Updated 9 Nov · updated in the last 30 hours

Z.ai GLM 4.6 API Pricing

Z.ai GLM 4.6 API pricing: $0.50 per 1M tokens for input and $2.00 per 1M tokens for output, from OpenRouter. Published Last checked · Source (data) · Methodology

OpenRouter: Amount worked out from the source page: $0.50 per 1M tokens, in USD · as shown in the United States on 9 Nov 2026 · the page does not say whether tax is included; we do not assume it is excluded · last price change seen on 29 Oct 2026.

Data as of9 Nov 2026Prices checked 9 Nov 2026 · test requests to 8 Nov 2026Data & API
Price changed 29 Oct 2026. output $2.20 → $2.00 (−9.1 %); input $0.55 → $0.50 (−9.1 %) per 1M tokens on OpenRouter. Confirmed by a later check on 30 Oct 2026. Briefing: what it does to task costs
Task receipt: OpenRouter: $0.085; Warm cache: $0.029 Calculated · Document analysis Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries. Warm-cache saving: $0.057 per task. Dashed outline: the no-cache bill.
Task receipt.Calculated · Document analysis Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries. Warm-cache saving: $0.057 per task. Dashed outline: the no-cache bill. Open image · Explore the chart · Measured Lab · CC BY 4.0
See cost receipt

Prices USD per 1M tokens, as listed

  • $0.50Input per 1M tokens, through OpenRouter Published
  • $2.00Output per 1M tokens, through OpenRouter Published
All prices by channel
Price per 1M tokensProvider directThrough OpenRouterPrevious prices by channel
Input—$0.50 PublishedOpenRouter: $0.55 until 29 Oct 2026
Output—$2.00 PublishedOpenRouter: $2.20 until 29 Oct 2026
Cached input · read—$0.10 Published—

Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026

16 Oct 2026$0.50 → $0.55 → $0.509 Nov 2026

Context window204,800tokens Published
Max output131,072tokens Published

OpenRouter providers who serves this model through OpenRouter, at what price

OpenRouter sends a call without a pinned provider to one of these endpoints, and each endpoint has its own price. Prices are USD per 1M tokens, input / output.

Pinned min: $0.40 / $1.60 · DeepInfra (deepinfra/fp4/flex)

Unpinned range: input $0.40–$0.60, output $1.60–$2.20 across 5 endpoints of 4 providers (listing shows $0.50 / $2.00).

Models with the widest provider price spread on OpenRouter

Request fragment that pins DeepInfra (deepinfra/fp4/flex):

{"provider": {"order": ["deepinfra/fp4/flex"], "allow_fallbacks": false}}

With fallbacks turned off, OpenRouter does not move the call to another provider. A full endpoint tag pins that endpoint; the provider name alone covers all of its endpoints (OpenRouter provider routing).

All endpoints (5), by input price
ProviderEndpoint tagPrecisionInputOutputContext, tokens
DeepInfradeepinfra/fp4/flexfp4$0.40$1.60202,752
Venicevenice/fp4fp4$0.43$1.75198,000
DeepInfradeepinfra/fp4fp4$0.50$2.00202,752
Novitanovita/bf16bf16$0.55$2.20204,800
Z.AIz-ai/fp4fp4$0.60$2.20202,752

Sorted by input price, then output price. Precision is the quantization field of the endpoints list.

Quality signals public test results, each with its source and date

SignalResultSource
Function callingBFCL V4 overall, native function calling, thinking on72.38 % Publishedlive 80.90 % · non-live 87.56 % · multi-turn 68.00 % · web search 77.50 % · memory 55.70 %Berkeley Function Calling Leaderboard, BFCL V4, last updated 12 Apr 2026read 17 Oct 2026 · leaderboard entry GLM-4.6 (FC thinking) · Apache 2.0
  • Your own task: quality on it is not measured here. These are public test sets; a short trial on a few of your own examples is the check that fits your work.
  • Other public leaderboards, without figures copied here: human preference votes on open-ended answers: Arena (LMArena) text leaderboard; long tasks in coding, data analysis and research: LiveBench.

