Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for z-ai

Z.ai: GLM 5.2

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

1M

Released

Jun 16, 2026

Compare

About Z.ai: GLM 5.2

OpenRouter makes Z.ai: GLM 5.2 available through a unified, OpenAI-compatible API using the model ID z-ai/glm-5.2. Requests can be routed across 27 providers, including Sail Research, Ambient, Decart, DigitalOcean, StreamLake, NovitaAI, GMICloud, DeepInfra and 19 more, with automatic failover when an endpoint is unavailable.

Z.ai: GLM 5.2 accepts text and returns text. It has a 1,048,576-token context window and a maximum output of 131,072 tokens.

On OpenRouter, Z.ai: 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. Effective pricing can be lower when prompt caching applies. It was released on June 16, 2026.

More models from Z.ai

  • GLM 5.3
  • GLM 5.1
  • GLM 5V Turbo

Frequently asked questions

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.

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.

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

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

GLM 5.2 is served by 27 providers on OpenRouter: Sail Research, Ambient, Decart, DigitalOcean, StreamLake, NovitaAI, 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.

GLM 5.2 was released on June 16, 2026.

ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQ

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).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

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).

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.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

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.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

$0.50$3.15$0.1151.50s17 tps
98.89%
43% off
$1.20$0.684$4.00$2.28$0.20$0.1141.78s51 tps
99.81%
$0.70$2.20$0.1051.26s33 tps
99.04%
48% off
$1.40$0.7336$4.40$2.306$0.26$0.13621.38s45 tps
99.86%
47% off
$1.40$0.7406$4.40$2.328$0.26$0.13752.13s31 tps
99.94%
47% off
$1.40$0.742$4.40$2.332$0.26$0.13781.81s51 tps
99.62%
$0.75$2.90$0.170.56s111 tps
96.19%
$0.76$2.42$0.140.37s167 tps
99.95%
45% off
$1.40$0.77$4.40$2.42$0.26$0.1431.33s33 tps
99.22%
$0.966$3.036$0.19321.16s49 tps
99.68%
$1.10$4.10$0.221.33s29 tps
98.11%
$1.134$3.00$0.21062.61s40 tps
99.83%
15% off
$1.40$1.19$4.40$3.74$0.26$0.2211.82s39 tps
99.98%
$1.26$3.96$0.2345.27s49 tps
99.20%
10% off
$1.40$1.26$4.40$3.96$0.26$0.2341.55s42 tps
99.85%
$1.40$4.40$0.263.78s33 tps
99.55%
$1.40$4.40$0.141.13s56 tps
97.16%
$1.40$4.40$0.262.66s59 tps
99.73%
$1.40$4.40$0.260.49s118 tps
99.84%
$1.40$4.40$0.260.61s83 tps
99.88%
$1.40$4.40$0.261.88s32 tps
98.74%
$1.40$4.40$0.260.68s86 tps
96.32%
$1.40$4.40$0.260.97s47 tps
99.95%
$1.40$4.40$0.260.85s41 tps
99.83%
$1.40$4.40$0.141.14s44 tps
99.82%
$2.10$6.60$0.210.68s136 tps
98.88%
$2.10$6.60$0.210.62s77 tps
99.98%
$2.10$6.60$0.211.30s55 tps
99.53%
$2.31$7.26$0.4621.31s44 tps
99.91%
$0.75$2.40$0.141.37s36 tps
97.96%
$0.60$2.00$0.154.64s15 tps
81.98%

Throughput

167tok/s

P50, best across providers

Latency

0.37s

P50, best provider

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 (3d)

100.00%

Availability (3d)

99.82%

Availability over the last 3 days

Last 72 hours
Availability 99.82%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.70%
Without Routing
82.15%

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.

1.
Favicon for https://claude.ai/apple-touch-icon.png
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
2.
Favicon for https://nousresearch.com
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.
1.57Ttokens
3.
Favicon for https://www.gohighlevel.com/
schema-markup-generation
new
774Btokens
4.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
260Btokens
5.
Favicon for https://openclaw.ai/
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.
237Btokens