ENTERPILOT · SantiagoDePolonia · May 5, 2026 · May 5, 2026 · May 5, 2026 · May 5, 2026
diff --git a/README.md b/README.md
@@ -51,6 +51,9 @@ docker run --rm -p 8080:8080 \
   -e OPENAI_API_KEY="your-openai-key" \
   -e ANTHROPIC_API_KEY="your-anthropic-key" \
   -e GEMINI_API_KEY="your-gemini-key" \
+  -e VERTEX_PROJECT="your-gcp-project" \
+  -e VERTEX_LOCATION="us-central1" \
+  -e VERTEX_AUTH_TYPE="gcp_adc" \
   -e DEEPSEEK_API_KEY="your-deepseek-key" \
   -e GROQ_API_KEY="your-groq-key" \
   -e OPENROUTER_API_KEY="your-openrouter-key" \
@@ -90,7 +93,8 @@ Example model identifiers are illustrative and subject to change; consult provid
 | ------------- | ----------------------------------------------------------------- | ---------------------------------- | :--: | :----------: | :---: | :---: | :-----: | :------: |
 | OpenAI        | `OPENAI_API_KEY`                                                  | `gpt-5.5`                          |  ✅  |      ✅      |  ✅   |  ✅   |   ✅    |    ✅    |
 | Anthropic     | `ANTHROPIC_API_KEY`                                               | `claude-sonnet-4-20250514`         |  ✅  |      ✅      |  ❌   |  ❌   |   ✅    |    ✅    |
-| Google Gemini | `GEMINI_API_KEY`                                                  | `gemini-2.5-flash`                 |  ✅  |      ✅      |  ✅   |  ✅   |   ✅    |    ❌    |
+| Google Gemini | `GEMINI_API_KEY`                                                   | `gemini-2.5-flash`                 |  ✅  |      ✅      |  ✅   |  ✅   |   ✅    |    ❌    |
+| Vertex AI     | `VERTEX_PROJECT` + `VERTEX_LOCATION`                               | `google/gemini-2.5-flash`          |  ✅  |      ✅      |  ✅   |  ❌   |   ❌    |    ❌    |
 | DeepSeek      | `DEEPSEEK_API_KEY`                                                | `deepseek-v4-pro`                  |  ✅  |      ✅      |  ❌   |  ❌   |   ❌    |    ❌    |
 | Groq          | `GROQ_API_KEY`                                                    | `llama-3.3-70b-versatile`          |  ✅  |      ✅      |  ✅   |  ✅   |   ✅    |    ❌    |
 | OpenRouter    | `OPENROUTER_API_KEY`                                              | `google/gemini-2.5-flash`          |  ✅  |      ✅      |  ✅   |  ✅   |   ✅    |    ✅    |
@@ -120,6 +124,10 @@ To register multiple instances of the same provider type without `config.yaml`,
 use suffixed env vars such as `OPENAI_EAST_API_KEY` and
 `OPENAI_EAST_BASE_URL`; add `OPENAI_EAST_MODELS` to configure that instance's
 model list. This registers provider `openai-east` with type `openai`.
+Vertex AI uses the `VERTEX_*` prefix and registers provider `vertex`
+with type `vertex`; suffixed variables such as `VERTEX_US_PROJECT` register
+provider `vertex_us`. Vertex requires `VERTEX_PROJECT` and `VERTEX_LOCATION`;
+`VERTEX_AUTH_TYPE` defaults to Application Default Credentials (`gcp_adc`).
 
