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

Update GLM 5.2 model references

Ali Khokhar15cab79a43b6
diff --git a/README.md b/README.md
index a5e577e9..895ad63f 100644
--- a/README.md
+++ b/README.md
@@ -378,13 +378,13 @@ This provider calls Cloudflare's account-scoped **OpenAI-compatible** Chat Compl
Get an API key at [Z.ai/manage-apikey/apikey-list](https://z.ai/manage-apikey/apikey-list).
-In the Admin UI, paste it into `ZAI_API_KEY`, then set `MODEL` to a Z.ai model slug such as `zai/glm-5.1`.
+In the Admin UI, paste it into `ZAI_API_KEY`, then set `MODEL` to a Z.ai model slug such as `zai/glm-5.2`.
This provider calls Z.ai's **Anthropic-compatible** Messages API (`https://api.z.ai/api/anthropic/v1/messages`). The former OpenAI Coding Plan base (`https://api.z.ai/api/coding/paas/v4`) is **not** used by this gateway.
Popular examples:
-- `zai/glm-5.1`
+- `zai/glm-5.2`
- `zai/glm-5-turbo`
Browse models at [Z.ai](https://z.ai).
@@ -420,7 +420,7 @@ In the Admin UI, keep or update `OLLAMA_BASE_URL`, then set `MODEL` to the same
Each model tier can use a different provider by setting `MODEL_OPUS`, `MODEL_SONNET`, and `MODEL_HAIKU` in the Admin UI. Leave a tier blank to inherit `MODEL`. These tier overrides apply to Claude model names that contain `opus`, `sonnet`, or `haiku`. Codex uses the Admin `MODEL` default through `fcc-codex` unless a session requests a provider-prefixed slug directly.
-For example, you can route Opus to `nvidia_nim/moonshotai/kimi-k2.6`, Sonnet to `open_router/openrouter/free`, Haiku to `lmstudio/qwen3.5-coder`, and keep the fallback `MODEL` on `zai/glm-5.1`.
+For example, you can route Opus to `nvidia_nim/moonshotai/kimi-k2.6`, Sonnet to `open_router/openrouter/free`, Haiku to `lmstudio/qwen3.5-coder`, and keep the fallback `MODEL` on `zai/glm-5.2`.
<a id="connect-your-client"></a>
diff --git a/pyproject.toml b/pyproject.toml
index 2dd35785..3f78835a 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
[project]
name = "free-claude-code"
-version = "3.3.0"
+version = "3.3.1"
description = "Middleware between Claude Code CLI (Anthropic API) and NVIDIA NIM"
readme = "README.md"
requires-python = ">=3.14.0"
diff --git a/smoke/README.md b/smoke/README.md
index 58c6ab21..bcb28094 100644
--- a/smoke/README.md
+++ b/smoke/README.md
@@ -102,7 +102,7 @@ uv run pytest smoke/product -n 0 -s --tb=short
```powershell
$env:FCC_LIVE_SMOKE = "1"
$env:FCC_SMOKE_TARGETS = "nvidia_nim_cli"
-$env:FCC_SMOKE_NIM_MODELS = "z-ai/glm-5.1,moonshotai/kimi-k2.6,minimaxai/minimax-m2.7,nvidia/nemotron-3-super-120b-a12b,deepseek-ai/deepseek-v4-pro,deepseek-ai/deepseek-v4-flash"
+$env:FCC_SMOKE_NIM_MODELS = "z-ai/glm-5.2,moonshotai/kimi-k2.6,minimaxai/minimax-m2.7,nvidia/nemotron-3-super-120b-a12b,deepseek-ai/deepseek-v4-pro,deepseek-ai/deepseek-v4-flash"
uv run pytest smoke/product -n 0 -s --tb=short
```
diff --git a/smoke/lib/config.py b/smoke/lib/config.py
index b68e4144..c44d32a9 100644
--- a/smoke/lib/config.py
+++ b/smoke/lib/config.py
@@ -57,7 +57,7 @@ PROVIDER_SMOKE_DEFAULT_MODELS: dict[str, str] = {
"huggingface": "huggingface/openai/gpt-oss-120b:fastest",
"cohere": "cohere/command-a-plus-05-2026",
"github_models": "github_models/openai/gpt-4.1",
- "zai": "zai/glm-5.1",
+ "zai": "zai/glm-5.2",
"gemini": "gemini/models/gemini-3.1-flash-lite",
"groq": "groq/llama-3.3-70b-versatile",
"sambanova": "sambanova/Meta-Llama-3.3-70B-Instruct",
@@ -66,7 +66,7 @@ PROVIDER_SMOKE_DEFAULT_MODELS: dict[str, str] = {
}
NVIDIA_NIM_CLI_DEFAULT_MODELS: tuple[str, ...] = (
- "z-ai/glm-5.1",
+ "z-ai/glm-5.2",
"moonshotai/kimi-k2.6",
"minimaxai/minimax-m2.7",
