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 28 providers on OpenRouter: Sail Research, Ambient, Decart, StreamLake, NovitaAI, DigitalOcean, DeepInfra, Inceptron and 20 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

$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	1.81s	22 tps	99.94%
51% off	$1.40$0.693	$4.40$2.178	$0.26$0.1287	1.26s	58 tps	99.87%
50% off	$1.40$0.70	$4.40$2.20	$0.26$0.13	1.55s	46 tps	99.89%
	$0.70	$2.20	$0.105	0.94s	70 tps	99.24%
	$0.75	$2.40	$0.14	1.21s	38 tps	99.13%
	$0.75	$2.90	$0.17	0.60s	97 tps	96.52%
	$0.76	$2.42	$0.14	1.33s	60 tps	98.13%
	$0.966	$3.036	$0.1932	0.91s	59 tps	99.73%
	$1.10	$3.75	--	1.04s	66 tps	99.96%
15% off	$1.40$1.19	$4.40$3.74	$0.26$0.221	1.72s	56 tps	99.78%
	$1.26	$3.00	$0.22	1.71s	48 tps	99.83%
10% off	$1.40$1.26	$4.40$3.96	$0.26$0.234	1.80s	25 tps	99.26%
	$1.26	$3.96	$0.234	3.26s	27 tps	96.97%
	$1.40	$4.40	$0.26	0.87s	75 tps	99.88%
	$1.40	$4.40	$0.14	0.92s	76 tps	94.89%
	$1.40	$4.40	$0.26	1.70s	27 tps	99.70%
	$1.40	$4.40	$0.14	1.26s	55 tps	99.47%
	$1.40	$4.40	$0.26	4.52s	33 tps	99.89%
	$1.40	$4.40	$0.26	1.35s	51 tps	99.60%
	$1.40	$4.40	$0.26	0.60s	150 tps	99.95%
	$1.40	$4.40	$0.26	0.85s	56 tps	96.77%
	$1.40	$4.40	$0.26	0.60s	102 tps	99.21%
	$1.40	$4.40	$0.14	1.50s	92 tps	99.93%
	$1.40	$4.40	$0.26	2.08s	41 tps	97.42%
	$1.40	$4.40	$0.26	1.03s	93 tps	99.63%
	$2.10	$6.60	$0.21	1.08s	110 tps	99.89%
	$2.10	$6.60	$0.21	1.45s	91 tps	83.40%
	$2.10	$6.60	$0.21	1.15s	91 tps	93.64%
	$2.10	$6.60	$0.21	1.73s	100 tps	99.92%
	$2.31	$7.26	$0.462	1.68s	50 tps	99.98%
43% off	$1.20$0.684	$4.00$2.28	$0.20$0.114	1.09s	59 tps	97.95%
	$0.60	$2.00	$0.15	1.68s	54 tps	83.40%
	$0.8415	$3.137	$0.1683	1.60s	33 tps	73.35%

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

150tok/s

P50, best across providers

Latency

0.60s

P50, best provider

Latency / throughput

AutoExacto Benchmarks

GPQA DiamondTAU-Bench

Fireworks Fast (US)

86.4%--

Reka AI

90.2%76.0%

Wafer Fast

92.2%73.3%

Venice

84.1%77.9%

Baseten Fast

84.6%77.2%

Fireworks

85.5%75.8%

Fireworks Fast

85.0%75.6%

Wafer

83.2%73.8%

Baseten

83.8%70.7%

+29 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)

99.83%

Availability over the last 3 days

Last 72 hours

Availability 99.83%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.81%

Without Routing

91.31%

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.

1.45Ttokens

schema-markup-generation

new

774Btokens

HighLevel

new

310Btokens

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

238Btokens