_KEY").is_ok_and(|k| !k.trim().is_empty())
        }
@@ -3074,6 +3124,7 @@ pub fn has_api_key_for(config: &Config, provider: ApiProvider) -> bool {
        ApiProvider::Deepseek | ApiProvider::DeepseekCN => "DEEPSEEK_API_KEY",
        ApiProvider::NvidiaNim => "NVIDIA_API_KEY",
        ApiProvider::Openai => "OPENAI_API_KEY",
+        ApiProvider::Atlascloud => "ATLASCLOUD_API_KEY",
        ApiProvider::Openrouter => "OPENROUTER_API_KEY",
        ApiProvider::Novita => "NOVITA_API_KEY",
        ApiProvider::Fireworks => "FIREWORKS_API_KEY",
@@ -3142,6 +3193,7 @@ pub fn save_api_key_for(provider: ApiProvider, api_key: &str) -> Result<PathBuf>
        }
        ApiProvider::NvidiaNim => "providers.nvidia_nim",
        ApiProvider::Openai => "providers.openai",
+        ApiProvider::Atlascloud => "providers.atlascloud",
        ApiProvider::Openrouter => "providers.openrouter",
        ApiProvider::Novita => "providers.novita",
        ApiProvider::Fireworks => "providers.fireworks",
@@ -3176,6 +3228,7 @@ pub fn save_api_key_for(provider: ApiProvider, api_key: &str) -> Result<PathBuf>
        }
        ApiProvider::NvidiaNim => "nvidia_nim",
        ApiProvider::Openai => "openai",
+        ApiProvider::Atlascloud => "atlascloud",
        ApiProvider::Openrouter => "openrouter",
        ApiProvider::Novita => "novita",
        ApiProvider::Fireworks => "fireworks",
@@ -3320,6 +3373,9 @@ mod tests {
        openai_api_key: Option<OsString>,
        openai_base_url: Option<OsString>,
        openai_model: Option<OsString>,
+        atlascloud_api_key: Option<OsString>,
+        atlascloud_base_url: Option<OsString>,
+        atlascloud_model: Option<OsString>,
        openrouter_api_key: Option<OsString>,
        openrouter_base_url: Option<OsString>,
        novita_api_key: Option<OsString>,
@@ -3360,6 +3416,9 @@ mod tests {
            let openai_api_key_prev = env::var_os("OPENAI_API_KEY");
            let openai_base_url_prev = env::var_os("OPENAI_BASE_URL");
            let openai_model_prev = env::var_os("OPENAI_MODEL");
+            let atlascloud_api_key_prev = env::var_os("ATLASCLOUD_API_KEY");
+            let atlascloud_base_url_prev = env::var_os("ATLASCLOUD_BASE_URL");
+            let atlascloud_model_prev = env::var_os("ATLASCLOUD_MODEL");
            let openrouter_api_key_prev = env::var_os("OPENROUTER_API_KEY");
            let openrouter_base_url_prev = env::var_os("OPENROUTER_BASE_URL");
            let novita_api_key_prev = env::var_os("NOVITA_API_KEY");
@@ -3395,6 +3454,9 @@ mod tests {
                env::remove_var("OPENAI_API_KEY");
                env::remove_var("OPENAI_BASE_URL");
                env::remove_var("OPENAI_MODEL");
+                env::remove_var("ATLASCLOUD_API_KEY");
+                env::remove_var("ATLASCLOUD_BASE_URL");
+                env::remove_var("ATLASCLOUD_MODEL");
                env::remove_var("OPENROUTER_API_KEY");
                env::remove_var("OPENROUTER_BASE_URL");
                env::remove_var("NOVITA_API_KEY");
@@ -3430,6 +3492,9 @@ mod tests {
                openai_api_key: openai_api_key_prev,
                openai_base_url: openai_base_url_prev,
                openai_model: openai_model_prev,
+                atlascloud_api_key: atlascloud_api_key_prev,
+                atlascloud_base_url: atlascloud_base_url_prev,
+                atlascloud_model: atlascloud_model_prev,
                openrouter_api_key: openrouter_api_key_prev,
                openrouter_base_url: openrouter_base_url_prev,
                novita_api_key: novita_api_key_prev,
@@ -3474,6 +3539,9 @@ mod tests {
                Self::restore_var("OPENAI_API_KEY", self.openai_api_key.take());
