How much does GLM 5.2 cost?

GLM 5.2 costs $0.336/M input tokens and $1.056/M output tokens, with separate rates for Cache Read at $0.0624/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 128,000 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: StreamLake, Baidu Qianfan, Sail Research, Ambient, Decart, NovitaAI, DigitalOcean, GMICloud 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 June 16, 2026.

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

76% off

$0.336 / $1.056per 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


76% off	$1.40$0.336	$4.40$1.056	$0.26$0.0624	2.12s	44 tps	99.85%
75% off	$1.40$0.35	$4.40$1.10	$0.26$0.065	1.01s	56 tps	99.92%
	$0.50	$3.15	$0.115	1.80s	39 tps	99.97%
	$0.60	$2.00	$0.15	1.00s	54 tps	94.48%
43% off	$1.20$0.684	$4.00$2.28	$0.20$0.114	1.81s	38 tps	96.55%
50% off	$1.40$0.70	$4.40$2.20	$0.26$0.13	1.16s	48 tps	99.83%
	$0.70	$2.20	$0.105	0.74s	77 tps	99.80%
47% off	$1.40$0.742	$4.40$2.332	$0.26$0.1378	1.23s	47 tps	99.91%
	$0.75	$2.40	$0.14	1.43s	32 tps	99.85%
	$0.75	$2.90	$0.17	0.70s	105 tps	96.58%
	$0.76	$2.42	$0.14	0.69s	96 tps	99.89%
	$0.8415	$3.137	$0.1683	2.73s	23 tps	95.86%
	$0.966	$3.036	$0.1932	1.11s	62 tps	99.76%
15% off	$1.40$1.19	$4.40$3.74	$0.26$0.221	1.15s	27 tps	99.99%
	$1.26	$3.00	$0.22	1.58s	28 tps	99.89%
10% off	$1.40$1.26	$4.40$3.96	$0.26$0.234	1.34s	53 tps	99.98%
	$1.26	$3.96	$0.234	5.11s	47 tps	99.20%
	$1.40	$4.40	$0.14	6.96s	56 tps	99.52%
	$1.40	$4.40	$0.14	1.11s	58 tps	99.44%
	$1.40	$4.40	$0.26	1.68s	75 tps	100.00%
	$1.40	$4.40	$0.26	0.92s	33 tps	99.98%
	$1.40	$4.40	$0.26	0.44s	105 tps	99.97%
	$1.40	$4.40	$0.26	0.51s	91 tps	98.17%
	$1.40	$4.40	$0.26	0.68s	89 tps	99.98%
	$1.40	$4.40	$0.26	1.65s	51 tps	99.46%
	$1.40	$4.40	$0.26	0.75s	108 tps	99.69%
	$2.10	$6.60	$0.21	0.95s	100 tps	99.85%
	$2.31	$7.26	$0.462	1.25s	73 tps	99.98%
	$1.40	$4.40	$0.14	1.43s	79 tps	98.55%
	$2.10	$6.60	$0.21	1.81s	86 tps	95.57%
	$2.10	$6.60	$0.21	0.81s	148 tps	97.43%
	$2.10	$6.60	$0.21	1.06s	125 tps	88.46%

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

148tok/s

P50, best across providers

Latency

0.44s

P50, best provider

Latency / throughput

AutoExacto Benchmarks

GPQA DiamondTAU-Bench

Fireworks Fast (US)

86.4%--

Wafer Fast

92.2%73.3%

Venice

84.1%77.9%

Baseten Fast

84.6%77.2%

Fireworks

85.5%75.8%

Ambient

84.6%76.3%

Fireworks Fast

85.0%75.6%

Wafer

83.2%73.8%

Baseten

83.8%70.7%

+27 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)

99.74%

Availability over the last 3 days

Last 72 hours

Availability 99.74%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.80%

Without Routing

93.30%

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.

4.01Ttokens

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.

1.53Ttokens

schema-markup-generation

new

774Btokens

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

254Btokens

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.

234Btokens