What each signal covers and how our run is scored: methodology.

How we got this number

  • What we read: the published price on openrouter.ai/api/v1/models
  • Checked: ; tracked since 16 Oct 2026
  • Shown in: the United States
  • Checks so far: 25 checks since 16 Oct 2026
  • What changed: the price last changed on ; every change is listed under History
  • Page updated:

Other measured facts

QuestionAnswerCheckedStatus
How much does Z.ai GLM 4.6 cost per 1M cache-read tokens (cache hits) on OpenRouter?$0.10 per 1M tokensPublished
How much does Z.ai GLM 4.6 cost per 1M output tokens on OpenRouter?$2.00 per 1M tokensPublished
What is the context window of Z.ai GLM 4.6 on OpenRouter, in tokens?204,800 tokensPublished
What is the maximum output length of Z.ai GLM 4.6 on OpenRouter, in tokens?131,072 tokensPublished

History

  1. — $0.55 per 1M tokens → $0.50 per 1M tokens Confirmed by the check on 30 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
  2. — $2.20 per 1M tokens → $2.00 per 1M tokens (How much does Z.ai GLM 4.6 cost per 1M output tokens on OpenRouter?) Confirmed by the check on 30 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
  3. — $0.11 per 1M tokens → $0.10 per 1M tokens (How much does Z.ai GLM 4.6 cost per 1M cache-read tokens (cache hits) on OpenRouter?) Confirmed by the check on 30 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
  4. — $2.00 per 1M tokens → $2.20 per 1M tokens (How much does Z.ai GLM 4.6 cost per 1M output tokens on OpenRouter?) Confirmed by the check on 21 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
  5. — $0.50 per 1M tokens → $0.55 per 1M tokens Confirmed by the check on 21 Oct 2026. What this means for you: If you buy or renew this plan now, you pay the new price; the old price is shown for comparison.
  6. — First check: $0.50 per 1M tokens

The source record lists $0.0000005 per token ($0.50 per 1M tokens), fetched on 9 Nov 2026.

The source record, as published
"prompt":"0.0000005"
What the source says · openrouter.ai

Briefings on this model each price change recalculated as a task cost

  1. Z.ai GLM 4.6: price cut input $0.550 → $0.500 per 1M tokens (-9 %), output $2.20 → $2.00 per 1M tokens (-9 %)
  2. DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)
  3. DeepSeek V4.1 Flash 1017: price cut input $0.300 → $0.0060 per 1M tokens (-98 %), output $1.20 → $0.500 per 1M tokens (-58 %)

