How much does GLM 5.2 cost?

GLM 5.2 costs $0.4886/M input tokens and $1.536/M output tokens, with separate rates for Cache Read at $0.09074/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 supports response_format for JSON output, without JSON-schema enforcement.

Which providers serve GLM 5.2?

GLM 5.2 is served by 27 providers on OpenRouter: NovitaAI, Baidu Qianfan, Sail Research, StreamLake, Decart, DigitalOcean, GMICloud, DeepInfra 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

65% off

$0.4886 / $1.536per 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


65% off	$1.40$0.4886	$4.40$1.536	$0.26$0.09074	2.64s	34 tps	99.20%
65% off	$1.40$0.49	$4.40$1.54	$0.26$0.091	1.74s	47 tps	98.39%
	$0.50	$3.15	$0.115	2.28s	9 tps	99.64%
60% off	$1.40$0.56	$4.40$1.76	$0.26$0.104	1.48s	51 tps	99.51%
43% off	$1.20$0.684	$4.00$2.28	$0.20$0.114	2.41s	49 tps	99.06%
	$0.70	$2.20	$0.105	1.09s	48 tps	98.41%
47% off	$1.40$0.742	$4.40$2.332	$0.26$0.1378	1.76s	28 tps	98.94%
	$0.75	$2.40	$0.14	1.60s	30 tps	99.03%
	$0.75	$2.90	$0.17	0.72s	84 tps	95.83%
	$0.76	$2.42	$0.14	0.69s	96 tps	88.32%
45% off	$1.40$0.77	$4.40$2.42	$0.26$0.143	1.23s	21 tps	94.19%
	$0.966	$3.036	$0.1932	1.29s	48 tps	99.69%
	$1.05	$4.40	$0.20	2.02s	62 tps	75.44%
	$1.10	$4.10	$0.22	1.63s	33 tps	95.17%
	$1.134	$3.00	$0.2106	2.28s	38 tps	99.39%
15% off	$1.40$1.19	$4.40$3.74	$0.26$0.221	1.76s	45 tps	99.75%
	$1.26	$3.96	$0.234	5.30s	66 tps	98.52%
10% off	$1.40$1.26	$4.40$3.96	$0.26$0.234	1.46s	41 tps	97.22%
	$1.40	$4.40	$0.26	2.57s	34 tps	98.22%
	$1.40	$4.40	$0.14	1.61s	53 tps	98.30%
	$1.40	$4.40	$0.26	2.15s	57 tps	99.56%
	$1.40	$4.40	$0.26	0.63s	94 tps	99.58%
	$1.40	$4.40	$0.26	0.74s	115 tps	99.81%
	$1.40	$4.40	$0.26	1.85s	45 tps	98.02%
	$1.40	$4.40	$0.26	0.82s	48 tps	93.03%
	$1.40	$4.40	$0.26	0.59s	54 tps	99.59%
	$1.40	$4.40	$0.14	1.81s	64 tps	99.96%
	$2.10	$6.60	$0.21	0.98s	41 tps	99.69%
	$2.10	$6.60	$0.21	1.20s	137 tps	99.79%
	$2.31	$7.26	$0.462	1.66s	63 tps	99.86%
	$2.10	$6.60	$0.21	3.01s	90 tps	91.88%

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

137tok/s

P50, best across providers

Latency

0.59s

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)

99.86%

Availability over the last 3 days

Last 72 hours

Availability 99.86%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.81%

Without Routing

72.70%

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.

4.12Ttokens

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.

1.62Ttokens

schema-markup-generation

new

774Btokens

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

267Btokens

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.

242Btokens