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

feat: add Kilo.ai provider (#1273)

tdogghockey58147b1e18e6
diff --git a/.env.example b/.env.example
index 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.md
index 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.toml
index 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.py
index 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.py
index 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.py
index 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.py
index 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.py
new file mode 100644
index 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.py
index 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 = 40
mock.provider_rate_window = 60
mock.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.lock
index 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" },