How much does GLM 5.2 cost?

GLM 5.2 costs $0.50/M input tokens and $3.15/M output tokens, with separate rates for Cache Read at $0.115/M tokens.

What is the context length of GLM 5.2?

GLM 5.2 has a 1,048,576 token context window. It supports up to 131,072 completion tokens.

Does GLM 5.2 support tool calling and structured outputs?

Yes. GLM 5.2 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Which providers serve GLM 5.2?

GLM 5.2 is served by 27 providers on OpenRouter: Sail Research, Decart, DigitalOcean, StreamLake, NovitaAI, GMICloud, DeepInfra, Inceptron and 19 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was GLM 5.2 released?

GLM 5.2 was released on 2026-06-16.

Z.ai: GLM 5.2

Name: Z.ai: GLM 5.2
Author: z-ai

z-ai/glm-5.2

Model weights

Compare

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering, and complex multi-step automation.

Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.

Modalities

In / Out Price

$0.50 / $3.15per 1M

Context

Released

Jun 16, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Latency / throughput


	$0.50	$3.15	$0.115	1.31s	18 tps	99.64%
43% off	$1.20$0.684	$4.00$2.28	$0.20$0.114	1.78s	52 tps	99.05%
	$0.70	$2.20	$0.105	1.19s	29 tps	98.44%
48% off	$1.40$0.7336	$4.40$2.306	$0.26$0.1362	1.38s	51 tps	99.41%
47% off	$1.40$0.7406	$4.40$2.328	$0.26$0.1375	1.77s	60 tps	99.11%
47% off	$1.40$0.742	$4.40$2.332	$0.26$0.1378	1.39s	42 tps	99.11%
	$0.75	$2.40	$0.14	1.31s	37 tps	98.94%
	$0.75	$2.90	$0.17	0.68s	92 tps	95.95%
	$0.76	$2.42	$0.14	0.54s	106 tps	85.82%
45% off	$1.40$0.77	$4.40$2.42	$0.26$0.143	1.41s	40 tps	93.87%
	$0.966	$3.036	$0.1932	1.38s	50 tps	99.77%
	$1.05	$4.40	$0.20	2.84s	25 tps	72.60%
	$1.134	$3.00	$0.2106	1.92s	37 tps	99.25%
15% off	$1.40$1.19	$4.40$3.74	$0.26$0.221	1.98s	33 tps	99.59%
	$1.26	$3.96	$0.234	4.55s	75 tps	98.56%
10% off	$1.40$1.26	$4.40$3.96	$0.26$0.234	2.38s	39 tps	96.42%
	$1.40	$4.40	$0.26	4.38s	40 tps	98.01%
	$1.40	$4.40	$0.14	1.48s	53 tps	98.82%
	$1.40	$4.40	$0.26	2.91s	41 tps	99.47%
	$1.40	$4.40	$0.26	0.78s	83 tps	99.59%
	$1.40	$4.40	$0.26	0.62s	112 tps	99.83%
	$1.40	$4.40	$0.26	1.74s	46 tps	98.28%
	$1.40	$4.40	$0.26	0.71s	45 tps	92.81%
	$1.40	$4.40	$0.26	0.69s	76 tps	99.66%
	$1.40	$4.40	$0.14	1.36s	83 tps	99.98%
	$2.10	$6.60	$0.21	0.92s	103 tps	93.09%
	$2.10	$6.60	$0.21	1.25s	67 tps	99.55%
	$2.10	$6.60	$0.21	1.38s	129 tps	99.85%
	$2.31	$7.26	$0.462	1.68s	69 tps	99.85%
	$1.10	$4.10	$0.22	1.47s	24 tps	94.64%
	$1.40	$4.40	$0.26	1.06s	56 tps	98.02%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

129tok/s

P50, best across providers

Latency

0.54s

P50, best provider

Latency / throughput

AutoExacto Benchmarks

GPQA DiamondTAU-Bench

Wafer Fast

90.5%73.5%

Venice

85.6%77.9%

Baidu Qianfan

86.4%76.8%

Z.ai

86.4%76.4%

Wafer

85.9%76.2%

Ambient

84.7%77.4%

+28 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.88%

Availability over the last 3 days

Last 72 hours

Availability 99.88%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.83%

Without Routing

71.73%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

4.1Ttokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

1.61Ttokens

schema-markup-generation

new

774Btokens

There are many coding agents, but this one is yours.

265Btokens

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

240Btokens