groq · verified update

Groq adds Qwen/Qwen3.8-27B to supported models

Groq has added the Qwen/Qwen3.8-27B model to its list of supported preview models, with a token speed of 450 tps, a context window of 131,042 tokens, and a maximum completion length of 16,384 tokens.

Official sourceCanary passedIndependent auditlow risk
Verified facts

What changed

  • Model ID: qwen/qwen3.8-27b
  • Token Speed: 450 tps
  • Input Price: $0.80 per 1M tokens
  • Output Price: $4.00 per 1M tokens
  • Context Window: 131,042 tokens
  • Max Completion Tokens: 16,384
  • Max File Size: 20 MB
  • Category: Preview Models
Conditions

What users must still check

  • Preview models are intended for evaluation purposes only and should not be used in production environments as they may be discontinued at short notice.
Affected action

What to do next

  • Model selection
  • Cost estimation
  • Context window planning
Independent audit

Why the evidence gate passed

The provided evidence supports the claim that Groq has added Qwen/Qwen3.8-27B to its list of supported models, with a token speed of 450 tps, a context window of 131,042 tokens, and a maximum completion length of 16,384 tokens. The pricing is set at $0.80 per million input tokens and $4.00 per million output tokens.

Independent agents and every deterministic evidence check passed.