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

Add LLM7.io as the 50th provider (#1536)

Ali Khokhar9b334dedfec8
diff --git a/.env.example b/.env.example
index d908ca4f..add20b06 100644
--- a/.env.example
+++ b/.env.example
@@ -82,6 +82,11 @@ NARAROUTE_BASE_URL="https://router.bynara.id/v1"
# Poolside AI (OpenAI-compatible Chat Completions at inference.poolside.ai/v1)
# POOLSIDE_API_KEY=<your-token>
+
+# LLM7.io (OpenAI-compatible Chat Completions at api.llm7.io/v1)
+# LLM7_API_KEY=<your-token>
+
+
# Fireworks AI Config (OpenAI-compatible Chat Completions at api.fireworks.ai/inference/v1)
# FIREWORKS_API_KEY=<your-token>
@@ -191,7 +196,7 @@ OLLAMA_BASE_URL="http://localhost:11434"
# Default model and optional Claude tier overrides
# 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" | "cline_pass" | "xai" | "qwencloud" | "qwencloud_coding" | "together" | "deepinfra" | "siliconflow" | "nebius" | "chutes" | "featherless" | "agnes" | "zenmux" | "wandb" | "sambanova" | "kilo" | "fireworks" | "novita" | "cloudflare" | "zai" | "ollama_cloud" | "lmstudio" | "llamacpp" | "ollama" | "tokenrouter" | "nararoute" | "poolside"
+# 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" | "cline_pass" | "xai" | "qwencloud" | "qwencloud_coding" | "together" | "deepinfra" | "siliconflow" | "nebius" | "chutes" | "featherless" | "agnes" | "zenmux" | "wandb" | "sambanova" | "kilo" | "fireworks" | "novita" | "cloudflare" | "zai" | "ollama_cloud" | "lmstudio" | "llamacpp" | "ollama" | "tokenrouter" | "nararoute" | "poolside" | "llm7"
# MODEL_FABLE=<provider/model-id>
# MODEL_OPUS=<provider/model-id>
# MODEL_SONNET=<provider/model-id>
@@ -232,6 +237,7 @@ MODEL="nvidia_nim/nvidia/nemotron-3-super-120b-a12b"
# FCC_SMOKE_MODEL_TOKENROUTER=<your-token>
# FCC_SMOKE_MODEL_NARAROUTE=<provider/model-id>
# FCC_SMOKE_MODEL_POOLSIDE=<provider/model-id>
+# FCC_SMOKE_MODEL_LLM7=<provider/model-id>
# FCC_SMOKE_MODEL_FIREWORKS=<provider/model-id>
# FCC_SMOKE_MODEL_NOVITA=<provider/model-id>
# FCC_SMOKE_MODEL_CLOUDFLARE=<provider/model-id>
@@ -308,6 +314,7 @@ REASONING_HAIKU=inherit
# TOKENROUTER_PROXY=<http-or-socks-url>
# NARAROUTE_PROXY=<http-or-socks-url>
# POOLSIDE_PROXY=<http-or-socks-url>
+# LLM7_PROXY=<http-or-socks-url>
# FIREWORKS_PROXY=<http-or-socks-url>
# NOVITA_PROXY=<http-or-socks-url>
# CLOUDFLARE_PROXY=<http-or-socks-url>
diff --git a/README.md b/README.md
index 69aaedcd..2ed0dd09 100644
--- a/README.md
+++ b/README.md
@@ -25,7 +25,7 @@
## What You Get
-- **49 ToS-friendly providers. 1.3B+ free tokens every month.** Use free, paid, subscription, and local models from one searchable UI without putting your account at risk. FCC follows provider terms and removes integrations if they stop being allowed.
+- **50 ToS-friendly providers. 1.3B+ free tokens every month.** Use free, paid, subscription, and local models from one searchable UI without putting your account at risk. FCC follows provider terms and removes integrations if they stop being allowed.
- **9 coding agents. One model catalog.** Run [Claude Code](https://code.claude.com/docs/en/overview), [Codex](https://github.com/openai/codex), [Pi](https://github.com/earendil-works/pi), [OpenCode](https://github.com/anomalyco/opencode), [Cline](https://github.com/cline/cline), [Hermes](https://github.com/NousResearch/hermes-agent), [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness), [Grok Build](https://github.com/xai-org/grok-build), or [Muse Code](https://research.meta.ai/blog/introducing-muse-code-and-muse-spark-1-2/) with your FCC models.
