feat(xai): update model YAMLs [bot] - #1972
Open
models-bot[bot] wants to merge 1 commit into
Open
Conversation
Contributor
|
/test-models |
Collaborator
Gateway test results
Failures (6)
ErrorCode snippetfrom openai import OpenAI
import json
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response_schema = json.loads('''{
"title": "CalendarEvent",
"type": "object",
"properties": {
"name": { "type": "string" },
"date": { "type": "string" },
"participants": {
"type": "array",
"items": { "type": "string" }
}
},
"required": ["name", "date", "participants"],
"additionalProperties": false
}''')
response = client.chat.completions.create(
model="test-v2-xai/grok-4.20-non-reasoning-latest",
messages=[
{"role": "system", "content": "Extract the event information as JSON."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday. Extract the event details as JSON."},
],
response_format={"type": "json_schema", "json_schema": {"name": "CalendarEvent", "schema": response_schema}},
stream=False,
)
import json as _json
_content = response.choices[0].message.content
print(_content)
if not _content:
raise Exception("VALIDATION FAILED: structured-output - response content is empty")
_parsed = _json.loads(_content)
if "name" not in _parsed or "date" not in _parsed or "participants" not in _parsed:
raise Exception("VALIDATION FAILED: structured-output - missing expected fields (name, date, participants)")
if not isinstance(_parsed.get("participants"), list):
raise Exception("VALIDATION FAILED: structured-output - 'participants' is not a list, schema not enforced")
if set(_parsed.keys()) != {"name", "date", "participants"}:
raise Exception(
f"VALIDATION FAILED: structured-output - unexpected keys present: {set(_parsed.keys())}"
)
print("VALIDATION: structured-output SUCCESS")
ErrorCode snippetfrom openai import OpenAI
import json
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response_schema = json.loads('''{
"title": "CalendarEvent",
"type": "object",
"properties": {
"name": { "type": "string" },
"date": { "type": "string" },
"participants": {
"type": "array",
"items": { "type": "string" }
}
},
"required": ["name", "date", "participants"],
"additionalProperties": false
}''')
response = client.chat.completions.create(
model="test-v2-xai/grok-4.20-non-reasoning-latest",
messages=[
{"role": "system", "content": "Extract the event information as JSON."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Alice and Bob are going to a science fair on Friday. Extract the event details as JSON."},
],
response_format={"type": "json_schema", "json_schema": {"name": "CalendarEvent", "schema": response_schema}},
stream=True,
)
import json as _json
_accumulated = ""
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
_accumulated += delta.content
print(delta.content, end="", flush=True)
if not _accumulated:
raise Exception("VALIDATION FAILED: structured-output stream - no content received")
_parsed = _json.loads(_accumulated)
if "name" not in _parsed or "date" not in _parsed or "participants" not in _parsed:
raise Exception("VALIDATION FAILED: structured-output stream - missing expected fields (name, date, participants)")
if not isinstance(_parsed.get("participants"), list):
raise Exception("VALIDATION FAILED: structured-output stream - 'participants' is not a list, schema not enforced")
if set(_parsed.keys()) != {"name", "date", "participants"}:
raise Exception(
f"VALIDATION FAILED: structured-output stream - unexpected keys present: {set(_parsed.keys())}"
)
print("\nVALIDATION: structured-output stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
"additionalProperties": False,
},
"strict": True,
},
},
]
response = client.chat.completions.create(
model="test-v2-xai/grok-4.20-non-reasoning-latest",
messages=[
{"role": "system", "content": "You are a helpful assistant with access to tools. You MUST strictly use the provided tools to answer. Never respond with plain text when a tool is available."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London. You must call the tool, do not respond with plain text."},
],
tools=tools,
tool_choice="auto",
stream=False,
)
_message = response.choices[0].message
if _message.tool_calls:
for _tc in _message.tool_calls:
print(f"Function: {_tc.function.name}")
print(f"Arguments: {_tc.function.arguments}")
else:
print(_message.content)
if not _message.tool_calls or len(_message.tool_calls) == 0:
raise Exception("VALIDATION FAILED: tool-call - no tool calls in response")
print("VALIDATION: tool-call SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-xai/grok-4.20-non-reasoning-latest",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "What is the capital of France?"},
],
max_tokens=256,
temperature=0.7,
stream=False,
)
print(response.choices[0].message.content)
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location.",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city name, e.g. London",
},
},
"required": ["location"],
"additionalProperties": False,
},
"strict": True,
},
},
]
response = client.chat.completions.create(
model="test-v2-xai/grok-4.20-non-reasoning-latest",
messages=[
{"role": "system", "content": "You are a helpful assistant with access to tools. You MUST strictly use the provided tools to answer. Never respond with plain text when a tool is available."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "Use the get_weather tool to check the weather in London. You must call the tool, do not respond with plain text."},
],
tools=tools,
tool_choice="auto",
stream=True,
)
_tool_calls_made = False
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
print(delta.content, end="", flush=True)
if delta.tool_calls:
_tool_calls_made = True
for _tc in delta.tool_calls:
if _tc.function:
print(_tc.function.arguments or "", end="", flush=True)
if not _tool_calls_made:
raise Exception("VALIDATION FAILED: tool-call stream - no tool calls received")
print("\nVALIDATION: tool-call stream SUCCESS")
ErrorCode snippetfrom openai import OpenAI
client = OpenAI(api_key="***", base_url="https://internal.devtest.truefoundry.tech/api/llm")
response = client.chat.completions.create(
model="test-v2-xai/grok-4.20-non-reasoning-latest",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hi"},
{"role": "assistant", "content": "Hi, how can I help you"},
{"role": "user", "content": "What is the capital of France?"},
],
max_tokens=256,
temperature=0.7,
stream=True,
)
for chunk in response:
if chunk.choices and len(chunk.choices) > 0:
delta = chunk.choices[0].delta
if delta.content is not None:
print(delta.content, end="", flush=True) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Auto-generated by poc-agent for provider
xai.Note
Low Risk
Metadata-only pricing and documentation link changes; no runtime or API behavior is modified, though incorrect costs could skew batch usage estimates.
Overview
Updates batch API pricing for
grok-4.20-non-reasoning-latest:input_cost_per_token_batchesrises from6.25e-7to0.000001, andoutput_cost_per_token_batchesfrom0.00000125to0.000002(in line with doubling batch rates relative to the prior values).Adds a
sourcesentry pointing at the official x.ai model documentation for this variant.Reviewed by Cursor Bugbot for commit 07a6ece. Bugbot is set up for automated code reviews on this repo. Configure here.