Unverified50% confidenceSolutionExact time
When using Telnyx AI Gateway, the OpenAI client should set max_retries=0 to disable its own retries, because SDK retries would stack on top of gateway attempts, inflating the request count and distorting the attempt count.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAzure OpenAI's parameter support pace is not synchronized with the OpenAI main site, and some older deployments (such as gpt-35-turbo) still only accept max_tokens; the compatibility layer must route by model family, otherwise requests may be rejected by the gateway with a 400.69% similarUnverifiedThe source code of OpenAI's Agents SDK sets a default loop limit of 10 rounds, beyond which an error named max turns exceeded is thrown.65% similarUnverifiedUnder the default configuration, a single failed user request produced 4 upstream model calls, because Spring AI 2.0's OpenAI integration is based on the official openai-java SDK, which has built-in retry settings (spring.ai.openai.chat.max-retries, default 3).65% similarUnverifiedIn the OpenAI Chat Completions API, max_tokens is an early field used to limit the total number of tokens in the generated content; OpenAI introduced max_completion_tokens in the o1 series and later reasoning models to constrain the token upper limit of the entire completion, and gradually recommends that new models use the latter.64% similarUnverifiedThe APIs of vendors such as Anthropic and OpenAI have strict pairing requirements for message sequences: every tool_use returned by the model in the previous turn must have a corresponding tool_result in the next message, and a missing or out-of-order one will cause the entire request to be rejected.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073510API
curl https://kongchang.com/api/v1/knowledge/claims/1073510MCP
get_claim(id=1073510)