- **Keep coding through provider outages.** After retries are exhausted, FCC automatically tries your next configured model without making you restart the turn—across every client.
- **Up to 90% fewer terminal-output tokens.** Optional [RTK](https://github.com/rtk-ai/rtk) filters common command output, while five FCC optimizations handle quota probes, command-prefix detection, titles, suggestions, and filepaths without calling a provider.
@@ -225,6 +225,7 @@ from more than one provider before succeeding.
| [TokenRouter](https://www.tokenrouter.com/) | `TOKENROUTER_API_KEY` | `tokenrouter/moonshotai/kimi-k3-free` |
| [NaraRoute](https://router.bynara.id/) | `NARAROUTE_API_KEY` | `nararoute/kimi-k3-free` |
| [Poolside AI](https://platform.poolside.ai/) | `POOLSIDE_API_KEY` | `poolside/poolside/laguna-s-2.1` |
+| [LLM7.io](https://dash.llm7.io/) | `LLM7_API_KEY` | `llm7/default` |
| [Ollama Cloud](https://ollama.com/settings/keys) | `OLLAMA_API_KEY` | `ollama_cloud/qwen3-coder:480b` |
| [LM Studio](https://lmstudio.ai/) | `LM_STUDIO_BASE_URL` | `lmstudio/<model-id>` |
| [llama.cpp](https://github.com/ggml-org/llama.cpp) | `LLAMACPP_BASE_URL` | `llamacpp/<model-id>` |
diff --git a/pyproject.toml b/pyproject.toml
index fd914bd2..1004200e 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
[project]
name = "free-claude-code"
-version = "5.13.10"
+version = "5.14.0"
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.py
index 87675620..55f61d55 100644
--- a/smoke/lib/config.py
+++ b/smoke/lib/config.py
@@ -90,6 +90,7 @@ PROVIDER_SMOKE_DEFAULT_MODELS: dict[str, str] = {
"tokenrouter": "tokenrouter/moonshotai/kimi-k3-free",
"nararoute": "nararoute/kimi-k3-free",
"poolside": "poolside/poolside/laguna-s-2.1",
+ "llm7": "llm7/default",
"agnes": "agnes/agnes-2.0-flash",
"zenmux": "zenmux/deepseek/deepseek-v4-flash-free",
"wandb": "wandb/openai/gpt-oss-20b",
diff --git a/src/free_claude_code/config/provider_catalog.py b/src/free_claude_code/config/provider_catalog.py
index bbf3c2a3..8fb63945 100644
--- a/src/free_claude_code/config/provider_catalog.py
+++ b/src/free_claude_code/config/provider_catalog.py
@@ -79,6 +79,8 @@ TOKENROUTER_DEFAULT_BASE = "https://api.tokenrouter.com/v1"
NARAROUTE_DEFAULT_BASE = "https://router.bynara.id/v1"
# Poolside AI OpenAI-compatible Chat Completions API.
POOLSIDE_DEFAULT_BASE = "https://inference.poolside.ai/v1"
+# LLM7.io OpenAI-compatible Chat Completions API.
+LLM7_DEFAULT_BASE = "https://api.llm7.io/v1"
# Agnes AI OpenAI-compatible Chat Completions API.
AGNES_DEFAULT_BASE = "https://apihub.agnes-ai.com/v1"
