How much does GLM 4.6 cost per million tokens?

$0.60 per million input tokens and $2.20 per million output tokens, as listed on OpenRouter on October 22, 2026.

Does GLM 4.6 support prompt caching?

Yes. OpenRouter lists cached input at $0.11 per million tokens, against $0.60 for uncached input.

Is there a cheaper model as good as GLM 4.6?

gpt-oss-20b scores 38.5 on the LLMBenchmark Index, within two points of GLM 4.6 or above it, and costs $0.15 per million output tokens.

Has the price of GLM 4.6 changed?

Not since we started recording it daily on October 21, 2026.

GLM 4.6 API pricing

As of October 22, 2026, Z.ai GLM 4.6 costs $0.60 per million input tokens and $2.20 per million output tokens on Z.ai's own API, with cached input at $0.11 per million.

GLM 4.6 benchmarks and specs · Every Z.ai model's price

Input, per million tokens$0.60
Output, per million tokens$2.20
Cached input, per million$0.11
Context window205K tokens
Max output131K tokens
Output speedNot measured

What a request costs

Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.

Cost of three workloads on GLM 4.6
Workload	Tokens	One request	1,000 requests	Fits the context window
Chat turn	1K input + 500 output tokens	$0.0017	$1.70	Yes
Repository review	50K input + 3K output tokens	$0.037	$36.60	Yes
Agent loop	200K input + 10K output tokens	$0.142	$142.00	No, it would need splitting
Solved coding task	One SWE-bench Verified attempt, divided by the share that succeed	Not computable	Not computable

Price history

We have read Z.ai's own price every day since October 21, 2026. It has not changed yet; any change will be listed here with its date.

October 21, 2026 First recorded: $0.60 input, $2.20 output

Cheaper models as good as GLM 4.6

Models within two points of GLM 4.6 or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.

GLM 4.6 pricing questions

How much does GLM 4.6 cost per million tokens?: $0.60 per million input tokens and $2.20 per million output tokens, as listed on OpenRouter on October 22, 2026.
Does GLM 4.6 support prompt caching?: Yes. OpenRouter lists cached input at $0.11 per million tokens, against $0.60 for uncached input.
Is there a cheaper model as good as GLM 4.6?: gpt-oss-20b scores 38.5 on the LLMBenchmark Index, within two points of GLM 4.6 or above it, and costs $0.15 per million output tokens.
Has the price of GLM 4.6 changed?: Not since we started recording it daily on October 21, 2026.