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
Add QwenCloud Token Plan provider (#1394)
Ali Khokhar003b582da1e5
diff --git a/.env.example b/.env.exampleindex 2f434838..bb68fb59 100644--- a/.env.example+++ b/.env.example@@ -109,6 +109,10 @@ GROQ_API_KEY=""XAI_API_KEY=""+# QwenCloud Token Plan (dedicated sk-sp- key; OpenAI-compatible Chat Completions)+QWENCLOUD_API_KEY=""++# SambaNova Cloud (OpenAI-compatible Chat Completions at api.sambanova.ai/v1)SAMBANOVA_API_KEY=""@@ -139,7 +143,7 @@ OLLAMA_BASE_URL="http://localhost:11434"# All Claude model requests are mapped to these models, plain model is fallback# Format: provider_type/model/name-# Valid providers: "nvidia_nim" | "openai" | "azure_openai" | "open_router" | "gemini" | "vertex" | "deepseek" | "mistral" | "mistral_codestral" | "opencode_zen" | "opencode_go" | "vercel" | "bedrock" | "huggingface" | "cohere" | "github_models" | "wafer" | "kimi" | "kimi_code" | "minimax" | "cerebras" | "groq" | "sambanova" | "kilo" | "fireworks" | "novita" | "cloudflare" | "zai" | "ollama_cloud" | "lmstudio" | "llamacpp" | "ollama" | "tokenrouter" | "nararoute"+# Valid providers: "nvidia_nim" | "openai" | "azure_openai" | "open_router" | "gemini" | "vertex" | "deepseek" | "mistral" | "mistral_codestral" | "opencode_zen" | "opencode_go" | "vercel" | "bedrock" | "huggingface" | "cohere" | "github_models" | "wafer" | "kimi" | "kimi_code" | "minimax" | "cerebras" | "groq" | "xai" | "qwencloud" | "sambanova" | "kilo" | "fireworks" | "novita" | "cloudflare" | "zai" | "ollama_cloud" | "lmstudio" | "llamacpp" | "ollama" | "tokenrouter" | "nararoute"MODEL_FABLE=MODEL_OPUS=MODEL_SONNET=@@ -181,6 +185,7 @@ FCC_SMOKE_MODEL_CLOUDFLARE=FCC_SMOKE_MODEL_GEMINI=FCC_SMOKE_MODEL_VERTEX=FCC_SMOKE_MODEL_GROQ=+FCC_SMOKE_MODEL_QWENCLOUD=FCC_SMOKE_MODEL_SAMBANOVA=FCC_SMOKE_MODEL_KILO=FCC_SMOKE_MODEL_CEREBRAS=@@ -205,6 +210,7 @@ REASONING_HAIKU=inherit# Per-provider proxy support: http and socks5, example: "http://username:password@host:port"OPENAI_PROXY=""XAI_PROXY=""+QWENCLOUD_PROXY=""AZURE_OPENAI_PROXY=""NVIDIA_NIM_PROXY=""OPENROUTER_PROXY=""diff --git a/README.md b/README.mdindex 7a61e78d..9bfebb90 100644--- a/README.md+++ b/README.md@@ -157,6 +157,7 @@ fcc-codex exec "hello"| [Groq](https://console.groq.com/keys) | `GROQ_API_KEY` | `groq/llama-3.3-70b-versatile` || [OpenAI / ChatGPT](https://learn.chatgpt.com/docs/auth) | Connect ChatGPT in the Admin UI | `openai/<model-id>` || [xAI (Grok)](https://console.x.ai/team/default/api-keys) | `XAI_API_KEY` | `xai/grok-4.5` |+| [QwenCloud Token Plan](https://home.qwencloud.com/api-keys) | `QWENCLOUD_API_KEY` | `qwencloud/qwen3.7-plus` || [Azure OpenAI](https://learn.microsoft.com/azure/foundry/openai/how-to/chatgpt) | `AZURE_OPENAI_API_KEY` and `AZURE_OPENAI_BASE_URL` | `azure_openai/<deployment-name>` || [Google AI Studio (Gemini)](https://aistudio.google.com/apikey) | `GEMINI_API_KEY` | `gemini/models/gemini-3.1-flash-lite` || [Google Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/start/openai) | `VERTEX_PROJECT_ID` + ADC | `vertex/google/gemini-3.5-flash` |diff --git a/pyproject.toml b/pyproject.tomlindex 43383234..4ed4f4de 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "hatchling.build"[project]name = "free-claude-code"-version = "4.21.0"+version = "4.22.0"description = "Local proxy connecting coding agents to OpenAI-compatible AI providers"readme = "README.md"requires-python = ">=3.14.0"diff --git a/smoke/lib/config.py b/smoke/lib/config.pyindex 0dd98f29..c810494f 