# ZenMux OpenAI-compatible Chat Completions gateway.
@@ -538,6 +540,15 @@ PROVIDER_CATALOG: dict[str, ProviderDescriptor] = {
default_base_url=POOLSIDE_DEFAULT_BASE,
proxy_attr="poolside_proxy",
),
+ "llm7": ProviderDescriptor(
+ provider_id="llm7",
+ display_name="LLM7.io",
+ credential_env="LLM7_API_KEY",
+ credential_url="https://dash.llm7.io/",
+ credential_attr="llm7_api_key",
+ default_base_url=LLM7_DEFAULT_BASE,
+ proxy_attr="llm7_proxy",
+ ),
"ollama_cloud": ProviderDescriptor(
provider_id="ollama_cloud",
display_name="Ollama Cloud",
diff --git a/src/free_claude_code/config/settings.py b/src/free_claude_code/config/settings.py
index d0b605fb..ff4b7d14 100644
--- a/src/free_claude_code/config/settings.py
+++ b/src/free_claude_code/config/settings.py
@@ -201,6 +201,11 @@ class Settings(BaseModel):
default=None, validation_alias="POOLSIDE_API_KEY"
)
+ # ==================== LLM7.io (OpenAI-compatible) ====================
+ llm7_api_key: OptionalNonEmptyString = Field(
+ default=None, validation_alias="LLM7_API_KEY"
+ )
+
# ==================== Fireworks AI Config ====================
fireworks_api_key: OptionalNonEmptyString = Field(
default=None, validation_alias="FIREWORKS_API_KEY"
@@ -490,6 +495,9 @@ class Settings(BaseModel):
poolside_proxy: OptionalNonEmptyString = Field(
default=None, validation_alias="POOLSIDE_PROXY"
)
+ llm7_proxy: OptionalNonEmptyString = Field(
+ default=None, validation_alias="LLM7_PROXY"
+ )
fireworks_proxy: OptionalNonEmptyString = Field(
default=None, validation_alias="FIREWORKS_PROXY"
)
diff --git a/src/free_claude_code/providers/openai_chat/profiles.py b/src/free_claude_code/providers/openai_chat/profiles.py
index eaa8807e..3f4b5393 100644
--- a/src/free_claude_code/providers/openai_chat/profiles.py
+++ b/src/free_claude_code/providers/openai_chat/profiles.py
@@ -85,6 +85,7 @@ class OpenAIModelListing:
collection_field: str | None = "data"
id_field: str = "id"
aliases_field: str | None = None
+ additional_model_ids: tuple[str, ...] = ()
required_path_values: RequiredPathValues = ()
required_null_field: str | None = None
required_sequence_items: tuple[tuple[str, str], ...] = ()
@@ -623,6 +624,24 @@ OPENAI_CHAT_PROFILES: dict[str, OpenAIChatProfile] = {
),
ChatTemplateReasoning(field="enable_thinking"),
),
+ "llm7": OpenAIChatProfile(
+ _policy(
+ "LLM7",
+ ReasoningReplayMode.REASONING_CONTENT,
+ default_max_tokens=ANTHROPIC_DEFAULT_MAX_OUTPUT_TOKENS,
+ ),
+ NO_REASONING,
+ model_listing=OpenAIModelListing(
+ path="/models",
+ additional_model_ids=("default", "fast", "pro"),
+ required_path_values=(
+ (("model_type",), ("chat",)),
+ (("stream",), (True,)),
+ (("tools_calling",), (True,)),
+ ),
+ thinking_boolean_path=("reasoning",),
+ ),
+ ),
"ollama_cloud": OpenAIChatProfile(
_policy(
"OLLAMA_CLOUD",
diff --git a/src/free_claude_code/providers/openai_chat/provider.py b/src/free_claude_code/providers/openai_chat/provider.py
index 97b47467..5154bc94 100644
--- a/src/free_claude_code/providers/openai_chat/provider.py
+++ b/src/free_claude_code/providers/openai_chat/provider.py
@@ -57,6 +57,7 @@ from free_claude_code.providers.http import (
from free_claude_code.providers.model_listing import (
extract_openai_model_infos,
merge_model_list_pages,
+ model_infos_from_ids,
validate_model_list_page,
)
from free_claude_code.providers.stream_recovery import (
@@ -496,7 +497,7 @@ class OpenAIChatProvider(BaseProvider):
if not self._profile.model_ids_are_routable:
return frozenset()
listing = self._profile.model_listing
- return extract_openai_model_infos(
+ live_model_infos = extract_openai_model_infos(
payload,
provider_name=self._provider_name,
collection_field=listing.collection_field,
@@ -511,6 +512,12 @@ class OpenAIChatProvider(BaseProvider):
non_thinking_tag=listing.non_thinking_tag,
thinking_boolean_path=listing.thinking_boolean_path,
)
+ model_infos_by_id = {
+ model_info.model_id: model_info for model_info in live_model_infos
+ }
+ for model_info in model_infos_from_ids(listing.additional_model_ids):
+ model_infos_by_id.setdefault(model_info.model_id, model_info)
+ return frozenset(model_infos_by_id.values())
async def _list_models_payload(self) -> Any:
"""Fetch one OpenAI-compatible model-list payload with shared retries."""
