Z.ai · October 2026
GLM API pricing, every model
16 GLM models, from $0.046 to $2.80 per million input tokens. GLM models from Z.ai, a cheap option for coding agents.
Prices from OpenRouter’s models API, updated October 29, 2026
GLM 5.3 Flash
$0.046 in · $0.074 outAbout $2.95 a month for a 1,000-chats-a-day support bot.
GLM 5.3 Prime
$2.80 in · $8.80 outReleased 2026-09-23, 1M tokens of context.
GLM 4.6V
−83%Cached input costs $0.05 instead of $0.30 per 1M tokens.
All GLM models and prices
| Model | Released | Input /1M | Output /1M | Cache read /1M | Batch in / out | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|---|
| GLM 5.3 Prime | 2026-09-23 | $2.80 | $8.80 | $0.56 | – | 1M | $232 |
| GLM 5.3 FlashX | 2026-09-18 | $0.37 | $1.25 | $0.09 | – | 1.05M | $31.65 |
| GLM 5.3 Flash | 2026-08-26 | $0.046 | $0.074 | $0.03 | $0.05 / $0.18 | 1.05M | $2.95 |
| GLM 5.3 | 2026-08-18 | $0.07 | $1.40 | $0.069 | $0.45 / $2 | 1.05M | $19.95 |
| GLM 5.2 | 2026-06-16 | $0.006 | $7 | $0.005 | – | 1.05M | $84.27 |
| GLM 5.1 | 2026-04-07 | $1.40 | $4.40 | $0.26 | – | 205K | $116 |
| GLM 5V Turbo | 2026-04-01 | $1.20 | $4 | $0.24 | – | 203K | $102 |
| GLM 5 Turbo | 2026-03-15 | $1.20 | $4 | $0.24 | – | 203K | $102 |
| GLM 5 | 2026-02-11 | $1 | $3.20 | $0.20 | – | 205K | $83.40 |
| GLM 4.7 Flash | 2026-01-19 | $0.06 | $0.40 | – | – | 200K | $7.52 |
| GLM 4.7 | 2025-12-22 | $0.54 | $1.98 | $0.099 | – | 205K | $48.06 |
| GLM 4.6V | 2025-12-08 | $0.30 | $0.90 | $0.05 | – | 131K | $24.30 |
| GLM 4.6 | 2025-09-30 | $0.50 | $2 | $0.10 | – | 205K | $46.50 |
| GLM 4.5V | 2025-08-11 | $0.60 | $1.80 | $0.11 | – | 66K | $48.60 |
| GLM 4.5 | 2025-07-25 | $0.60 | $2.20 | $0.11 | – | 131K | $53.40 |
| GLM 4.5 Air | 2025-07-25 | $0.13 | $0.85 | $0.025 | – | 131K | $16.05 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
What three real workloads cost a month
| Model | Support chatbot | Daily summaries | Coding agent |
|---|---|---|---|
| GLM 5.3 Flash | $2.95 | $47.81 | $25.64 |
| GLM 4.7 Flash | $7.52 | $90.45 | $53.16 |
| GLM 4.5 Air | $16.05 | $193 | $53.52 |
| GLM 5.3 | $19.95 | $189 | $83.35 |
| GLM 4.6V | $24.30 | $351 | $93.60 |
| GLM 5.3 FlashX | $31.65 | $446 | $135 |
| GLM 4.6 | $46.50 | $630 | $178 |
| GLM 4.5V | $48.60 | $702 | $193 |
Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out · Daily summaries: 10,000 a day, 3,000 tokens in, 300 out · Coding agent: 400 calls a day, 60,000 tokens in (80% cached), 2,000 out. Cached share billed at the cache-read price where the model has one.
Compare with other providers
GLM pricing questions
How much does the GLM API cost?
Z.ai’s models range from $0.046 per 1M input tokens and $0.074 per 1M output tokens (GLM 5.3 Flash) to $2.80 and $8.80 (GLM 5.3 Prime). The newest, GLM 5.3 Prime, costs $2.80 in and $8.80 out.
Which GLM model is the cheapest?
GLM 5.3 Flash, at $0.046 per 1M input tokens. A support chatbot doing 1,000 chats a day would cost about $2.95 a month on it.
Does Z.ai discount cached prompts?
Yes. On GLM 4.6V, cached input costs $0.05 per 1M tokens instead of $0.30, 83% less. Long, repeated system prompts and agent loops benefit most.
Is there a batch discount?
2 GLM models have a batch price, typically half the normal rate, for jobs that can wait (up to 24 hours). See the Batch column below.
How do I track my GLM spend per product?
Route it through OpenRouter with one API key per product and connect OpenRouter to Glow: you get spend by model, API key and product every day, with cache hit rate. Track AI spend.
See your real GLM bill.
Glow shows what you actually spend by model, API key and product, every day, and which cheaper model would do the same job.
- Read-only keys
- Never shown again
- 2FA + Face ID
- 7-day trial