                Self::restore_var("OPENAI_BASE_URL", self.openai_base_url.take());
                Self::restore_var("OPENAI_MODEL", self.openai_model.take());
+                Self::restore_var("ATLASCLOUD_API_KEY", self.atlascloud_api_key.take());
+                Self::restore_var("ATLASCLOUD_BASE_URL", self.atlascloud_base_url.take());
+                Self::restore_var("ATLASCLOUD_MODEL", self.atlascloud_model.take());
                Self::restore_var("OPENROUTER_API_KEY", self.openrouter_api_key.take());
                Self::restore_var("OPENROUTER_BASE_URL", self.openrouter_base_url.take());
                Self::restore_var("NOVITA_API_KEY", self.novita_api_key.take());
@@ -4706,6 +4774,50 @@ http_headers = { "X-Model-Provider-Id" = "from-file" }
        Ok(())
    }

+    #[test]
+    fn atlascloud_provider_uses_documented_defaults() -> Result<()> {
+        let config = Config {
+            provider: Some("atlascloud".to_string()),
+            ..Default::default()
+        };
+
+        config.validate()?;
+        assert_eq!(config.api_provider(), ApiProvider::Atlascloud);
+        assert_eq!(config.default_model(), DEFAULT_ATLASCLOUD_MODEL);
+        assert_eq!(config.deepseek_base_url(), DEFAULT_ATLASCLOUD_BASE_URL);
+        Ok(())
+    }
+
+    #[test]
+    fn atlascloud_env_overrides_provider_base_url_and_model() -> Result<()> {
+        let _lock = lock_test_env();
+        let nanos = SystemTime::now()
+            .duration_since(UNIX_EPOCH)
+            .unwrap()
+            .as_nanos();
+        let temp_root = env::temp_dir().join(format!(
+            "deepseek-tui-atlascloud-env-test-{}-{}",
+            std::process::id(),
+            nanos
+        ));
+        fs::create_dir_all(&temp_root)?;
+        let _guard = EnvGuard::new(&temp_root);
+
+        unsafe {
+            env::set_var("DEEPSEEK_PROVIDER", "atlascloud");
+            env::set_var("ATLASCLOUD_API_KEY", "atlascloud-env-key");
+            env::set_var("ATLASCLOUD_BASE_URL", "https://api.atlascloud.ai/v1");
+            env::set_var("ATLASCLOUD_MODEL", "deepseek-ai/deepseek-v4-flash");
+        }
+
+        let config = Config::load(None, None)?;
+        assert_eq!(config.api_provider(), ApiProvider::Atlascloud);
+        assert_eq!(config.deepseek_api_key()?, "atlascloud-env-key");
+        assert_eq!(config.deepseek_base_url(), "https://api.atlascloud.ai/v1");
+        assert_eq!(config.default_model(), "deepseek-ai/deepseek-v4-flash");
+        Ok(())
+    }
+
    #[test]
    fn openai_provider_accepts_custom_model_and_base_url() -> Result<()> {
        let _lock = lock_test_env();
@@ -5672,6 +5784,22 @@ model = "deepseek-ai/deepseek-v4-pro"
        );
    }

+    #[test]
+    fn provider_capability_atlascloud_custom_model_is_chat_completions_without_thinking() {
+        let cap = provider_capability(ApiProvider::Atlascloud, "deepseek-ai/deepseek-v4-flash");
+        assert_eq!(
+            cap.context_window,
+            crate::models::LEGACY_DEEPSEEK_CONTEXT_WINDOW_TOKENS
+        );
+        assert_eq!(cap.max_output, 4096);
+        assert!(!cap.thinking_supported);
+        assert!(!cap.cache_telemetry_supported);
+        assert_eq!(
+            cap.request_payload_mode,
+            RequestPayloadMode::ChatCompletions
+        );
+    }
+
    #[test]
    fn provider_capability_ollama_is_openai_compatible_without_thinking() {
        let cap = provider_capability(ApiProvider::Ollama, "deepseek-v3.1:671b");
@@ -379,6 +379,7 @@ impl Engine {
            ApiProvider::Deepseek | ApiProvider::DeepseekCN => "DEEPSEEK_API_KEY",
            ApiProvider::NvidiaNim => "NVIDIA_API_KEY/NVIDIA_NIM_API_KEY",
            ApiProvider::Openai => "OPENAI_API_KEY",