100644--- a/smoke/lib/config.py+++ b/smoke/lib/config.py@@ -71,6 +71,7 @@ PROVIDER_SMOKE_DEFAULT_MODELS: dict[str, str] = {"vertex": "vertex/google/gemini-3.5-flash","groq": "groq/llama-3.3-70b-versatile","xai": "xai/grok-4.5",+ "qwencloud": "qwencloud/qwen3.7-plus","sambanova": "sambanova/Meta-Llama-3.3-70B-Instruct","kilo": "kilo/kilo-auto/free","cerebras": "cerebras/llama3.1-8b",diff --git a/src/free_claude_code/config/admin/provider_manifest.py b/src/free_claude_code/config/admin/provider_manifest.pyindex 89c0869a..7eb05181 100644--- a/src/free_claude_code/config/admin/provider_manifest.py+++ b/src/free_claude_code/config/admin/provider_manifest.py@@ -144,6 +144,14 @@ _PROVIDER_FIELD_OVERRIDES: dict[str, dict[str, Any]] = {"models."),},+ "QWENCLOUD_API_KEY": {+ "label": "QwenCloud Token Plan API Key",+ "description": (+ "Dedicated QwenCloud Token Plan key (sk-sp-...). Token Plan, Coding "+ "Plan, and pay-as-you-go keys use separate endpoints and cannot be "+ "mixed."+ ),+ },"SAMBANOVA_API_KEY": {"label": "SambaNova API Key","description": (diff --git a/src/free_claude_code/config/provider_catalog.py b/src/free_claude_code/config/provider_catalog.pyindex f81f6af6..239ad0d2 100644--- a/src/free_claude_code/config/provider_catalog.py+++ b/src/free_claude_code/config/provider_catalog.py@@ -52,6 +52,10 @@ KILO_DEFAULT_BASE = "https://api.kilo.ai/api/gateway"OPENAI_CODEX_DEFAULT_BASE = "https://chatgpt.com/backend-api/codex"# xAI OpenAI-compatible Chat Completions API.XAI_DEFAULT_BASE = "https://api.x.ai/v1"+# QwenCloud Token Plan OpenAI-compatible Chat Completions API.+QWENCLOUD_DEFAULT_BASE = (+ "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1"+)# TokenRouter OpenAI-compatible Chat Completions gateway.TOKENROUTER_DEFAULT_BASE = "https://api.tokenrouter.com/v1"# NaraRoute OpenAI-compatible Chat Completions gateway.@@ -137,6 +141,15 @@ PROVIDER_CATALOG: dict[str, ProviderDescriptor] = {default_base_url=XAI_DEFAULT_BASE,proxy_attr="xai_proxy",),+ "qwencloud": ProviderDescriptor(+ provider_id="qwencloud",+ display_name="QwenCloud Token Plan",+ credential_env="QWENCLOUD_API_KEY",+ credential_url="https://home.qwencloud.com/api-keys",+ credential_attr="qwencloud_api_key",+ default_base_url=QWENCLOUD_DEFAULT_BASE,+ proxy_attr="qwencloud_proxy",+ ),"azure_openai": ProviderDescriptor(provider_id="azure_openai",display_name="Azure OpenAI",diff --git a/src/free_claude_code/config/settings.py b/src/free_claude_code/config/settings.pyindex 52946cdd..cef0e03a 100644--- a/src/free_claude_code/config/settings.py+++ b/src/free_claude_code/config/settings.py@@ -134,6 +134,9 @@ class Settings(BaseSettings):# ==================== xAI / Grok (OpenAI-compatible) ====================xai_api_key: str = Field(default="", validation_alias="XAI_API_KEY")+ # ==================== QwenCloud Token Plan (OpenAI-compatible) ====================+ qwencloud_api_key: str = Field(default="", validation_alias="QWENCLOUD_API_KEY")+# ==================== Cerebras Inference (OpenAI-compatible) ====================cerebras_api_key: str = Field(default="", validation_alias="CEREBRAS_API_KEY")@@ -188,6 +191,7 @@ class Settings(BaseSettings):# ==================== Per-Provider Proxy ====================openai_proxy: str = Field(default="", validation_alias="OPENAI_PROXY")xai_proxy: str = Field(default="", validation_alias="XAI_PROXY")+ qwencloud_proxy: str = Field(default="", validation_alias="QWENCLOUD_PROXY")azure_openai_proxy: str = Field(default="", validation_alias="AZURE_OPENAI_PROXY")nvidia_nim_proxy: str = Field(default="", validation_alias="NVIDIA_NIM_PROXY")open_router_proxy: str = Field(default="", validation_alias="OPENROUTER_PROXY")diff --git a/src/free_claude_code/providers/openai_chat/profiles.py b/src/free_claude_code/providers/openai_chat/profiles.pyindex 0cd43f19..2bc80d66 100644--- a/src/free_claude_code/providers/openai_chat/profiles.py+++ b/src/free_claude_code/providers/openai_chat/profiles.py@@ -162,6 +162,14 @@ OPENAI_CHAT_PROFILES: dict[str, OpenAIChatProfile] = {aliases_field="aliases",),),+ "qwencloud": OpenAIChatProfile(+ _policy(+ "QWENCLOUD",+ ReasoningReplayMode.REASONING_CONTENT,+ default_max_tokens=ANTHROPIC_DEFAULT_MAX_OUTPUT_TOKENS,+ ),+ NO_REASONING,+ ),"azure_openai": OpenAIChatProfile(_policy("AZURE_OPENAI",diff --git a/tests/contracts/test_provider_catalog_order.py b/tests/contracts/test_provider_catalog_order.pyindex efdd230c..7e0353fa 100644--- a/tests/contracts/test_provider_catalog_order.py+++ b/tests/contracts/test_provider_catalog_order.py@@ -11,6 +11,7 @@ _EXPECTED_PROVIDER_ORDER: tuple[str, ...] = ("groq","openai","xai",+ "qwencloud","azure_openai","gemini","vertex",diff --git a/tests/contracts/test_smoke_config.py b/tests/contracts/test_smoke_config.pyindex 6febfa1c..860e5de6 100644--- a/tests/contracts/test_smoke_config.py+++ b/tests/contracts/test_smoke_config.py@@ -54,6 +54,7 @@ def _settings(**overrides):"vertex_location": "global","groq_api_key": "","xai_api_key": "",+ "qwencloud_api_key": "","sambanova_api_key": "","cerebras_api_key": "","ollama_api_key": "",@@ -169,6 +170,23 @@ def test_xai_provider_smoke_uses_current_grok_model(monkeypatch) -> None:assert models[0].source == "provider_default"+def test_qwencloud_provider_smoke_uses_current_coding_model(monkeypatch) -> None:+ monkeypatch.delenv("FCC_SMOKE_MODEL_QWENCLOUD", raising=False)+ config = _smoke_config(+ settings=_settings(+ model="ollama/llama3.1",+ ollama_base_url="",+ qwencloud_api_key="qwencloud-key",+ )+ )++ models = config.provider_smoke_models()++ assert [model.provider for model in models] == ["qwencloud"]+ assert models[0].full_model == "qwencloud/qwen3.7-plus"+ assert models[0].source == "provider_default"++def test_connected_account_provider_smoke_requires_explicit_model(monkeypatch,) -> None:diff --git a/tests/providers/test_provider_runtime.py b/tests/providers/test_provider_runtime.pyindex 138c2484..92d9900d 100644--- a/tests/providers/test_provider_runtime.py+++ b/tests/providers/test_provider_runtime.py@@ -20,6 +20,7 @@ from free_claude_code.config.provider_catalog import (NARAROUTE_DEFAULT_BASE,OLLAMA_CLOUD_DEFAULT_BASE,PROVIDER_CATALOG,+ QWENCLOUD_DEFAULT_BASE,SUPPORTED_PROVIDER_IDS,TOKENROUTER_DEFAULT_BASE,VERCEL_AI_GATEWAY_DEFAULT_BASE,@@ -62,6 +63,7 @@ def _make_settings(**overrides):mock.nvidia_nim_api_key = "test_key"mock.open_router_api_key = "test_openrouter_key"mock.xai_api_key = "test_xai_key"+ mock.qwencloud_api_key = "test_qwencloud_key"mock.mistral_api_key = "test_mistral_key"mock.codestral_api_key = "test_codestral_key"mock.deepseek_api_key = "test_deepseek_key"@@ -126,6 +128,7 @@ def _make_settings(**overrides):mock.kilo_proxy = ""mock.openai_proxy = ""mock.xai_proxy = ""+ mock.qwencloud_proxy = ""mock.azure_openai_proxy = ""mock.provider_rate_limit = 40mock.provider_rate_window = 60@@ -214,6 +217,25 @@ def test_xai_provider_config_uses_key_base_and_proxy() -> None:assert isinstance(provider, OpenAIChatProvider)+def test_qwencloud_provider_config_uses_key_base_and_proxy() -> None:+ descriptor = PROVIDER_CATALOG["qwencloud"]+ settings = _make_settings(+ qwencloud_api_key="qwencloud-token",+ qwencloud_proxy="http://proxy.test:8080",+ )++ config = build_provider_config(descriptor, settings)+ with patch("free_claude_code.providers.openai_chat.provider.AsyncOpenAI"):+ provider = create_provider("qwencloud", settings)++ assert descriptor.display_name == "QwenCloud Token Plan"+ assert descriptor.credential_env == "QWENCLOUD_API_KEY"+ assert config.api_key == "qwencloud-token"+ assert config.base_url == QWENCLOUD_DEFAULT_BASE+ assert config.proxy == "http://proxy.test:8080"+ assert isinstance(provider, OpenAIChatProvider)++def test_bedrock_provider_config_uses_regional_base_key_and_proxy() -> None:descriptor = PROVIDER_CATALOG["bedrock"]settings = _make_settings(@@ -506,6 +528,7 @@ def test_create_provider_instantiates_each_builtin():"nvidia_nim": NvidiaNimProvider,"openai": OpenAICodexProvider,"xai": OpenAIChatProvider,+ "qwencloud": OpenAIChatProvider,"azure_openai": OpenAIChatProvider,"open_router": OpenRouterProvider,"mistral": MistralProvider,diff --git a/tests/providers/test_qwencloud.py b/tests/providers/test_qwencloud.pynew file mode 100644index 00000000..16c16230--- /dev/null+++ b/tests/providers/test_qwencloud.py@@ -0,0 +1,228 @@+"""Tests for the QwenCloud Token Plan OpenAI-chat provider profile."""++from types import SimpleNamespace+from unittest.mock import AsyncMock++import httpx+import pytest+from openai import AsyncOpenAI++from free_claude_code.application.model_metadata import ProviderModelInfo+from free_claude_code.config.constants import ANTHROPIC_DEFAULT_MAX_OUTPUT_TOKENS+from free_claude_code.config.provider_catalog import QWENCLOUD_DEFAULT_BASE+from free_claude_code.core.anthropic.models import MessagesRequest+from free_claude_code.providers.base import ProviderConfig+from free_claude_code.providers.model_listing import ModelListResponseError+from free_claude_code.providers.openai_chat import OpenAIChatProvider+from tests.providers.support import (+ REASONING_OFF,+ REASONING_ON,+ immediate_admission,+ profiled_provider,+ reasoning_for,+)+++def qwencloud_provider() -> OpenAIChatProvider:+ return profiled_provider(+ "qwencloud",+ ProviderConfig(+ api_key="test-qwencloud-key",+ base_url=QWENCLOUD_DEFAULT_BASE,+ rate_limit=10,+ rate_window=60,+ ),+ admission=immediate_admission(provider_name="qwencloud"),+ )+++def test_init_uses_openai_chat_provider(+ qwencloud_provider: OpenAIChatProvider,+) -> None:+ assert qwencloud_provider._api_key == "test-qwencloud-key"+ assert qwencloud_provider._base_url == QWENCLOUD_DEFAULT_BASE+ assert qwencloud_provider._provider_name == "QWENCLOUD"+++def test_build_request_body_preserves_common_chat_tools_and_images(+ qwencloud_provider: OpenAIChatProvider,+) -> None:+ request = MessagesRequest.model_validate(+ {+ "model": "qwen3.7-plus",+ "system": "Be concise.",+ "messages": [+ {+ "role": "user",+ "content": [+ {"type": "text", "text": "Inspect this image."},+ {+ "type": "image",+ "source": {+ "type": "base64",+ "media_type": "image/png",+ "data": "aW1hZ2U=",+ },+ },+ ],+ }+ ],+ "tools": [+ {+ "name": "inspect_image",+ "description": "Inspect an image",+ "input_schema": {+ "type": "object",+ "properties": {"detail": {"type": "string"}},+ },+ }+ ],+ }+ )++ body = qwencloud_provider._build_request_body(+ request,+ reasoning=reasoning_for(request),+ )++ assert body["model"] == "qwen3.7-plus"+ assert body["max_tokens"] == ANTHROPIC_DEFAULT_MAX_OUTPUT_TOKENS+ assert body["messages"][0] == {"role": "system", "content": "Be concise."