 ---
 
@@ -250,7 +258,9 @@ Key settings:
 | `ENABLE_PASSTHROUGH_ROUTES`     | `true`                                 | Enable provider-native passthrough routes under `/p/{provider}/...`              |
 | `ALLOW_PASSTHROUGH_V1_ALIAS`    | `true`                                 | Allow `/p/{provider}/v1/...` aliases while keeping `/p/{provider}/...` canonical |
 | `ENABLED_PASSTHROUGH_PROVIDERS` | `openai,anthropic,openrouter,zai,vllm` | Comma-separated list of enabled passthrough providers                            |
-| `USE_GOOGLE_GEMINI_NATIVE_API`  | `true`                                 | Use Gemini native `generateContent` for chat/responses; set `false` for Gemini's OpenAI-compatible API and image_url pass-through behavior |
+| `GEMINI_API_MODE`               | `native`                               | Gemini AI Studio upstream mode: `native` or `openai_compatible`                 |
+| `VERTEX_API_MODE`               | `native`                               | Vertex AI Gemini upstream mode: `native` or `openai_compatible`                 |
+| `USE_GOOGLE_GEMINI_NATIVE_API`  | `true`                                 | Legacy global Gemini mode toggle used when per-provider `*_API_MODE` is unset   |
 | `STORAGE_TYPE`                  | `sqlite`                               | Storage backend (`sqlite`, `postgresql`, `mongodb`)                              |
 | `METRICS_ENABLED`               | `false`                                | Enable Prometheus metrics (experimental)                                         |
 | `LOGGING_ENABLED`               | `false`                                | Enable audit logging                                                             |

diff --git a/cmd/gomodel/main.go b/cmd/gomodel/main.go
@@ -26,6 +26,7 @@ import (
 	"gomodel/internal/providers/openai"
 	"gomodel/internal/providers/openrouter"
 	"gomodel/internal/providers/oracle"
+	"gomodel/internal/providers/vertex"
 	"gomodel/internal/providers/vllm"
 	"gomodel/internal/providers/xai"
 	"gomodel/internal/providers/zai"
@@ -122,6 +123,7 @@ func main() {
 	factory.Add(anthropic.Registration)
 	factory.Add(deepseek.Registration)
 	factory.Add(gemini.Registration)
+	factory.Add(vertex.Registration)
 	factory.Add(groq.Registration)
 	factory.Add(minimax.Registration)
 	factory.Add(ollama.Registration)

diff --git a/config/config.example.yaml b/config/config.example.yaml
@@ -202,9 +202,22 @@ providers:
     type: gemini
     api_key: "..."
     # Chat/responses use Gemini's native generateContent API by default.
-    # Set USE_GOOGLE_GEMINI_NATIVE_API=false to use Gemini's OpenAI-compatible API instead.
+    # Set GEMINI_API_MODE=openai_compatible or api_mode: openai_compatible to use
+    # Gemini's OpenAI-compatible API instead.
     # Native mode accepts image data URLs but does not fetch remote image URLs yet.
 
+  vertex:
+    type: vertex
+    auth_type: gcp_adc # or gcp_service_account
+    vertex_project: "my-gcp-project"
+    vertex_location: "us-central1"
+    # service_account_file: "/var/run/secrets/google/service-account.json"
+    # service_account_json: "${VERTEX_SERVICE_ACCOUNT_JSON}"
+    # service_account_json_base64: "${VERTEX_SERVICE_ACCOUNT_JSON_BASE64}"
+    # api_mode: native # or openai_compatible
+    # models:
+    #   - id: "google/gemini-2.5-flash"
+
   xai:
     type: xai
     api_key: "..."

diff --git a/config/config.go b/config/config.go
@@ -54,12 +54,21 @@ type LoadResult struct {
 // overrides, credential filtering, or resilience merging. Exported so the
 // providers package can resolve it into a fully-configured ProviderConfig.
 type RawProviderConfig struct {
-	Type       string               `yaml:"type"`
-	APIKey     string               `yaml:"api_key"`
-	BaseURL    string               `yaml:"base_url"`
-	APIVersion string               `yaml:"api_version"`
-	Models     []RawProviderModel   `yaml:"models"`
-	Resilience *RawResilienceConfig `yaml:"resilience"`
+	Type                     string               `yaml:"type"`
+	APIKey                   string               `yaml:"api_key"`
+	BaseURL                  string               `yaml:"base_url"`
+	APIVersion               string               `yaml:"api_version"`
+	Backend                  string               `yaml:"backend"`
+	AuthType                 string               `yaml:"auth_type"`
+	APIMode                  string               `yaml:"api_mode"`
+	VertexProject            string               `yaml:"vertex_project"`
+	VertexLocation           string               `yaml:"vertex_location"`
+	ServiceAccountFile       string               `yaml:"service_account_file"`
+	ServiceAccountJSON       string               `yaml:"service_account_json"`
+	ServiceAccountJSONBase64 string               `yaml:"service_account_json_base64"`
+	GCPScope                 string               `yaml:"gcp_scope"`
+	Models                   []RawProviderModel   `yaml:"models"`
+	Resilience               *RawResilienceConfig `yaml:"resilience"`
 }
 