"nvidia/nemotron-3-super-120b-a12b",
diff --git a/tests/api/test_admin.py b/tests/api/test_admin.py
index 0938aa43..1c064c25 100644
--- a/tests/api/test_admin.py
+++ b/tests/api/test_admin.py
@@ -463,7 +463,7 @@ def test_admin_apply_omits_stale_zai_base_url(monkeypatch, tmp_path):
env_file.write_text(
"\n".join(
[
- "MODEL=zai/glm-5.1",
+ "MODEL=zai/glm-5.2",
"ZAI_API_KEY=zai-secret",
"ZAI_BASE_URL=https://custom.zai.invalid/v1",
"",
@@ -475,7 +475,7 @@ def test_admin_apply_omits_stale_zai_base_url(monkeypatch, tmp_path):
response = _local_client(app).post(
"/admin/api/config/apply",
- json={"values": {"MODEL": "zai/glm-5.1"}},
+ json={"values": {"MODEL": "zai/glm-5.2"}},
)
assert response.status_code == 200
diff --git a/tests/contracts/test_nvidia_nim_cli_matrix.py b/tests/contracts/test_nvidia_nim_cli_matrix.py
index 6b0fbc81..d17658d1 100644
--- a/tests/contracts/test_nvidia_nim_cli_matrix.py
+++ b/tests/contracts/test_nvidia_nim_cli_matrix.py
@@ -45,8 +45,8 @@ def test_nvidia_nim_cli_matrix_report_shape_and_redaction(
duration_s=1.25,
)
outcome = make_outcome(
- model="z-ai/glm-5.1",
- full_model="nvidia_nim/z-ai/glm-5.1",
+ model="z-ai/glm-5.2",
+ full_model="nvidia_nim/z-ai/glm-5.2",
source="nvidia_nim_cli_default",
feature="basic_text",
marker="FCC_NIM_BASIC",
@@ -65,7 +65,7 @@ def test_nvidia_nim_cli_matrix_report_shape_and_redaction(
assert path.name.startswith("nvidia-nim-cli-matrix-test-worker-")
assert payload["target"] == "nvidia_nim_cli"
- assert payload["models"] == ["nvidia_nim/z-ai/glm-5.1"]
+ assert payload["models"] == ["nvidia_nim/z-ai/glm-5.2"]
saved = payload["outcomes"][0]
assert saved["feature"] == "basic_text"
assert saved["classification"] == "passed"
@@ -114,8 +114,8 @@ def test_cli_matrix_normalizes_missing_captured_output(
tools="",
)
outcome = make_outcome(
- model="z-ai/glm-5.1",
- full_model="nvidia_nim/z-ai/glm-5.1",
+ model="z-ai/glm-5.2",
+ full_model="nvidia_nim/z-ai/glm-5.2",
source="nvidia_nim_cli_default",
feature="basic_text",
marker="FCC_NIM_BASIC",
@@ -183,8 +183,8 @@ def test_nvidia_nim_cli_matrix_regression_detection(tmp_path: Path) -> None:
duration_s=0.1,
)
outcome = make_outcome(
- model="z-ai/glm-5.1",
- full_model="nvidia_nim/z-ai/glm-5.1",
+ model="z-ai/glm-5.2",
+ full_model="nvidia_nim/z-ai/glm-5.2",
source="nvidia_nim_cli_default",
feature="basic_text",
marker="FCC_NIM_BASIC",
@@ -195,7 +195,7 @@ def test_nvidia_nim_cli_matrix_regression_detection(tmp_path: Path) -> None:
assert outcome.classification == "product_failure"
assert regression_failures([outcome]) == [
- "nvidia_nim/z-ai/glm-5.1 basic_text: product_failure"
+ "nvidia_nim/z-ai/glm-5.2 basic_text: product_failure"
]
@@ -210,8 +210,8 @@ def test_nvidia_nim_cli_matrix_model_feature_failures_do_not_regress(
duration_s=0.1,
)
outcome = make_outcome(
- model="z-ai/glm-5.1",
- full_model="nvidia_nim/z-ai/glm-5.1",
+ model="z-ai/glm-5.2",
+ full_model="nvidia_nim/z-ai/glm-5.2",
source="nvidia_nim_cli_default",
feature="tool_use_roundtrip",
marker="FCC_NIM_TOOL",
@@ -236,13 +236,13 @@ def test_nvidia_nim_cli_raw_payload_log_counts_as_proxy_request(
duration_s=0.1,
)
outcome = make_outcome(
- model="z-ai/glm-5.1",
- full_model="nvidia_nim/z-ai/glm-5.1",
+ model="z-ai/glm-5.2",
+ full_model="nvidia_nim/z-ai/glm-5.2",
source="nvidia_nim_cli_default",
feature="subagent_task",
marker="FCC_NIM_TASK",
run=run,
- log_delta="API_REQUEST: request_id=req_1 model=z-ai/glm-5.1 messages=2",
+ log_delta="API_REQUEST: request_id=req_1 model=z-ai/glm-5.2 messages=2",
log_path=tmp_path / "server.log",
requires_task=True,
)
@@ -428,13 +428,13 @@ def test_nvidia_nim_cli_timeout_is_not_model_missing(