+            ApiProvider::Atlascloud => "ATLASCLOUD_API_KEY",
            ApiProvider::Openrouter => "OPENROUTER_API_KEY",
            ApiProvider::Novita => "NOVITA_API_KEY",
            ApiProvider::Fireworks => "FIREWORKS_API_KEY",
@@ -1366,6 +1366,10 @@ fn run_setup_status(config: &Config, workspace: &Path) -> Result<()> {
                    "OPENAI_API_KEY",
                    "deepseek auth set --provider openai --api-key \"...\"",
                ),
+                crate::config::ApiProvider::Atlascloud => (
+                    "ATLASCLOUD_API_KEY",
+                    "deepseek auth set --provider atlascloud --api-key \"...\"",
+                ),
                crate::config::ApiProvider::Openrouter => (
                    "OPENROUTER_API_KEY",
                    "deepseek auth set --provider openrouter --api-key \"...\"",
@@ -1399,6 +1403,7 @@ fn run_setup_status(config: &Config, workspace: &Path) -> Result<()> {
                match config.api_provider() {
                    crate::config::ApiProvider::NvidiaNim => "nvidia_nim",
                    crate::config::ApiProvider::Openai => "openai",
+                    crate::config::ApiProvider::Atlascloud => "atlascloud",
                    crate::config::ApiProvider::Openrouter => "openrouter",
                    crate::config::ApiProvider::Novita => "novita",
                    crate::config::ApiProvider::Fireworks => "fireworks",
@@ -89,6 +89,7 @@ impl ProviderPickerView {
            ApiProvider::Deepseek | ApiProvider::DeepseekCN => "DEEPSEEK_API_KEY",
            ApiProvider::NvidiaNim => "NVIDIA_API_KEY",
            ApiProvider::Openai => "OPENAI_API_KEY",
+            ApiProvider::Atlascloud => "ATLASCLOUD_API_KEY",
            ApiProvider::Openrouter => "OPENROUTER_API_KEY",
            ApiProvider::Novita => "NOVITA_API_KEY",
            ApiProvider::Fireworks => "FIREWORKS_API_KEY",
@@ -393,6 +394,7 @@ mod tests {
                "DeepSeek",
                "NVIDIA NIM",
                "OpenAI-compatible",
+                "AtlasCloud",
                "OpenRouter",
                "Novita AI",
                "Fireworks AI",
@@ -5295,6 +5295,8 @@ async fn execute_command_input(
            providers.deepseek.api_key = None;
            providers.deepseek_cn.api_key = None;
            providers.nvidia_nim.api_key = None;
+            providers.openai.api_key = None;
+            providers.atlascloud.api_key = None;
            providers.openrouter.api_key = None;
            providers.novita.api_key = None;
            providers.fireworks.api_key = None;
@@ -5675,6 +5677,7 @@ fn render(f: &mut Frame, app: &mut App) {
            crate::config::ApiProvider::DeepseekCN => None,
            crate::config::ApiProvider::NvidiaNim => Some("NIM"),
            crate::config::ApiProvider::Openai => Some("OpenAI"),
+            crate::config::ApiProvider::Atlascloud => Some("Atlas"),
            crate::config::ApiProvider::Openrouter => Some("OR"),
            crate::config::ApiProvider::Novita => Some("Novita"),
            crate::config::ApiProvider::Fireworks => Some("Fireworks"),
@@ -6390,6 +6393,7 @@ async fn apply_provider_picker_api_key(
            }
            ApiProvider::NvidiaNim => &mut providers.nvidia_nim,
            ApiProvider::Openai => &mut providers.openai,
+            ApiProvider::Atlascloud => &mut providers.atlascloud,
            ApiProvider::Openrouter => &mut providers.openrouter,
            ApiProvider::Novita => &mut providers.novita,
            ApiProvider::Fireworks => &mut providers.fireworks,
@@ -62,16 +62,19 @@ label without printing the key itself. The command only probes the active
 provider's keyring entry.

