Skip to content
NEWKimi K3 is live — Moonshot flagship, 1M context, cache hits from $0.30/MView pricing
HopBase
← Back to blog

GLM 5.3 API Now Available: 1M Context, Thinking-Length Control, ~15% Off | HopBase

HopBase Aug 14, 2026 4 min read
GLM 5.3 API Now Available: 1M Context, Thinking-Length Control, ~15% Off | HopBase

Zhipu's newest flagship model GLM 5.3 is now live on HopBase, served through the Tencent official channel. Sign up and you can enable it self-serve.

Model specs

  • 1M context window: fit roughly a million tokens of input in a single request — whole repos, long documents, extended multi-turn sessions.
  • Deep reasoning with thinking-length control: tune reasoning depth to task complexity and trade latency against quality on your terms.
  • OpenAI-compatible protocol: standard /v1/chat/completions; existing OpenAI SDKs and clients switch over with zero code changes.

Pricing: aligned with the official list, limited-time ~15% off

ItemOfficial direct-pay refHopBase limited-time
Input (per million tokens)$1.40$1.19
Output (per million tokens)$4.40$3.74
Cached input read (per million tokens)$0.26$0.22

Billing is channel-discounted unit price × actual usage, visible in the console in real time. Full details on the pricing page.

Three-minute quickstart

curl https://api.hop-base.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3",
    "messages": [{"role": "user", "content": "Hello, introduce yourself"}]
  }'

Full setup guides for Claude Code / CC Switch, Codex CLI, and the OpenAI SDK are in the GLM-5.3 docs. If you already have a key, just switch the model name to glm-5.3.

Product