Loading

GLM 5.3 Flash Red

Reduced refusalsAvailable

Z.ai's fast, low-cost GLM 5.3 Flash, modified to reduce refusals. Suited to high-volume chat, drafting, and agent steps where speed and price matter most.

Input
$0.25
Cached input
$0.10
Output
$1.00

per 1M tokens

Context
1M
Max output
8.2K
Tool callingJSON outputOpenAI Chat CompletionsOpenAI ResponsesAnthropic Messages

Quickstart

Base URL
Model ID
curl 'https://redrouter.org/v1/chat/completions' \
  -H "Authorization: Bearer $REDROUTER_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"messages":[{"content":"Hello","role":"user"}],"model":"glm-5.3-flash-red"}'

Set REDROUTER_API_KEY to a key from API Keys.

Supported parameters

modelmessagesstreamstream_optionsmax_tokensmax_completion_tokenstemperaturetop_pstoppresence_penaltyfrequency_penaltyseedtoolstool_choiceparallel_tool_callsresponse_formatuserreasoning_effortreasoningenable_thinkingthinkingthinking_budgetchat_template_kwargsoutput_config

Other parameters return HTTP 400; user is accepted but not forwarded. Request fields and limits.

Setup notes and limits: GLM 5.3 Flash Red on the RedRouter blog.