All briefings

Record history — 113 records for 5 questions
Last record
Shown in
the United States
How much does Z.ai GLM 4.6 cost per 1M input tokens on OpenRouter?
TimeValueStatus
9 Nov 2026$0.50 per 1M tokensPublished
8 Nov 2026$0.50 per 1M tokensPublished
7 Nov 2026$0.50 per 1M tokensPublished
6 Nov 2026$0.50 per 1M tokensPublished
5 Nov 2026$0.50 per 1M tokensPublished
4 Nov 2026$0.50 per 1M tokensPublished
3 Nov 2026$0.50 per 1M tokensPublished
2 Nov 2026$0.50 per 1M tokensPublished
1 Nov 2026$0.50 per 1M tokensPublished
31 Oct 2026$0.50 per 1M tokensPublished
30 Oct 2026$0.50 per 1M tokensPublished
29 Oct 2026$0.50 per 1M tokensPublished
How much does Z.ai GLM 4.6 cost per 1M cache-read tokens (cache hits) on OpenRouter?
TimeValueStatus
9 Nov 2026$0.10 per 1M tokensPublished
8 Nov 2026$0.10 per 1M tokensPublished
7 Nov 2026$0.10 per 1M tokensPublished
6 Nov 2026$0.10 per 1M tokensPublished
5 Nov 2026$0.10 per 1M tokensPublished
4 Nov 2026$0.10 per 1M tokensPublished
3 Nov 2026$0.10 per 1M tokensPublished
2 Nov 2026$0.10 per 1M tokensPublished
1 Nov 2026$0.10 per 1M tokensPublished
31 Oct 2026$0.10 per 1M tokensPublished
30 Oct 2026$0.10 per 1M tokensPublished
29 Oct 2026$0.10 per 1M tokensPublished
How much does Z.ai GLM 4.6 cost per 1M output tokens on OpenRouter?
TimeValueStatus
9 Nov 2026$2.00 per 1M tokensPublished
8 Nov 2026$2.00 per 1M tokensPublished
7 Nov 2026$2.00 per 1M tokensPublished
6 Nov 2026$2.00 per 1M tokensPublished
5 Nov 2026$2.00 per 1M tokensPublished
4 Nov 2026$2.00 per 1M tokensPublished
3 Nov 2026$2.00 per 1M tokensPublished
2 Nov 2026$2.00 per 1M tokensPublished
1 Nov 2026$2.00 per 1M tokensPublished
31 Oct 2026$2.00 per 1M tokensPublished
30 Oct 2026$2.00 per 1M tokensPublished
29 Oct 2026$2.00 per 1M tokensPublished
What is the context window of Z.ai GLM 4.6 on OpenRouter, in tokens?
TimeValueStatus
9 Nov 2026204,800 tokensPublished
8 Nov 2026204,800 tokensPublished
7 Nov 2026204,800 tokensPublished
6 Nov 2026204,800 tokensPublished
5 Nov 2026204,800 tokensPublished
4 Nov 2026204,800 tokensPublished
3 Nov 2026204,800 tokensPublished
2 Nov 2026204,800 tokensPublished
1 Nov 2026204,800 tokensPublished
31 Oct 2026204,800 tokensPublished
30 Oct 2026204,800 tokensPublished
29 Oct 2026204,800 tokensPublished
What is the maximum output length of Z.ai GLM 4.6 on OpenRouter, in tokens?
TimeValueStatus
9 Nov 2026131,072 tokensPublished
8 Nov 2026131,072 tokensPublished
7 Nov 2026131,072 tokensPublished
6 Nov 2026131,072 tokensPublished
5 Nov 2026131,072 tokensPublished
4 Nov 2026131,072 tokensPublished
3 Nov 2026131,072 tokensPublished
2 Nov 2026131,072 tokensPublished
1 Nov 2026131,072 tokensPublished
31 Oct 2026131,072 tokensPublished
30 Oct 2026131,072 tokensPublished
29 Oct 2026131,072 tokensPublished

Showing the latest 60 of 113 records; the full history is in data.json and data.csv.

Download JSON Download CSV

Explore the numbers

GLM 4.6

OpenRouter$0.085Warm cache$0.029$0.00$0.05$0.10OpenRouter$0.085Warm cache$0.029$0.00$0.05$0.10
OpenRouter$1,248.30Warm cache$422.67$0$500$1,000$1,500OpenRouter$1,248.30Warm cache$422.67$0$500$1,000$1,500

Calculated · Document analysis

Assumption: 3 steps; initial input 50,500 tokens; growth 2,500 tokens/step; visible output 1,000 tokens/step. Month: 14,600 tasks. No hidden reasoning or retries.

Warm-cache saving: $0.057 per task. Dashed outline: the no-cache bill.

Assumption: first-step cache fraction 75%; earlier context is read again and new context is written. All calls stay within the cache lifetime.

Formula: sum of input, output, cache reads and cache writes × their published rates / 1M. Each step uses its own context tier. Missing cache or batch prices are Unknown.

Fresh input · Visible output · Cache read · Cache write

Sources: this page; published model prices (data (JSON)); task assumptions (data (JSON)). Published prices · Observed responses · Calculated scenarios · Assumptions stated with each chart.