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
feat: add Kilo.ai provider (#1273)
tdogghockey58147b1e18e6
diff --git a/.env.example b/.env.exampleindex 09f37f8e..04bc7329 100644--- a/.env.example+++ b/.env.example@@ -90,6 +90,10 @@ GROQ_API_KEY=""SAMBANOVA_API_KEY=""+# Kilo.ai Config (OpenAI-compatible Chat Completions gateway at api.kilo.ai/api/gateway)+KILO_API_KEY=""++# Cerebras Inference (OpenAI-compatible Chat Completions; see https://inference-docs.cerebras.ai/resources/openai)CEREBRAS_API_KEY=""@@ -112,7 +116,7 @@ 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" | "open_router" | "gemini" | "vertex" | "deepseek" | "mistral" | "mistral_codestral" | "opencode" | "opencode_go" | "vercel" | "bedrock" | "huggingface" | "cohere" | "github_models" | "wafer" | "kimi" | "kimi_code" | "minimax" | "cerebras" | "groq" | "sambanova" | "fireworks" | "cloudflare" | "zai" | "ollama_cloud" | "lmstudio" | "llamacpp" | "ollama"+# Valid providers: "nvidia_nim" | "open_router" | "gemini" | "vertex" | "deepseek" | "mistral" | "mistral_codestral" | "opencode" | "opencode_go" | "vercel" | "bedrock" | "huggingface" | "cohere" | "github_models" | "wafer" | "kimi" | "kimi_code" | "minimax" | "cerebras" | "groq" | "sambanova" | "kilo" | "fireworks" | "cloudflare" | "zai" | "ollama_cloud" | "lmstudio" | "llamacpp" | "ollama"MODEL_FABLE=MODEL_OPUS=MODEL_SONNET=@@ -194,6 +198,7 @@ GEMINI_PROXY=""VERTEX_PROXY=""GROQ_PROXY=""SAMBANOVA_PROXY=""+KILO_PROXY=""CEREBRAS_PROXY=""OLLAMA_CLOUD_PROXY=""diff --git a/README.md b/README.mdindex a30fd4e1..ddfcb58d 100644--- a/README.md+++ b/README.md@@ -187,6 +187,7 @@ fcc-codex exec "hello"| [Cerebras Inference](https://cloud.cerebras.ai/) | `CEREBRAS_API_KEY` | `cerebras/gpt-oss-120b` || [Groq](https://console.groq.com/keys) | `GROQ_API_KEY` | `groq/llama-3.3-70b-versatile` || [SambaNova](https://cloud.sambanova.ai/apis) | `SAMBANOVA_API_KEY` | `sambanova/Meta-Llama-3.3-70B-Instruct` |+| [Kilo.ai](https://kilo.ai) | `KILO_API_KEY` | `kilo/kilo-auto/free` || [Fireworks AI](https://fireworks.ai/account/api-keys) | `FIREWORKS_API_KEY` | `fireworks/accounts/fireworks/models/llama-v3p3-70b-instruct` || [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/) | `CLOUDFLARE_API_TOKEN` and `CLOUDFLARE_ACCOUNT_ID` | `cloudflare/@cf/moonshotai/kimi-k2.6` || [Z.ai](https://z.ai/manage-apikey/apikey-list) | `ZAI_API_KEY` | `zai/glm-5.2` |diff --git a/pyproject.toml b/pyproject.tomlindex 7d05ed0f..9af86e6e 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "hatchling.build"[project]name = "free-claude-code"-version = "4.12.11"+version = "4.13.0"description = "Local proxy connecting coding agents to OpenAI-compatible AI providers"readme = "README.md"requires-python = ">=3.14.0"diff --git a/src/free_claude_code/config/provider_catalog.py b/src/free_claude_code/config/provider_catalog.pyindex 08ad752a..89617124 100644--- a/src/free_claude_code/config/provider_catalog.py+++ b/src/free_claude_code/config/provider_catalog.py@@ -45,6 +45,8 @@ VERTEX_AI_API_ROOT = "https://aiplatform.googleapis.com"GROQ_DEFAULT_BASE = "https://api.groq.com/openai/v1"CEREBRAS_DEFAULT_BASE = "https://api.cerebras.ai/v1"SAMBANOVA_DEFAULT_BASE = "https://api.sambanova.ai/v1"+# Kilo.ai gateway OpenAI-compatible Chat Completions API.