GLM 4.6 API Pricing 2026

Overview

GLM 4.6 was released on September 30, 2025. Pricing starts at $0.350 per million input tokens and $1.50 per million output tokens. The model supports a context window of up to 203K tokens. API access is available through Z-ai.

Context Window

203K

tokens

Pricing

Input$0.350

Output$1.50

per 1M tokens

Speed

Output69 tok/s

TTFT1.20s

median latency

Capabilities

Tools

Pricing Comparison

Compare GLM 4.6 with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Provider	Model	Input $/M	Output $/M	Context	Actions
Z Z-ai	glm-4.6	$0.350	$1.500	202,752	Try
TD Thedrummer	cydonia-24b-v4.1	$0.300	$0.500	131,072	Try
G Google	gemini-2.5-flash-image-preview	$0.300	$2.500	32,768	Try
MI Mistral AI	codestral-2508	$0.300	$0.900	256,000	Try
G Google	gemini-2.5-flash	$0.300	$2.500	1,048,576	Try
X Xai	grok-3-mini	$0.300	$0.500	131,072	Try
DS Deepseek	deepseek-chat	$0.300	$1.200	163,840	Try
AM Amazon	nova-2-lite-v1	$0.300	$2.500	1,000,000	Try
QW Qwen	qwen3-coder-flash	$0.300	$1.500	128,000	Try
NO Nousresearch	hermes-3-llama-3.1-70b	$0.300	$0.300	65,536	Try
M Meta-llama	llama-3-70b-instruct	$0.300	$0.400	8,192	Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

GLM 4.6 is available from multiple providers with different pricing and availability.

13

Providers

$0.350

Cheapest Input/M

$1.500

Cheapest Output/M

Chutes

Best Price

Provider Pricing

13 models

Provider	Input $/M	Output $/M	Uptime
C Chutes Best Price	$0.350	$1.500	-
S SiliconFlow	$0.390	$1.900	97.5%
D DeepInfra	$0.430	$1.750	100.0%
A AtlasCloud	$0.440	$1.740	98.1%
M Mancer 2	$0.450	$2.000	-
OpenRouter	$0.500	$1.750	-
F Fireworks	$0.550	$2.190	100.0%
N Novita	$0.550	$2.200	99.6%
Z Z.AI	$0.600	$2.200	96.1%
F Friendli	$0.600	$2.200	-
T Together	$0.600	$2.200	99.8%
B BaseTen	$0.600	$2.200	-
C Cerebras	$2.250	$2.750	-

Provider pricing data sourced from OpenRouter and Helicone

Cost vs. Quality

Compare GLM 4.6's benchmark performance against all models.

X-axis:

Y-axis:

Loading chart...

GLM 4.6

Other models

Detailed Benchmark Scores

Intelligence

29.8 (81th pct)

Coding

29.0 (81th pct)

Math

44.3 (56th pct)

MMLU Pro

78.4 (65th pct)

GPQA

63.2 (62th pct)

LiveCodeBench

56.1 (70th pct)

AIME

-

Aider

-

Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try GLM 4.6

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test GLM 4.6 directly in your browser.

Open Playground