 For hosted, generic OpenAI-compatible, or self-hosted providers, set
-`provider = "nvidia-nim"`, `"openai"`, `"fireworks"`, `"sglang"`, `"vllm"`, or
-`"ollama"` or pass `deepseek --provider <name>`. The facade saves provider
+`provider = "nvidia-nim"`, `"openai"`, `"atlascloud"`, `"fireworks"`,
+`"sglang"`, `"vllm"`, or `"ollama"` or pass `deepseek --provider <name>`. The facade saves provider
 credentials to the shared user config and forwards the resolved key, base URL,
 provider, and model to the TUI process. Use
 `deepseek auth set --provider nvidia-nim --api-key "YOUR_NVIDIA_API_KEY"` or
 `deepseek auth set --provider openai --api-key "YOUR_OPENAI_COMPATIBLE_API_KEY"` or
+`deepseek auth set --provider atlascloud --api-key "YOUR_ATLASCLOUD_API_KEY"` or
 `deepseek auth set --provider fireworks --api-key "YOUR_FIREWORKS_API_KEY"` to
 save provider keys through the facade. The generic `openai` provider defaults
 to `https://api.openai.com/v1`, accepts `OPENAI_BASE_URL`, and passes model IDs
-through unchanged for OpenAI-compatible gateways. SGLang, vLLM, and Ollama are
+through unchanged for OpenAI-compatible gateways. `atlascloud` defaults to
+`https://api.atlascloud.ai/v1`, accepts `ATLASCLOUD_BASE_URL`, and uses
+`deepseek-ai/deepseek-v4-flash` as its default model. SGLang, vLLM, and Ollama are
 self-hosted and can run without an API key by default. Ollama defaults to
 `http://localhost:11434/v1` and sends model tags such as `deepseek-coder:1.3b`
 or `qwen2.5-coder:7b` unchanged.
@@ -124,6 +127,13 @@ provider = "openai"
 base_url = "https://openai-compatible.example/v4"
 model = "glm-5"

+[profiles.atlascloud]
+provider = "atlascloud"
+
+[profiles.atlascloud.providers.atlascloud]
+base_url = "https://api.atlascloud.ai/v1"
+model = "deepseek-ai/deepseek-v4-flash"
+
 [profiles.sglang]
 provider = "sglang"
 base_url = "http://localhost:30000/v1"
@@ -155,7 +165,7 @@ fallbacks after saved config and keyring credentials:
 - `DEEPSEEK_API_KEY`
 - `DEEPSEEK_BASE_URL`
 - `DEEPSEEK_HTTP_HEADERS` (custom model request headers, comma-separated `name=value` pairs)
- `DEEPSEEK_PROVIDER` (`deepseek|nvidia-nim|openai|openrouter|novita|fireworks|sglang|vllm|ollama`)
+- `DEEPSEEK_PROVIDER` (`deepseek|nvidia-nim|openai|atlascloud|openrouter|novita|fireworks|sglang|vllm|ollama`)
 - `DEEPSEEK_MODEL` or `DEEPSEEK_DEFAULT_TEXT_MODEL`
 - `DEEPSEEK_STREAM_IDLE_TIMEOUT_SECS` (stream idle timeout in seconds; default `300`, clamped to `1..=3600`)
 - `DEEPSEEK_STREAM_OPEN_TIMEOUT_SECS` (connection setup + response-header wait in seconds; default `45`, clamped to `5..=300`; distinct from the per-chunk idle timeout)
@@ -165,6 +175,9 @@ fallbacks after saved config and keyring credentials:
 - `OPENAI_API_KEY`
 - `OPENAI_BASE_URL`
 - `OPENAI_MODEL`
+- `ATLASCLOUD_API_KEY`
+- `ATLASCLOUD_BASE_URL`
+- `ATLASCLOUD_MODEL`
 - `OPENROUTER_API_KEY`
 - `OPENROUTER_BASE_URL`
 - `NOVITA_API_KEY`
@@ -362,10 +375,10 @@ If you are upgrading from older releases:

 ### Core keys (used by the TUI/engine)

- `provider` (string, optional): `deepseek` (default), `nvidia-nim`, `openai`, `openrouter`, `novita`, `fireworks`, `sglang`, `vllm`, or `ollama`. Legacy `deepseek-cn` configs are still accepted as an alias for `deepseek`; DeepSeek uses the same official host [`https://api.deepseek.com`](https://api-docs.deepseek.com/) worldwide. `nvidia-nim` targets NVIDIA's NIM-hosted DeepSeek endpoints through `https://integrate.api.nvidia.com/v1`; `openai` targets a generic OpenAI-compatible endpoint, defaulting to `https://api.openai.com/v1`; `fireworks` targets `https://api.fireworks.ai/inference/v1`; `sglang` targets a self-hosted OpenAI-compatible endpoint, defaulting to `http://localhost:30000/v1`; `vllm` targets a self-hosted vLLM OpenAI-compatible endpoint, defaulting to `http://localhost:8000/v1`; `ollama` targets Ollama's OpenAI-compatible endpoint, defaulting to `http://localhost:11434/v1`.
