Skip to content

Use Claude Code, Codex, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)

Python

Treat empty model overrides as fallback

Alishahryar1d2db1bd6892e
diff --git a/.env.example b/.env.example
index 77fef510..59831881 100644
--- a/.env.example
+++ b/.env.example
@@ -21,9 +21,9 @@ LLAMACPP_BASE_URL="http://localhost:8080/v1"
# All Claude model requests are mapped to these models, plain model is fallback
# Format: provider_type/model/name
# Valid providers: "nvidia_nim" | "open_router" | "deepseek" | "lmstudio" | "llamacpp"
-MODEL_OPUS="nvidia_nim/z-ai/glm4.7"
-MODEL_SONNET="open_router/arcee-ai/trinity-large-preview:free"
-MODEL_HAIKU="open_router/stepfun/step-3.5-flash:free"
+MODEL_OPUS=
+MODEL_SONNET=
+MODEL_HAIKU=
MODEL="nvidia_nim/z-ai/glm4.7"
diff --git a/README.md b/README.md
index 6a2e11da..2309e617 100644
--- a/README.md
+++ b/README.md
@@ -76,9 +76,9 @@ Choose your provider and edit `.env`:
```dotenv
NVIDIA_NIM_API_KEY="nvapi-your-key-here"
-MODEL_OPUS="nvidia_nim/z-ai/glm4.7"
-MODEL_SONNET="nvidia_nim/moonshotai/kimi-k2-thinking"
-MODEL_HAIKU="nvidia_nim/stepfun-ai/step-3.5-flash"
+MODEL_OPUS=
+MODEL_SONNET=
+MODEL_HAIKU=
MODEL="nvidia_nim/z-ai/glm4.7" # fallback
# Global switch for provider reasoning requests and Claude thinking blocks.
@@ -502,10 +502,10 @@ Configure via `WHISPER_DEVICE` (`cpu` | `cuda` | `nvidia_nim`) and `WHISPER_MODE
| Variable | Description | Default |
| -------------------- | --------------------------------------------------------------------- | ------------------------------------------------- |
-| `MODEL` | Fallback model (`provider/model/name` format; invalid prefix → error) | `nvidia_nim/stepfun-ai/step-3.5-flash` |
-| `MODEL_OPUS` | Model for Claude Opus requests (falls back to `MODEL`) | `nvidia_nim/z-ai/glm4.7` |
-| `MODEL_SONNET` | Model for Claude Sonnet requests (falls back to `MODEL`) | `open_router/arcee-ai/trinity-large-preview:free` |
-| `MODEL_HAIKU` | Model for Claude Haiku requests (falls back to `MODEL`) | `open_router/stepfun/step-3.5-flash:free` |
+| `MODEL` | Fallback model (`provider/model/name` format; invalid prefix → error) | `nvidia_nim/z-ai/glm4.7` |
+| `MODEL_OPUS` | Model for Claude Opus requests; empty falls back to `MODEL` | empty |
+| `MODEL_SONNET` | Model for Claude Sonnet requests; empty falls back to `MODEL` | empty |
+| `MODEL_HAIKU` | Model for Claude Haiku requests; empty falls back to `MODEL` | empty |
| `NVIDIA_NIM_API_KEY` | NVIDIA API key | required for NIM |
| `ENABLE_THINKING` | Global switch for provider reasoning requests and Claude thinking blocks. Set `false` to hide thinking across all providers. | `true` |
| `OPENROUTER_API_KEY` | OpenRouter API key | required for OpenRouter |
diff --git a/config/env.example b/config/env.example
index a77fd4e1..6b0faa5c 100644
--- a/config/env.example
+++ b/config/env.example
@@ -17,9 +17,9 @@ LM_STUDIO_BASE_URL="http://localhost:1234/v1"
# All Claude model requests are mapped to these models, plain model is fallback
# Format: provider_type/model/name
# Valid providers: "nvidia_nim" | "open_router" | "deepseek" | "lmstudio" | "llamacpp"
-MODEL_OPUS="nvidia_nim/z-ai/glm4.7"
-MODEL_SONNET="open_router/arcee-ai/trinity-large-preview:free"
-MODEL_HAIKU="open_router/stepfun/step-3.5-flash:free"
+MODEL_OPUS=
+MODEL_SONNET=
+MODEL_HAIKU=
MODEL="nvidia_nim/z-ai/glm4.7"
diff --git a/config/settings.py b/config/settings.py
index deb6888c..59c69b0f 100644
--- a/config/settings.py
+++ b/config/settings.py
@@ -119,7 +119,7 @@ class Settings(BaseSettings):
# ==================== Model ====================
# All Claude model requests are mapped to this single model (fallback)
# Format: provider_type/model/name
- model: str = "nvidia_nim/stepfun-ai/step-3.5-flash"
+ model: str = "nvidia_nim/z-ai/glm4.7"
# Per-model overrides (optional, falls back to MODEL)
# Each can use a different provider
@@ -217,6 +217,9 @@ class Settings(BaseSettings):
"allowed_telegram_user_id",
"discord_bot_token",
"allowed_discord_channels",
+ "model_opus",
+ "model_sonnet",
+ "model_haiku",
mode="before",
)
@classmethod
diff --git a/tests/config/test_config.py b/tests/config/test_config.py
index ba53c0de..ae64bece 100644
--- a/tests/config/test_config.py
+++ b/tests/config/test_config.py
@@ -24,7 +24,7 @@ class TestSettings:
monkeypatch.delenv("HTTP_READ_TIMEOUT", raising=False)
monkeypatch.setitem(Settings.model_config, "env_file", ())
settings = Settings()
- assert settings.model == "nvidia_nim/stepfun-ai/step-3.5-flash"
+ assert settings.model == "nvidia_nim/z-ai/glm4.7"
assert isinstance(settings.provider_rate_limit, int)
assert isinstance(settings.provider_rate_window, int)
assert isinstance(settings.nim.temperature, float)
@@ -391,6 +391,19 @@ class TestPerModelMapping:
s = Settings()
assert s.model_opus == "open_router/deepseek/deepseek-r1"
+ @pytest.mark.parametrize("env_var", ["MODEL_OPUS", "MODEL_SONNET", "MODEL_HAIKU"])
+ def test_empty_model_override_env_is_unset(self, monkeypatch, env_var):
+ """Empty per-model override env vars are treated as unset."""
+ from config.settings import Settings
+
+ monkeypatch.setenv(env_var, "")
+ s = Settings()
+ assert getattr(s, env_var.lower()) is None
+ assert (
+ s.resolve_model(f"claude-{env_var.removeprefix('MODEL_').lower()}-4")
+ == s.model
+ )
+
@pytest.mark.parametrize(
"env_vars,expected_model,expected_haiku",
[