Original Summary

钉住官渠，刚刚使用的时候频繁报429 Failed to create stream: inference request failed: failed to generate stream from Vercel: failed to invoke model ‘deepseek/deepseek-v4.1-flash’ with streaming: request failed with status 429: {“error”:{“message”:“Rate limit exceeded for deepseek/deepseek-v4.1-flash: this team’s limit of 100000000 input tokens per minute (per region) was reached. Retry after 3s.”,“type”:“rate_limit_exceeded”,“param”:{“error”:“Rate limit exceeded for deepseek/deepseek-v4.1-flash: this team’s limit of 100000000 input tokens per minute (per region) was reached. Retry after 3s.”,“type”:“rate_limit_exceeded”,“statusCode”:429,“name”:“RateLimitExceededError”,“message”:“Rate limit exceeded for deepseek/deepseek-v4.1-flash: this team’s limit of 100000000 input tokens per minute (per region) was reached. Retry after 3s.”}},“providerMetadata”:{“gateway”:{“routing”:{“originalModelId”:“deepseek/deepseek-v4.1-flash”,“resolvedProvider”:“deepseek”,“fallbacksAvailable”:[“fireworks”,“alibaba”,“runware”,“relace”,“particle”,“novita”,“togetherai”,“deepinfra”,“wafer”,“parasail”,“gmicloud”,“modal”,“morph”,“deepseek”,“runinfra”,“boundless”],“canonicalSlug”:“deepseek/deepseek-v4.1-flash”,“modelAttemptCount”:1,“modelAttempts”:[{“canonicalSlug”:“deepseek/deepseek-v4.1-flash”,“success”:false,“providerAttemptCount”:0,“providerAttempts”: }],“totalProviderAttemptCount”:0,“affinity”:{“outcome”:“promoted”,“pinnedProvider”:“deepseek”,“displacedProvider”:“baseten”},“clientSessionId”:“sess- ",“clientSessionIdSource”:“explicit”},“generationId”:"gen_ ”}}} 7 个帖子 - 4 位参与者 阅读完整话题

  • 情报分类：商业与市场研究
  • 分类依据：内容涉及商业、投资或市场动态
  • 信息来源：服务器 / LINUX DO - 最新话题
  • 发布时间：2026/10/2 18:13:12