diff --git a/tests/contracts/test_provider_catalog_order.py b/tests/contracts/test_provider_catalog_order.py
index 3f214576..c419f241 100644
--- a/tests/contracts/test_provider_catalog_order.py
+++ b/tests/contracts/test_provider_catalog_order.py
@@ -51,6 +51,7 @@ _EXPECTED_PROVIDER_ORDER: tuple[str, ...] = (
"tokenrouter",
"nararoute",
"poolside",
+ "llm7",
"ollama_cloud",
"lmstudio",
"llamacpp",
diff --git a/tests/contracts/test_smoke_config.py b/tests/contracts/test_smoke_config.py
index d18003d1..214c0f8f 100644
--- a/tests/contracts/test_smoke_config.py
+++ b/tests/contracts/test_smoke_config.py
@@ -68,6 +68,7 @@ def _settings(**overrides):
"cerebras_api_key": "",
"ollama_api_key": "",
"poolside_api_key": "",
+ "llm7_api_key": "",
"fireworks_api_key": "",
"novita_api_key": "",
"cloudflare_api_token": "",
@@ -182,6 +183,53 @@ def test_poolside_provider_configuration_uses_documented_default_model(
assert models[0].source == "provider_default"
+def test_llm7_provider_configuration_uses_stable_default_selector(
+ monkeypatch,
+) -> None:
+ monkeypatch.delenv("FCC_SMOKE_MODEL_LLM7", raising=False)
+ config = _smoke_config(
+ settings=_settings(
+ model="ollama/llama3.1",
+ ollama_base_url="",
+ llm7_api_key="llm7-key",
+ )
+ )
+
+ assert config.has_provider_configuration("llm7")
+ models = config.provider_smoke_models()
+ assert [model.provider for model in models] == ["llm7"]
+ assert models[0].full_model == "llm7/default"
+ assert models[0].source == "provider_default"
+
+
+def test_llm7_smoke_override_accepts_selector_with_or_without_prefix(
+ monkeypatch,
+) -> None:
+ settings = _settings(
+ model="ollama/llama3.1",
+ ollama_base_url="",
+ llm7_api_key="llm7-key",
+ )
+ for override in ("fast", "llm7/fast"):
+ monkeypatch.setenv("FCC_SMOKE_MODEL_LLM7", override)
+ models = _smoke_config(settings=settings).provider_smoke_models()
+
+ assert [model.provider for model in models] == ["llm7"]
+ assert models[0].full_model == "llm7/fast"
+ assert models[0].source == "FCC_SMOKE_MODEL_LLM7"
+
+
+def test_llm7_is_not_enabled_without_explicit_credential(monkeypatch) -> None:
+ monkeypatch.delenv("FCC_SMOKE_MODEL_LLM7", raising=False)
+ config = _smoke_config(
+ provider_matrix=frozenset({"llm7"}),
+ settings=_settings(ollama_base_url="", llm7_api_key=""),
+ )
+
+ assert not config.has_provider_configuration("llm7")
+ assert config.provider_smoke_models() == []
+
+
def test_xai_provider_smoke_uses_current_grok_model(monkeypatch) -> None:
monkeypatch.delenv("FCC_SMOKE_MODEL_XAI", raising=False)
config = _smoke_config(
diff --git a/tests/providers/test_llm7.py b/tests/providers/test_llm7.py
new file mode 100644
index 00000000..6ba3a3a7
--- /dev/null
+++ b/tests/providers/test_llm7.py
@@ -0,0 +1,286 @@
+"""Tests for the LLM7.io OpenAI-chat provider profile."""