+- `provider` (string, optional): `deepseek` (default), `nvidia-nim`, `openai`, `atlascloud`, `openrouter`, `novita`, `fireworks`, `sglang`, `vllm`, or `ollama`. Legacy `deepseek-cn` configs are still accepted as an alias for `deepseek`; DeepSeek uses the same official host [`https://api.deepseek.com`](https://api-docs.deepseek.com/) worldwide. `nvidia-nim` targets NVIDIA's NIM-hosted DeepSeek endpoints through `https://integrate.api.nvidia.com/v1`; `openai` targets a generic OpenAI-compatible endpoint, defaulting to `https://api.openai.com/v1`; `atlascloud` targets AtlasCloud's OpenAI-compatible endpoint at `https://api.atlascloud.ai/v1`; `fireworks` targets `https://api.fireworks.ai/inference/v1`; `sglang` targets a self-hosted OpenAI-compatible endpoint, defaulting to `http://localhost:30000/v1`; `vllm` targets a self-hosted vLLM OpenAI-compatible endpoint, defaulting to `http://localhost:8000/v1`; `ollama` targets Ollama's OpenAI-compatible endpoint, defaulting to `http://localhost:11434/v1`.
 - `api_key` (string, required for hosted providers): must be non-empty for DeepSeek/hosted providers (or set the provider API key env var). Self-hosted SGLang, vLLM, and Ollama can omit it.
- `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, `https://api.openai.com/v1` for `provider = "openai"`, or the provider-specific endpoint for hosted/self-hosted providers. Set `https://api.deepseek.com` or `https://api.deepseek.com/v1` explicitly to opt out of DeepSeek beta features.
- `default_text_model` (string, optional): defaults to `deepseek-v4-pro` for DeepSeek, `deepseek-ai/deepseek-v4-pro` for NVIDIA NIM, `gpt-4.1` for generic OpenAI-compatible endpoints, `accounts/fireworks/models/deepseek-v4-pro` for Fireworks, `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. Provider-specific mappings translate `deepseek-v4-pro` / `deepseek-v4-flash` to each provider's model ID where supported. Generic `openai` and Ollama model IDs are passed through unchanged. OpenRouter provider configs with a custom `base_url` also preserve explicit model values, which lets OpenAI-compatible gateways accept bare model IDs. Use `/models` or `deepseek models` to discover live IDs from your configured endpoint. `DEEPSEEK_MODEL` overrides this for a single process.
+- `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, `https://api.openai.com/v1` for `provider = "openai"`, `https://api.atlascloud.ai/v1` for `provider = "atlascloud"`, or the provider-specific endpoint for hosted/self-hosted providers. Set `https://api.deepseek.com` or `https://api.deepseek.com/v1` explicitly to opt out of DeepSeek beta features.
+- `default_text_model` (string, optional): defaults to `deepseek-v4-pro` for DeepSeek, `deepseek-ai/deepseek-v4-pro` for NVIDIA NIM, `gpt-4.1` for generic OpenAI-compatible endpoints, `deepseek-ai/deepseek-v4-flash` for AtlasCloud, `accounts/fireworks/models/deepseek-v4-pro` for Fireworks, `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. Provider-specific mappings translate `deepseek-v4-pro` / `deepseek-v4-flash` to each provider's model ID where supported. Generic `openai`, `atlascloud`, and Ollama model IDs are passed through unchanged. OpenRouter provider configs with a custom `base_url` also preserve explicit model values, which lets OpenAI-compatible gateways accept bare model IDs. Use `/models` or `deepseek models` to discover live IDs from your configured endpoint. `DEEPSEEK_MODEL` overrides this for a single process.
 - `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 `true` (sandboxed).
 - `approval_policy` (string, optional): `on-request`, `untrusted`, or `never`. Runtime `approval_mode` editing in `/config` also accepts `on-request` and `untrusted` aliases.