feat(deepinfra): update model YAMLs [bot]#1736
Conversation
|
/test-models |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 8f791dc. Configure here.
| - input_cost_per_token: 2e-8 | ||
| output_cost_per_token: 5e-8 | ||
| region: "*" | ||
| deprecationDate: "2026-07-16" |
There was a problem hiding this comment.
Deprecation date without isDeprecated
Medium Severity
deprecationDate was added for these models, but isDeprecated: true was not. Other DeepInfra models with a deprecation date set the flag too, so downstream logic that keys off isDeprecated may not treat these as deprecated.
Additional Locations (1)
Reviewed by Cursor Bugbot for commit 8f791dc. Configure here.
Gateway test results
Failures (2)
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-deepinfra/ByteDance-Seed-2.0-code",
messages=[
{"role": "user", "content": "List 3 colors with their hex codes in JSON."},
],
response_format={"type": "json_object"},
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: json-output stream - no content received")
_json.loads(_accumulated)
print("\nVALIDATION: json-output 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-deepinfra/ByteDance-Seed-2.0-code",
messages=[
{"role": "user", "content": "List 3 colors with their hex codes in JSON."},
],
response_format={"type": "json_object"},
stream=False,
)
import json as _json
_content = response.choices[0].message.content
print(_content)
if not _content:
raise Exception("VALIDATION FAILED: json-output - response content is empty")
_json.loads(_content)
print("VALIDATION: json-output SUCCESS")Successes (16)
Output
Output
Output
Output
Output
Output
Output
Output
Output
Output
Output
Output
Output
Output
Output
OutputSkipped (2)
Skip reason
Skip reason |
1 participant
Auto-generated by poc-agent for provider
deepinfra.Note
Low Risk
Metadata-only provider catalog changes with no code or pricing logic updates.
Overview
Updates three DeepInfra model YAMLs to match current provider metadata.
ByteDance/Seed-2.0-codenow listsjson_outputunderfeatures, reflecting that structured JSON responses are supported (the file still has a stale comment saying json output is not supported).meta-llama/Meta-Llama-3.1-8B-Instructandnvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoningeach gaindeprecationDate: "2026-07-16", signaling planned sunset without changing costs, limits, orstatusin this diff.Reviewed by Cursor Bugbot for commit 8f791dc. Bugbot is set up for automated code reviews on this repo. Configure here.