}+ assert body["messages"][1]["content"] == [+ {"type": "text", "text": "Inspect this image."},+ {+ "type": "image_url",+ "image_url": {"url": "data:image/png;base64,aW1hZ2U="},+ },+ ]+ assert body["tools"][0]["function"]["name"] == "inspect_image"++[email protected]("reasoning", [REASONING_OFF, REASONING_ON])+def test_build_request_body_does_not_invent_catalog_wide_reasoning_control(+ qwencloud_provider: OpenAIChatProvider,+ reasoning,+) -> None:+ request = MessagesRequest.model_validate(+ {+ "model": "qwen3.7-plus",+ "messages": [{"role": "user", "content": "Hello"}],+ }+ )++ body = qwencloud_provider._build_request_body(request, reasoning=reasoning)+ extra_body = body.get("extra_body", {})++ for field in (+ "enable_thinking",+ "preserve_thinking",+ "reasoning_effort",+ "thinking_budget",+ ):+ assert field not in body+ assert field not in extra_body+++def test_build_request_body_replays_prior_reasoning_content(+ qwencloud_provider: OpenAIChatProvider,+) -> None:+ request = MessagesRequest.model_validate(+ {+ "model": "qwen3.7-plus",+ "messages": [+ {"role": "user", "content": "Solve it."},+ {+ "role": "assistant",+ "content": [+ {"type": "thinking", "thinking": "Work through it."},+ {"type": "text", "text": "The answer is 42."},+ ],+ },+ {"role": "user", "content": "Continue."},+ ],+ }+ )++ body = qwencloud_provider._build_request_body(+ request,+ reasoning=reasoning_for(request),+ )++ assert body["messages"][1] == {+ "role": "assistant",+ "content": "The answer is 42.",+ "reasoning_content": "Work through it.",+ }+ assert (+ qwencloud_provider._profile.reasoning_delta(+ SimpleNamespace(reasoning_content="next thought")+ )+ == "next thought"+ )+++async def test_model_catalog_uses_standard_endpoint_base_url_and_auth(+ qwencloud_provider: OpenAIChatProvider,+) -> None:+ requests: list[httpx.Request] = []++ def handler(request: httpx.Request) -> httpx.Response:+ requests.append(request)+ return httpx.Response(+ 200,+ json={+ "object": "list",+ "data": [+ {+ "id": "qwen3.7-plus",+ "object": "model",+ "created": 0,+ "owned_by": "qwencloud",+ },+ {+ "id": "deepseek-v4-pro",+ "object": "model",+ "created": 0,+ "owned_by": "qwencloud",+ },+ ],+ },+ )++ await qwencloud_provider._client.close()+ qwencloud_provider._client = AsyncOpenAI(+ api_key="wire-qwencloud-key",+ base_url=QWENCLOUD_DEFAULT_BASE,+ max_retries=0,+ http_client=httpx.AsyncClient(transport=httpx.MockTransport(handler)),+ )+ try:+ model_infos = await qwencloud_provider.list_model_infos()+ finally:+ await qwencloud_provider.cleanup()++ assert model_infos == frozenset(+ {+ ProviderModelInfo("qwen3.7-plus"),+ ProviderModelInfo("deepseek-v4-pro"),+ }+ )+ assert len(requests) == 1+ assert str(requests[0].url) == (+ "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/models"+ )+ assert requests[0].headers["authorization"] == "Bearer wire-qwencloud-key"+++async def test_empty_model_catalog_fails_instead_of_publishing_partial_state(+ qwencloud_provider: OpenAIChatProvider,+) -> None:+ qwencloud_provider._client.models.list = AsyncMock(+ return_value=SimpleNamespace(data=[])+ )++ with pytest.raises(ModelListResponseError, match="did not include any model ids"):+ await qwencloud_provider.list_model_infos()diff --git a/uv.lock b/uv.lockindex 26a049b7..d7801129 100644--- a/uv.lock+++ b/uv.lock@@ -620,7 +620,7 @@ wheels = [[[package]]name = "free-claude-code"-version = "4.21.0"+version = "4.22.0"source = { editable = "." }dependencies = [{ name = "aiohttp" },