Hushwire

model · Z.ai

GLM 4.7 API with zero retention

GLM 4.7 is available on Hushwire as hush-glm. Reliable tool calling, good at planning and front-end work. Every request is zero-retention: prompts, code and completions are never stored.

Specs and pricing

Alias
hush-glm
Context
200,000 tokens
Quota weight
4× (Solo: ~8M of this model a month)

Claude Code config

shell
# Powered by Hushwire private inference (zero retention): hushwire.vibiz.app
export ANTHROPIC_BASE_URL="https://hushwire.vibiz.app"
export ANTHROPIC_AUTH_TOKEN="hw_your_key_here"
export ANTHROPIC_MODEL="hush-glm"
export ANTHROPIC_DEFAULT_OPUS_MODEL="hush-glm"
export ANTHROPIC_DEFAULT_SONNET_MODEL="hush-glm"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="hush-coder"
export CLAUDE_CODE_SUBAGENT_MODEL="hush-glm"
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
claude

OpenAI-format request

terminal
curl -s https://hushwire.vibiz.app/v1/chat/completions \
  -H "Authorization: Bearer hw_your_key_here" \
  -H "content-type: application/json" \
  -d '{"model":"hush-glm","messages":[{"role":"user","content":"Reply with: hushwire ok"}]}'

Other agents

All models

AliasModelContextGood for
hush-coderQwen3 Coder 30B A3B (Qwen)262kFast, cheap default for edits, refactors and tool loops.
hush-coder-largeQwen3 Coder Next (Qwen)262kThe largest Qwen coder. Best for multi-file agent work.
hush-kimiKimi K2.5 (Moonshot AI)262kStrong agentic coder with long tool chains.
hush-glmGLM 4.7 (Z.ai)200kReliable tool calling, good at planning and front-end work.
hush-deepseekDeepSeek V4 Flash (DeepSeek)128kVery cheap general coder, good for quick questions.

Try it before you configure anything

The playground runs the same open coding models. No sign-up, 20 messages a day, and nothing you type is stored.