+
+from unittest.mock import AsyncMock
+
+import httpx2
+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 LLM7_DEFAULT_BASE
+from free_claude_code.core.anthropic.models import MessagesRequest
+from free_claude_code.core.json_types import JsonObject, JsonValue
+from free_claude_code.core.reasoning import ReasoningPolicy
+from free_claude_code.providers.model_listing import ModelListResponseError
+from free_claude_code.providers.openai_chat import OpenAIChatProvider
+from tests.providers.support import (
+ REASONING_DEFAULT,
+ REASONING_OFF,
+ REASONING_ON,
+ immediate_admission,
+ make_provider_config,
+ profiled_provider,
+ reasoning_for,
+)
+
+_MODEL = "openai/gpt-oss-120b"
+_SELECTOR_IDS = frozenset({"default", "fast", "pro"})
+
+
+def llm7_provider() -> OpenAIChatProvider:
+ return profiled_provider(
+ "llm7",
+ make_provider_config(
+ api_key="test-llm7-key",
+ base_url=LLM7_DEFAULT_BASE,
+ rate_limit=10,
+ rate_window=60,
+ ),
+ admission=immediate_admission(provider_name="llm7", max_attempts=1),
+ )
+
+
+def _request(**overrides: JsonValue) -> MessagesRequest:
+ payload: JsonObject = {
+ "model": _MODEL,
+ "messages": [{"role": "user", "content": "Inspect the file."}],
+ "tools": [
+ {
+ "name": "read_file",
+ "description": "Read a file",
+ "input_schema": {
+ "type": "object",
+ "properties": {"path": {"type": "string"}},
+ "required": ["path"],
+ },
+ }
+ ],
+ }
+ payload.update(overrides)
+ return MessagesRequest.model_validate(payload)
+
+
+def _catalog_model(
+ model_id: str = _MODEL,
+ *,
+ model_type: object = "chat",
+ stream: object = True,
+ tools_calling: object = True,
+ reasoning: bool | None = None,
+) -> dict[str, object]:
+ model: dict[str, object] = {
+ "id": model_id,
+ "model_type": model_type,
+ "stream": stream,
+ "tools_calling": tools_calling,
+ }
+ if reasoning is not None:
+ model["reasoning"] = reasoning
+ return model
+
+
+def test_constructs_standard_openai_chat_provider(
+ llm7_provider: OpenAIChatProvider,
+) -> None:
+ assert isinstance(llm7_provider, OpenAIChatProvider)
+ assert llm7_provider._provider_name == "LLM7"
+ assert llm7_provider._api_key == "test-llm7-key"
+ assert llm7_provider._base_url == LLM7_DEFAULT_BASE
+
+
+ "reasoning",
+ [REASONING_DEFAULT, REASONING_ON, REASONING_OFF],
+)
+def test_preserves_provider_reasoning_default_and_standard_request_fields(
+ llm7_provider: OpenAIChatProvider,
+ reasoning: ReasoningPolicy,
+) -> None:
+ body = llm7_provider._build_request_body(_request(), reasoning=reasoning)
+
+ assert body["max_tokens"] == ANTHROPIC_DEFAULT_MAX_OUTPUT_TOKENS
+ assert body["model"] == _MODEL
+ assert body["tools"][0]["function"]["name"] == "read_file"
+ assert "reasoning" not in body
+ assert "reasoning_effort" not in body
+ assert "thinking" not in body
+ assert "extra_body" not in body
+
+
+def test_replays_reasoning_content_with_tool_history(
+ llm7_provider: OpenAIChatProvider,
+) -> None:
+ request = _request(
+ messages=[
+ {"role": "user", "content": "Inspect the file."},
+ {
+ "role": "assistant",
+ "content": [
+ {"type": "thinking", "thinking": "Read it first."},
+ {"type": "text", "text": "I will inspect it."},
+ {
+ "type": "tool_use",
+ "id": "toolu_1",
+ "name": "read_file",
+ "input": {"path": "example.py"},
+ },
+ ],
+ },
+ {
+ "role": "user",
+ "content": [
+ {
+ "type": "tool_result",
+ "tool_use_id": "toolu_1",
+ "content": "print('hello')",