+KILO_DEFAULT_BASE = "https://api.kilo.ai/api/gateway"@dataclass(frozen=True, slots=True)@@ -230,6 +232,15 @@ PROVIDER_CATALOG: dict[str, ProviderDescriptor] = {default_base_url=KIMI_CODE_DEFAULT_BASE,proxy_attr="kimi_code_proxy",),+ "kilo": ProviderDescriptor(+ provider_id="kilo",+ display_name="Kilo.ai",+ credential_env="KILO_API_KEY",+ credential_url="https://app.kilo.ai",+ credential_attr="kilo_api_key",+ default_base_url=KILO_DEFAULT_BASE,+ proxy_attr="kilo_proxy",+ ),"minimax": ProviderDescriptor(provider_id="minimax",display_name="MiniMax",diff --git a/src/free_claude_code/config/settings.py b/src/free_claude_code/config/settings.pyindex efc91bca..c22087c1 100644--- a/src/free_claude_code/config/settings.py+++ b/src/free_claude_code/config/settings.py@@ -74,6 +74,9 @@ class Settings(BaseSettings):# ==================== SambaNova Cloud ====================sambanova_api_key: str = Field(default="", validation_alias="SAMBANOVA_API_KEY")+ # ==================== Kilo.ai Config ====================+ kilo_api_key: str = Field(default="", validation_alias="KILO_API_KEY")+# ==================== Z.ai Config ====================zai_api_key: str = Field(default="", validation_alias="ZAI_API_KEY")@@ -170,6 +173,7 @@ class Settings(BaseSettings):cohere_proxy: str = Field(default="", validation_alias="COHERE_PROXY")github_models_proxy: str = Field(default="", validation_alias="GITHUB_MODELS_PROXY")sambanova_proxy: str = Field(default="", validation_alias="SAMBANOVA_PROXY")+ kilo_proxy: str = Field(default="", validation_alias="KILO_PROXY")zai_proxy: str = Field(default="", validation_alias="ZAI_PROXY")fireworks_proxy: str = Field(default="", validation_alias="FIREWORKS_PROXY")cloudflare_proxy: str = Field(default="", validation_alias="CLOUDFLARE_PROXY")diff --git a/src/free_claude_code/providers/openai_chat/profiles.py b/src/free_claude_code/providers/openai_chat/profiles.pyindex 9404e5b9..2e58b901 100644--- a/src/free_claude_code/providers/openai_chat/profiles.py+++ b/src/free_claude_code/providers/openai_chat/profiles.py@@ -295,6 +295,15 @@ OPENAI_CHAT_PROFILES: dict[str, OpenAIChatProfile] = {enabled_value="medium",),),+ "kilo": OpenAIChatProfile(+ _policy(+ "KILO",+ ReasoningReplayMode.REASONING_CONTENT,+ include_extra_body=True,+ extra_body_validator=validate_extra_body_does_not_override_reasoning_fields,+ ),+ ReasoningObject(_ALL_EFFORTS),+ ),"fireworks": OpenAIChatProfile(_policy("FIREWORKS",diff --git a/tests/contracts/test_provider_catalog_order.py b/tests/contracts/test_provider_catalog_order.pyindex 4ff9edb4..687878c0 100644--- a/tests/contracts/test_provider_catalog_order.py+++ b/tests/contracts/test_provider_catalog_order.py@@ -23,6 +23,7 @@ _EXPECTED_PROVIDER_ORDER: tuple[str, ...] = ("wafer","kimi","kimi_code",+ "kilo","minimax","cerebras","groq",diff --git a/tests/providers/test_kilo.py b/tests/providers/test_kilo.pynew file mode 100644index 00000000..fc7a4ff7--- /dev/null+++ b/tests/providers/test_kilo.py@@ -0,0 +1,139 @@+"""Tests for the Kilo.ai OpenAI-chat provider."""++from unittest.mock import AsyncMock, MagicMock++import pytest++from free_claude_code.application.model_metadata import ProviderModelInfo+from free_claude_code.config.provider_catalog import KILO_DEFAULT_BASE+from free_claude_code.core.anthropic.models import Message, MessagesRequest+from free_claude_code.providers.base import ProviderConfig+from free_claude_code.providers.openai_chat import OpenAIChatProvider+from tests.providers.support import (+ immediate_admission,+ profiled_provider,+ reasoning_for,+)+++def kilo_config():+ return ProviderConfig(+ api_key="test_kilo_key",+ base_url=KILO_DEFAULT_BASE,+ rate_limit=10,+ rate_window=60,+ )+++def kilo_provider(kilo_config):+ return profiled_provider(+ "kilo",+ kilo_config,+ admission=immediate_admission(),+ )+++def test_default_base_url():+ assert KILO_DEFAULT_BASE == "https://api.kilo.ai/api/gateway"+++def test_init_uses_openai_chat_provider(kilo_provider):+ assert