 // RawResilienceConfig holds optional per-provider resilience overrides from YAML.

diff --git a/docs/advanced/config-yaml.mdx b/docs/advanced/config-yaml.mdx
@@ -25,6 +25,11 @@ For multiple provider instances, env vars support
 `OLLAMA_A_BASE_URL` registers `ollama-a`. Azure also supports
 `<PROVIDER>_<SUFFIX>_API_VERSION`.
 
+Vertex AI is the exception to the provider-name shape: use `VERTEX_*`
+env vars to create `type: vertex` providers named `vertex`, `vertex_us`,
+`vertex_eu`, and so on. Vertex requires `VERTEX_PROJECT` and
+`VERTEX_LOCATION`; `VERTEX_AUTH_TYPE` defaults to `gcp_adc`.
+
 Configured provider model lists can stay in env via `<PROVIDER>_MODELS`, for
 example `OPENROUTER_MODELS`, `ORACLE_MODELS`, `AZURE_MODELS`, or `VLLM_MODELS`.
 Set `CONFIGURED_PROVIDER_MODELS_MODE=fallback` (default) to use those lists only

diff --git a/docs/advanced/configuration.mdx b/docs/advanced/configuration.mdx
@@ -350,6 +350,18 @@ The same pattern works for every registered provider type:
 suffixed `BASE_URL` values because their endpoints are deployment- or
 region-specific.
 
+Vertex AI uses the dedicated `VERTEX_*` prefix and registers provider
+`vertex` with type `vertex`. Suffixed Vertex env vars keep underscores in the
+provider name:
+
+```bash
+export VERTEX_PROJECT="prod-ai"
+export VERTEX_LOCATION="us-central1" # Registers "vertex", type "vertex"
+
+export VERTEX_US_PROJECT="prod-ai"
+export VERTEX_US_LOCATION="us-central1" # Registers "vertex_us", type "vertex"
+```
+
 ### YAML Provider Blocks
 
 For more control (custom names, per-provider resilience, or larger structured
@@ -404,6 +416,16 @@ providers:
     models:
       - gemini-2.0-flash
       - gemini-1.5-pro
+
+  # Add Vertex AI. Project and location are required.
+  vertex:
+    type: vertex
+    auth_type: gcp_adc
+    vertex_project: "prod-ai"
+    vertex_location: "us-central1"
+    api_mode: native
+    models:
+      - google/gemini-2.5-flash
 ```
 
 <Note>

diff --git a/docs/guides/gemini.mdx b/docs/guides/gemini.mdx
@@ -9,12 +9,13 @@ GoModel routes Gemini chat and Responses API requests through Gemini's native
 Gemini's OpenAI-compatible API when you need compatibility behavior that the
 native adapter does not implement yet.
 
-## Configure Gemini
+## Configure AI Studio
 
-Env-only configuration is enough:
+Use the `GEMINI_*` prefix for Gemini API keys from AI Studio:
 
 ```bash
 export GEMINI_API_KEY="..."
+export GEMINI_API_MODE="native"
 ```
 
 Or in `config.yaml`:
@@ -24,21 +25,85 @@ providers:
   gemini:
     type: gemini
     api_key: "${GEMINI_API_KEY}"
+    api_mode: native
 ```
 