+ }
+ ],
+ },
+ ]
+ )
+
+ body = llm7_provider._build_request_body(
+ request,
+ reasoning=reasoning_for(request),
+ )
+
+ assert body["messages"][1] == {
+ "role": "assistant",
+ "content": "I will inspect it.",
+ "reasoning_content": "Read it first.",
+ "tool_calls": [
+ {
+ "id": "toolu_1",
+ "type": "function",
+ "function": {
+ "name": "read_file",
+ "arguments": '{"path": "example.py"}',
+ },
+ }
+ ],
+ }
+ assert body["messages"][2] == {
+ "role": "tool",
+ "tool_call_id": "toolu_1",
+ "content": "print('hello')",
+ }
+
+
+async def test_filters_catalog_and_adds_live_authoritative_selectors(
+ llm7_provider: OpenAIChatProvider,
+) -> None:
+ llm7_provider._client.get = AsyncMock(
+ return_value={
+ "data": [
+ _catalog_model("reasoning-model", reasoning=True),
+ _catalog_model("plain-model", reasoning=False),
+ _catalog_model("unknown-reasoning-model"),
+ _catalog_model("default", reasoning=True),
+ _catalog_model("image-generator", model_type="image"),
+ _catalog_model("video-generator", model_type="video"),
+ _catalog_model("nonstreaming-chat", stream=False),
+ _catalog_model("chat-without-tools", tools_calling=False),
+ ]
+ }
+ )
+
+ model_infos = await llm7_provider.list_model_infos()
+
+ assert model_infos == frozenset(
+ {
+ ProviderModelInfo("reasoning-model", supports_thinking=True),
+ ProviderModelInfo("plain-model", supports_thinking=False),
+ ProviderModelInfo("unknown-reasoning-model"),
+ ProviderModelInfo("default", supports_thinking=True),
+ ProviderModelInfo("fast"),
+ ProviderModelInfo("pro"),
+ }
+ )
+ assert {info.model_id for info in model_infos} & _SELECTOR_IDS == _SELECTOR_IDS
+ assert sum(info.model_id == "default" for info in model_infos) == 1
+
+
+ ("field", "value"),
+ [
+ ("model_type", None),
+ ("model_type", 7),
+ ("stream", None),
+ ("stream", "true"),
+ ("tools_calling", None),
+ ("tools_calling", "true"),
+ ],
+)
+async def test_rejects_missing_or_wrongly_typed_required_catalog_metadata(
+ llm7_provider: OpenAIChatProvider,
+ field: str,
+ value: object,
+) -> None:
+ item = _catalog_model()
+ if value is None:
+ item.pop(field)
+ else:
+ item[field] = value
+ llm7_provider._client.get = AsyncMock(return_value={"data": [item]})
+
+ with pytest.raises(ModelListResponseError, match=f"include {field} as"):
+ await llm7_provider.list_model_infos()
+
+
+async def test_rejects_wrongly_typed_reasoning_metadata(
+ llm7_provider: OpenAIChatProvider,
+) -> None:
+ item = _catalog_model()
+ item["reasoning"] = "true"
+ llm7_provider._client.get = AsyncMock(return_value={"data": [item]})
+
+ with pytest.raises(ModelListResponseError, match="reasoning to be boolean"):
+ await llm7_provider.list_model_infos()
+
+
+async def test_selectors_do_not_mask_wholly_ineligible_catalog(
+ llm7_provider: OpenAIChatProvider,
+) -> None:
+ llm7_provider._client.get = AsyncMock(
+ return_value={"data": [_catalog_model(model_type="image")]}
+ )
+
+ with pytest.raises(ModelListResponseError, match="did not include any model ids"):
+ await llm7_provider.list_model_infos()
+
+
+async def test_model_catalog_uses_documented_url_and_bearer_auth(
+ llm7_provider: OpenAIChatProvider,
+) -> None:
+ requests: list[httpx2.Request] = []
+
+ def handler(request: httpx2.Request) -> httpx2.Response:
+ requests.append(request)
+ return httpx2.Response(200, json={"data": [_catalog_model()]})
+
+ await llm7_provider._client.close()