timed_out=True,
)
outcome = make_outcome(
- model="z-ai/glm-5.1",
- full_model="nvidia_nim/z-ai/glm-5.1",
+ model="z-ai/glm-5.2",
+ full_model="nvidia_nim/z-ai/glm-5.2",
source="nvidia_nim_cli_default",
feature="tool_use_roundtrip",
marker="FCC_NIM_TOOL",
run=run,
- log_delta="API_REQUEST: request_id=req_1 model=z-ai/glm-5.1 messages=2",
+ log_delta="API_REQUEST: request_id=req_1 model=z-ai/glm-5.2 messages=2",
log_path=tmp_path / "server.log",
)
@@ -452,14 +452,14 @@ def test_nvidia_nim_cli_success_beats_verbose_timeout_words(tmp_path: Path) -> N
duration_s=0.1,
)
outcome = make_outcome(
- model="z-ai/glm-5.1",
- full_model="nvidia_nim/z-ai/glm-5.1",
+ model="z-ai/glm-5.2",
+ full_model="nvidia_nim/z-ai/glm-5.2",
source="nvidia_nim_cli_default",
feature="thinking",
marker="FCC_NIM_THINK",
run=run,
log_delta=(
- "API_REQUEST: request_id=req_1 model=z-ai/glm-5.1 messages=1 "
+ "API_REQUEST: request_id=req_1 model=z-ai/glm-5.2 messages=1 "
"read_timeout_s=300"
),
log_path=tmp_path / "server.log",
diff --git a/tests/contracts/test_smoke_config.py b/tests/contracts/test_smoke_config.py
index 80137c8c..9d21ce2c 100644
--- a/tests/contracts/test_smoke_config.py
+++ b/tests/contracts/test_smoke_config.py
@@ -420,17 +420,17 @@ def test_nvidia_nim_cli_default_models_are_normalized() -> None:
def test_nvidia_nim_cli_models_override_and_append() -> None:
refs = nvidia_nim_cli_model_refs(
{
- "FCC_SMOKE_NIM_MODELS": "z-ai/glm-5.1,nvidia_nim/custom/model",
- "FCC_SMOKE_NIM_EXTRA_MODELS": "moonshotai/kimi-k2.6,z-ai/glm-5.1",
+ "FCC_SMOKE_NIM_MODELS": "z-ai/glm-5.2,nvidia_nim/custom/model",
+ "FCC_SMOKE_NIM_EXTRA_MODELS": "moonshotai/kimi-k2.6,z-ai/glm-5.2",
}
)
assert tuple(refs) == (
- "nvidia_nim/z-ai/glm-5.1",
+ "nvidia_nim/z-ai/glm-5.2",
"nvidia_nim/custom/model",
"nvidia_nim/moonshotai/kimi-k2.6",
)
- assert refs["nvidia_nim/z-ai/glm-5.1"] == "FCC_SMOKE_NIM_MODELS"
+ assert refs["nvidia_nim/z-ai/glm-5.2"] == "FCC_SMOKE_NIM_MODELS"
assert refs["nvidia_nim/moonshotai/kimi-k2.6"] == ("FCC_SMOKE_NIM_EXTRA_MODELS")
@@ -457,7 +457,7 @@ def test_smoke_config_returns_nvidia_nim_cli_provider_models(monkeypatch) -> Non
monkeypatch.delenv("FCC_SMOKE_NIM_EXTRA_MODELS", raising=False)
config = _smoke_config(
settings=_settings(
- model="nvidia_nim/z-ai/glm-5.1",
+ model="nvidia_nim/z-ai/glm-5.2",
nvidia_nim_api_key="nim-key",
ollama_base_url="",
)
@@ -466,7 +466,7 @@ def test_smoke_config_returns_nvidia_nim_cli_provider_models(monkeypatch) -> Non
models = config.nvidia_nim_cli_models()
assert models[0].provider == "nvidia_nim"
- assert models[0].full_model == "nvidia_nim/z-ai/glm-5.1"
+ assert models[0].full_model == "nvidia_nim/z-ai/glm-5.2"
assert models[0].source == "nvidia_nim_cli_default"
diff --git a/tests/providers/test_zai.py b/tests/providers/test_zai.py
index d0502d29..30ffaca7 100644
--- a/tests/providers/test_zai.py
+++ b/tests/providers/test_zai.py
@@ -69,12 +69,12 @@ def test_model_list_headers(zai_provider):
def test_build_request_body_native(zai_provider):
request = MessagesRequest(
- model="glm-5.1",
+ model="glm-5.2",
max_tokens=100,
messages=[Message(role="user", content="Hello")],
)
body = zai_provider._build_request_body(request)
- assert body["model"] == "glm-5.1"
+ assert body["model"] == "glm-5.2"
assert body["stream"] is True
assert body["max_tokens"] == 100
diff --git a/uv.lock b/uv.lock
index 3ac661e6..d9c43b78 100644
--- a/uv.lock
+++ b/uv.lock
@@ -561,7 +561,7 @@ wheels = [
[[package]]
name = "free-claude-code"
-version = "3.3.0"
+version = "3.3.1"
source = { editable = "." }
dependencies = [
{ name = "aiohttp" },