isinstance(kilo_provider, OpenAIChatProvider)+ assert kilo_provider._api_key == "test_kilo_key"+ assert kilo_provider._base_url == KILO_DEFAULT_BASE+ assert kilo_provider._provider_name == "KILO"+++def test_build_request_body_openai_shape(kilo_provider):+ request = MessagesRequest.model_validate(+ {+ "model": "anthropic/claude-sonnet-4.5",+ "messages": [Message(role="user", content="Hello")],+ "max_tokens": 100,+ }+ )++ body = kilo_provider._build_request_body(request, reasoning=reasoning_for(request))++ assert body["model"] == "anthropic/claude-sonnet-4.5"+ assert body["messages"][0] == {"role": "user", "content": "Hello"}+ assert body["max_tokens"] == 100+++def test_build_request_body_forwards_caller_extra_body(kilo_provider):+ request = MessagesRequest.model_validate(+ {+ "model": "m",+ "messages": [{"role": "user", "content": "hi"}],+ "extra_body": {"custom_field": "value"},+ }+ )++ body = kilo_provider._build_request_body(request, reasoning=reasoning_for(request))++ assert body.get("extra_body", {}).get("custom_field") == "value"+++def test_build_request_body_sends_reasoning_object(kilo_provider):+ request = MessagesRequest.model_validate(+ {+ "model": "m",+ "messages": [{"role": "user", "content": "hi"}],+ "thinking": {"type": "enabled", "budget_tokens": 2048},+ }+ )++ body = kilo_provider._build_request_body(request, reasoning=reasoning_for(request))++ assert body.get("extra_body", {}).get("reasoning") is not None+++def test_build_request_body_sends_reasoning_disabled(kilo_provider):+ from free_claude_code.core.reasoning import ReasoningControl, ReasoningPolicy++ request = MessagesRequest.model_validate(+ {+ "model": "m",+ "messages": [{"role": "user", "content": "hi"}],+ }+ )++ body = kilo_provider._build_request_body(+ request,+ reasoning=ReasoningPolicy(control=ReasoningControl.OFF),+ )++ assert body["extra_body"]["reasoning"] == {"enabled": False}+++async def test_model_list_uses_openai_client_models_endpoint(kilo_provider):+ kilo_provider._client.models.list = AsyncMock(+ return_value=MagicMock(+ data=[+ MagicMock(id="anthropic/claude-sonnet-4.5"),+ MagicMock(id="openai/gpt-5.4"),+ ]+ )+ )++ assert await kilo_provider.list_model_infos() == frozenset(+ {+ ProviderModelInfo("anthropic/claude-sonnet-4.5"),+ ProviderModelInfo("openai/gpt-5.4"),+ }+ )++ kilo_provider._client.models.list.assert_awaited_once_with()+++async def test_cleanup_closes_openai_client(kilo_provider):+ kilo_provider._client = MagicMock()+ kilo_provider._client.close = AsyncMock()++ await kilo_provider.cleanup()++ kilo_provider._client.close.assert_awaited_once()diff --git a/tests/providers/test_provider_runtime.py b/tests/providers/test_provider_runtime.pyindex b84833fa..bb4b5077 100644--- a/tests/providers/test_provider_runtime.py+++ b/tests/providers/test_provider_runtime.py@@ -102,6 +102,8 @@ def _make_settings(**overrides):mock.cerebras_api_key = ""mock.cerebras_proxy = ""mock.ollama_cloud_proxy = ""+ mock.kilo_api_key = "test_kilo_key"+ mock.kilo_proxy = ""mock.provider_rate_limit = 40mock.provider_rate_window = 60mock.provider_max_concurrency = 5@@ -439,6 +441,7 @@ def test_create_provider_instantiates_each_builtin():"vertex": VertexProvider,"groq": OpenAIChatProvider,"sambanova": OpenAIChatProvider,+ "kilo": OpenAIChatProvider,"cerebras": OpenAIChatProvider,}sentinel_admission = MagicMock(spec=ProviderAdmissionController)diff --git a/uv.lock b/uv.lockindex 0a4749f3..2d350f9a 100644--- a/uv.lock+++ b/uv.lock@@ -620,7 +620,7 @@ wheels = [[[package]]name = "free-claude-code"-version = "4.12.11"+version = "4.13.0"source = { editable = "." }dependencies = [{ name = "aiohttp" },