+ llm7_provider._client = AsyncOpenAI(
+ api_key="wire-llm7-key",
+ base_url=LLM7_DEFAULT_BASE,
+ max_retries=0,
+ http_client=httpx2.AsyncClient(transport=httpx2.MockTransport(handler)),
+ )
+ try:
+ model_infos = await llm7_provider.list_model_infos()
+ finally:
+ await llm7_provider.cleanup()
+
+ assert model_infos == frozenset(
+ {ProviderModelInfo(_MODEL)}
+ | {ProviderModelInfo(selector) for selector in _SELECTOR_IDS}
+ )
+ assert len(requests) == 1
+ assert str(requests[0].url) == "https://api.llm7.io/v1/models"
+ assert requests[0].headers["authorization"] == "Bearer wire-llm7-key"
diff --git a/tests/providers/test_provider_runtime.py b/tests/providers/test_provider_runtime.py
index 2062dd0e..86e39641 100644
--- a/tests/providers/test_provider_runtime.py
+++ b/tests/providers/test_provider_runtime.py
@@ -21,6 +21,7 @@ from free_claude_code.config.provider_catalog import (
GITHUB_MODELS_DEFAULT_BASE,
HUGGINGFACE_DEFAULT_BASE,
KIMI_CODE_DEFAULT_BASE,
+ LLM7_DEFAULT_BASE,
MINIMAX_DEFAULT_BASE,
NARAROUTE_DEFAULT_BASE,
NEBIUS_DEFAULT_BASE,
@@ -109,6 +110,7 @@ def _make_settings(**overrides):
mock.ollama_base_url = "http://localhost:11434"
mock.ollama_api_key = "test_ollama_cloud_key"
mock.poolside_api_key = "test_poolside_key"
+ mock.llm7_api_key = "test_llm7_key"
mock.nvidia_nim_proxy = None
mock.open_router_proxy = None
mock.lmstudio_proxy = None
@@ -155,6 +157,7 @@ def _make_settings(**overrides):
mock.cerebras_proxy = None
mock.ollama_cloud_proxy = None
mock.poolside_proxy = None
+ mock.llm7_proxy = None
mock.kilo_api_key = "test_kilo_key"
mock.kilo_proxy = None
mock.openai_proxy = None
@@ -260,6 +263,30 @@ def test_poolside_provider_config_uses_key_base_and_proxy() -> None:
assert isinstance(provider, OpenAIChatProvider)
+def test_llm7_provider_config_uses_key_base_and_proxy() -> None:
+ descriptor = PROVIDER_CATALOG["llm7"]
+ settings = _make_settings(
+ llm7_api_key="llm7-token",
+ llm7_proxy="http://proxy.test:8080",
+ )
+
+ config = build_provider_config(descriptor, settings)
+ with patch("free_claude_code.providers.openai_chat.provider.AsyncOpenAI"):
+ provider = create_provider("llm7", settings)
+
+ assert descriptor.display_name == "LLM7.io"
+ assert descriptor.credential_env == "LLM7_API_KEY"
+ assert descriptor.credential_attr == "llm7_api_key"
+ assert descriptor.credential_url == "https://dash.llm7.io/"
+ assert descriptor.default_base_url == LLM7_DEFAULT_BASE
+ assert descriptor.base_url_attr is None
+ assert descriptor.proxy_attr == "llm7_proxy"
+ assert config.api_key == "llm7-token"
+ assert config.base_url == LLM7_DEFAULT_BASE
+ assert config.proxy == "http://proxy.test:8080"
+ assert isinstance(provider, OpenAIChatProvider)
+
+
def test_xai_provider_config_uses_key_base_and_proxy() -> None:
descriptor = PROVIDER_CATALOG["xai"]
settings = _make_settings(
@@ -871,6 +898,7 @@ def test_create_provider_instantiates_each_builtin():
"wafer": OpenAIChatProvider,
"opencode_zen": OpenAIChatProvider,
"poolside": OpenAIChatProvider,
+ "llm7": OpenAIChatProvider,
"opencode_go": OpenAIChatProvider,
"vercel": OpenAIChatProvider,
"bedrock": OpenAIChatProvider,
diff --git a/uv.lock b/uv.lock
index d93cc6b7..24f4cb0b 100644
--- a/uv.lock
+++ b/uv.lock
@@ -607,7 +607,7 @@ wheels = [
[[package]]
name = "free-claude-code"
-version = "5.13.10"
+version = "5.14.0"
source = { editable = "." }
dependencies = [
{ name = "aiohttp" },