Verified 2026-11-18 · rates follow the live catalog
6 GLM models are in the catalog, from GLM-4.7-Flash at $0.0016 for one request to GLM-5.3 at $0.032, a 20.3× spread inside one family. Prices are what each model bills at its most expensive hour of the day. One request is a 20,000-token prompt with a 1,000-token reply and nothing cached, an illustration and not a measurement of your traffic.
| Model | Context | Input / 1M | Output / 1M | Cached input / 1M | One request (20,000 in, 1,000 out) | 1,000 requests |
|---|---|---|---|---|---|---|
GLM-4.7-Flash | 128K | $0.06 | $0.40 | — | $0.0016 | $1.60 |
GLM-5.3-Flash | 1.0M | $0.15 | $0.50 | $0.03 | $0.0035 | $3.50 |
GLM-5.3-Flash-Uncensored | 1.0M | $0.25 | $0.75 | $0.10 | $0.0057 | $5.75 |
GLM-5.1 | 256K | $1.40 | $4.40 | $0.26 | $0.032 | $32.40 |
GLM-5.2 | 256K | $1.40 | $4.40 | $0.26 | $0.032 | $32.40 |
GLM-5.3 | 1.0M | $1.40 | $4.40 | $0.26 | $0.032 | $32.40 |
GLM-5.1, GLM-5.2 and GLM-5.3 bill the same: $1.40 in and $4.40 out per million tokens. They differ in context window (GLM-5.1 256K, GLM-5.2 256K, GLM-5.3 1.0M) and reasoning tiers (GLM-5.1: none; GLM-5.2: max, high; GLM-5.3: low, high, max), so the price does not decide between them.| Model | Image input | Video input | Tool calling | Reasoning tiers | Serving precision |
|---|---|---|---|---|---|
GLM-4.7-Flash | No | No | Yes | — | FP8 |
GLM-5.3-Flash | Yes | Yes | Yes | low, high, max | FP8 |
GLM-5.3-Flash-Uncensored | No | No | Yes | low, high, max | — |
GLM-5.1 | No | No | Yes | — | BF16 |
GLM-5.2 | No | No | Yes | max, high | FP8 |
GLM-5.3 | No | No | Yes | low, high, max | FP8 |
These models publish a discount against their list price:
GLM-5.3-Flash: 10% off during 14:00–24:00 UTC, which brings one request to $0.0032 during the cheapest hours.GLM-5.1: 10% off during 14:00–24:00 UTC, which brings one request to $0.029 during the cheapest hours.GLM-5.2: 10% off during 14:00–24:00 UTC, which brings one request to $0.029 during the cheapest hours.GLM-5.3: 10% off during 14:00–24:00 UTC, which brings one request to $0.029 during the cheapest hours.Each model's page shows its list price, its rates and its schedule.
Free to call, with the last free day shown (UTC, inclusive): GLM-5.3-Flash-Free through 4 December 2026. Free models never draw down a plan allowance or credits, work on an account with no credits, and answer only streaming requests. After its last free day a model is no longer served. The free AI API page covers how free models behave at their limits.
Create an account, make a key in the dashboard and send it as a bearer token. Between model families, only the model field changes.
curl https://api.openference.com/v1/chat/completions \
-H "Authorization: Bearer $OPENFERENCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "GLM-5.3-Flash-Uncensored",
"messages": [{"role": "user", "content": "Say hello"}]}'
Send GLM-5.3-Flash-Uncensored exactly as written. OpenAI-format clients use https://api.openference.com/v1; Claude Code and other Anthropic-format clients use https://api.openference.com. The OpenAI-compatible API guide covers every endpoint.
Using GLM from Claude Code or Codex CLI? The GLM coding plan alternative page has the exact configuration for both and explains how plan allowances reset.
See also the cheap AI API guide, the model catalog and pricing.
Across the 6 billed GLM models, input runs $0.06 to $1.40 and output $0.40 to $4.40 per million tokens at the most expensive hour of the day. GLM-4.7-Flash is the least expensive per request.
https://api.openference.com/v1 for OpenAI-format clients and https://api.openference.com for Anthropic-format clients.
Some do: GLM-5.3-Flash accepts image input, and the other 5 are text-only.
Yes, for now: GLM-5.3-Flash-Free. Free models are a limited-time offer and answer only streaming requests.
Model catalog · Pricing · Comparisons · Cost guides · Integration guides · FAQ
Guides: GLM coding plan alternative · Free AI API · LLM gateway · LLM proxy · Cheap AI API · OpenAI-compatible API
Model APIs: GLM API · DeepSeek API · Kimi API · Qwen API · MiniMax API