+## Configure Vertex AI
+
+Use the `VERTEX_*` prefix for Gemini on Vertex AI. Vertex providers use the
+dedicated `vertex` provider type:
+
+```bash
+export VERTEX_PROJECT="my-gcp-project"
+export VERTEX_LOCATION="us-central1"
+export VERTEX_AUTH_TYPE="gcp_adc"
+export VERTEX_API_MODE="native"
+```
+
+This registers provider `vertex`, type `vertex`. For multiple Vertex regions
+or accounts, use suffixes:
+
+```bash
+export VERTEX_US_PROJECT="prod-ai"
+export VERTEX_US_LOCATION="us-central1"
+export VERTEX_US_AUTH_TYPE="gcp_adc"
+
+export VERTEX_EU_PROJECT="prod-ai"
+export VERTEX_EU_LOCATION="europe-west4"
+export VERTEX_EU_AUTH_TYPE="gcp_service_account"
+export VERTEX_EU_SERVICE_ACCOUNT_FILE="/secrets/vertex-eu.json"
+```
+
+These register providers `vertex_us` and `vertex_eu`.
+
+Or in `config.yaml`:
+
+```yaml
+providers:
+  vertex:
+    type: vertex
+    auth_type: gcp_adc
+    vertex_project: my-gcp-project
+    vertex_location: us-central1
+    api_mode: native
+```
+
+Vertex requires both project and location. `VERTEX_AUTH_TYPE` defaults to
+Application Default Credentials (`gcp_adc`) when service-account fields are not
+set. Use service-account JSON directly when ADC is not appropriate:
+
+<Note>
+  Vertex authentication is enterprise-oriented and may become paid or licensed
+  in a future release.
+</Note>
+
+```bash
+export VERTEX_AUTH_TYPE="gcp_service_account"
+export VERTEX_SERVICE_ACCOUNT_FILE="/secrets/service-account.json"
+# or VERTEX_SERVICE_ACCOUNT_JSON / VERTEX_SERVICE_ACCOUNT_JSON_BASE64
+```
+
+The default Vertex bases are derived from project and location:
+
+- OpenAI-compatible: `https://aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi`
+- native Gemini: `https://aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/publishers/google`
+
 ## Native versus OpenAI-compatible mode
 
 Gemini native mode is enabled by default:
 
 ```bash
-export USE_GOOGLE_GEMINI_NATIVE_API=true
+export GEMINI_API_MODE="native"
+export VERTEX_API_MODE="native"
 ```
 
-Set it to `false` to route chat and Responses API requests through Gemini's
-OpenAI-compatible `/chat/completions` endpoint:
+Set the per-provider API mode to `openai_compatible` to route chat and
+Responses API requests through the upstream OpenAI-compatible
+`/chat/completions` endpoint:
 
 ```bash
-export USE_GOOGLE_GEMINI_NATIVE_API=false
+export GEMINI_API_MODE="openai_compatible"
+export VERTEX_API_MODE="openai_compatible"
 ```
 
 `GEMINI_BASE_URL` configures the Gemini base. GoModel keeps separate internal
@@ -50,15 +115,17 @@ bases for native Gemini and the OpenAI-compatible API:
 When `GEMINI_BASE_URL` ends in `/openai`, GoModel uses that value for the
 OpenAI-compatible client and derives the native base by stripping `/openai`.
 Gemini embeddings, files, and batches still use the OpenAI-compatible surface.
+Vertex embeddings use Vertex AI native prediction. Vertex does not expose
+Gemini Files or OpenAI-compatible batch operations.
 
 ```bash
 export GEMINI_BASE_URL="https://generativelanguage.googleapis.com/v1beta/openai"
 ```
 
 <Note>
-  `USE_GOOGLE_GEMINI_NATIVE_API` decides whether chat and Responses API calls
-  use native Gemini or the OpenAI-compatible API. `GEMINI_BASE_URL` only
-  configures the upstream base URLs.
+  `USE_GOOGLE_GEMINI_NATIVE_API` is still supported as a legacy global toggle
+  when per-provider `*_API_MODE` is unset. Prefer `GEMINI_API_MODE` and
+  `VERTEX_API_MODE` for new deployments.
 </Note>
 
 ## Image URL behavior
@@ -84,8 +151,9 @@ mode. Google's native Gemini API supports inline image data and Files API
 references; for URL-hosted images, Google's examples fetch the URL first and
 send the bytes to `generateContent`.
 
