feat(deepinfra/anthropic/claude-fable-5): add new models [bot]#1707
feat(deepinfra/anthropic/claude-fable-5): add new models [bot]#1707models-bot[bot] wants to merge 2 commits into
Conversation
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
|
/test-models |
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 f1250fb. Configure here.
| - json_output | ||
| limits: | ||
| context_window: 1000000 | ||
| max_tokens: 1000000 |
There was a problem hiding this comment.
Wrong max_tokens output limit
Medium Severity
limits.max_tokens is set to 1000000, matching the context window instead of the model’s maximum generation size. Claude Fable 5 supports up to 128K output tokens; other DeepInfra Anthropic entries (e.g. claude-4-sonnet) set max_tokens and max_output_tokens to that output cap, not the full context.
Reviewed by Cursor Bugbot for commit f1250fb. Configure here.
Gateway test results
Failures (4)
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/anthropic-claude-fable-5",
messages=[
{"role": "user", "content": "How to calculate 3^3^3^3? Think step by step and show all reasoning."},
],
reasoning_effort="medium",
stream=True,
)
_reasoning_detected = 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 getattr(delta, "reasoning_content", None) is not None:
_reasoning_detected = True
if getattr(delta, "reasoning", None) is not None:
_reasoning_detected = True
_usage = getattr(chunk, "usage", None)
if _usage is not None:
_details = getattr(_usage, "completion_tokens_details", None)
if _details and getattr(_details, "reasoning_tokens", 0) > 0:
_reasoning_detected = True
if not _reasoning_detected:
raise Exception("VALIDATION FAILED: reasoning stream - no reasoning information in stream")
print("\nVALIDATION: reasoning 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/anthropic-claude-fable-5",
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")OutputTraceback (most recent call last): OutputTraceback (most recent call last): Successes (4)
Output
Output
Output
Output |
1 participant
Auto-generated by model-addition-agent for
deepinfra/anthropic/claude-fable-5.Note
Low Risk
Metadata-only model registration with no application or routing code changes.
Overview
Adds a new DeepInfra provider catalog file for
anthropic/claude-fable-5, exposing the model for chat routing with DeepInfra pricing ($0.00001 / $0.00005 per input/output token), function calling, JSON output, and thinking enabled.The entry marks the model active, supports text and image input, and documents a 1M context window and token limit per the DeepInfra source URL.
Reviewed by Cursor Bugbot for commit f1250fb. Bugbot is set up for automated code reviews on this repo. Configure here.