-Set `USE_GOOGLE_GEMINI_NATIVE_API=false` when you need GoModel to pass the
-OpenAI-compatible `image_url` request shape through to Gemini's
+Set `GEMINI_API_MODE=openai_compatible` or
+`VERTEX_API_MODE=openai_compatible` when you need GoModel to pass the
+OpenAI-compatible `image_url` request shape through to Google's
 OpenAI-compatible endpoint instead. Google documents image input for that
 endpoint using the OpenAI `image_url` field.
 
@@ -95,17 +163,21 @@ Integrated:
 
 - chat completions and streaming
 - Responses API and streaming
-- model listing through Gemini's native `/models`
+- model listing through AI Studio `/models` and Vertex publisher models
+- Vertex embeddings through native prediction
 - usage metadata normalization for native responses
 - tool calls and function-call results
 - inline image data via `data:` URLs in native mode
 
-Not integrated in native mode yet:
+Not integrated yet:
 
 - fetching remote `image_url` values
 - uploading remote images through the Gemini Files API before a chat request
+- Vertex Files and batch prediction APIs
 
 References:
 
 - [Gemini image understanding](https://ai.google.dev/gemini-api/docs/image-understanding)
 - [Gemini OpenAI compatibility](https://ai.google.dev/gemini-api/docs/openai)
+- [Vertex AI OpenAI compatibility](https://cloud.google.com/vertex-ai/generative-ai/docs/start/openai)
+- [Gemini API in Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference)
diff --git a/go.mod b/go.mod
@@ -17,13 +17,15 @@ require (
 	github.com/swaggo/swag/v2 v2.0.0-rc5
 	github.com/tidwall/gjson v1.18.0
 	go.mongodb.org/mongo-driver/v2 v2.6.0
+	golang.org/x/oauth2 v0.36.0
 	golang.org/x/sync v0.20.0
 	golang.org/x/term v0.42.0
 	gopkg.in/yaml.v3 v3.0.1
 	modernc.org/sqlite v1.50.0
 )
 
 require (
+	cloud.google.com/go/compute/metadata v0.3.0 // indirect
 	github.com/KyleBanks/depth v1.2.1 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cpuguy83/go-md2man/v2 v2.0.5 // indirect

diff --git a/go.sum b/go.sum
@@ -1,3 +1,5 @@
+cloud.google.com/go/compute/metadata v0.3.0 h1:Tz+eQXMEqDIKRsmY3cHTL6FVaynIjX2QxYC4trgAKZc=
+cloud.google.com/go/compute/metadata v0.3.0/go.mod h1:zFmK7XCadkQkj6TtorcaGlCW1hT1fIilQDwofLpJ20k=
 github.com/KyleBanks/depth v1.2.1 h1:5h8fQADFrWtarTdtDudMmGsC7GPbOAu6RVB3ffsVFHc=
 github.com/KyleBanks/depth v1.2.1/go.mod h1:jzSb9d0L43HxTQfT+oSA1EEp2q+ne2uh6XgeJcm8brE=
 github.com/andybalholm/brotli v1.2.1 h1:R+f5xP285VArJDRgowrfb9DqL18yVK0gKAW/F+eTWro=
@@ -161,6 +163,8 @@ golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
 golang.org/x/net v0.50.0 h1:ucWh9eiCGyDR3vtzso0WMQinm2Dnt8cFMuQa9K33J60=
 golang.org/x/net v0.50.0/go.mod h1:UgoSli3F/pBgdJBHCTc+tp3gmrU4XswgGRgtnwWTfyM=
+golang.org/x/oauth2 v0.36.0 h1:peZ/1z27fi9hUOFCAZaHyrpWG5lwe0RJEEEeH0ThlIs=
+golang.org/x/oauth2 v0.36.0/go.mod h1:YDBUJMTkDnJS+A4BP4eZBjCqtokkg1hODuPjwiGPO7Q=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.20.0 h1:e0PTpb7pjO8GAtTs2dQ6jYa5BWYlMuX047Dco/pItO4=