Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

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

Company

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

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

66% off

$0.4805 / $1.51per 1M

Context

1.0M

Released

Jun 16, 2026

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

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.

Explore more models

AI Model RankingsRanking
66% off
$1.40$0.4802$4.40$1.509$0.26$0.089181.04s62 tps
99.93%
66% off
$1.40$0.4805$4.40$1.51$0.26$0.089232.02s37 tps
99.60%
35% off
$0.75$0.4875$2.40$1.56$0.14$0.0911.18s45 tps
99.00%
$0.60$2.00$0.152.03s50 tps
92.32%
51% off
$1.40$0.6832$4.40$2.147$0.26$0.12692.45s43 tps
99.98%
$0.70$2.20$0.1050.90s53 tps
99.25%
$0.76$2.42$0.140.61s85 tps
99.85%
33% off
$1.40$0.938$4.40$2.948$0.26$0.17422.13s36 tps
99.93%
$0.966$3.036$0.19320.86s33 tps
99.86%
$1.084$2.895$0.17650.64s53 tps
98.70%
15% off
$1.40$1.19$4.40$3.74$0.26$0.2211.99s34 tps
100.00%
$1.26$3.00$0.221.69s61 tps
99.85%
$1.40$4.40$0.140.71s73 tps
98.99%
$1.40$4.40$0.140.83s71 tps
98.77%
$1.40$4.40$0.141.72s79 tps
99.86%
$1.40$4.40$0.262.16s67 tps
99.16%
$1.40$4.40$0.260.59s53 tps
98.53%
$1.40$4.40$0.141.39s60 tps
99.92%
$1.40$4.40$0.141.69s75 tps
99.79%
$1.40$4.40$0.260.99s60 tps
99.37%
$1.40$4.40$0.262.93s32 tps
99.57%
$1.40$4.40$0.261.04s73 tps
99.93%
$1.40$4.40$0.260.41s80 tps
99.85%
$1.40$4.40$0.263.15s36 tps
100.00%
$1.40$4.40$0.264.43s45 tps
99.41%
$1.54$4.84$0.1542.39s50 tps
100.00%
$2.10$6.60$0.211.00s189 tps
99.93%
$2.10$6.60$0.211.88s79 tps
99.93%
$2.10$6.60$0.211.14s93 tps
99.99%
$2.10$6.60$0.211.66s78 tps
99.95%
$2.10$6.60$0.210.78s129 tps
99.80%
$2.25$7.88$0.560.87s79 tps
100.00%
$2.31$7.26$0.4621.86s64 tps
99.99%

Throughput

189tok/s

P50, best across providers

Latency

0.41s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-Bench
Fireworks Fast (US)
86.5%--
Baidu Qianfan
85.9%--
Fireworks Fast
84.9%--
Venice
86.3%75.6%
Reka
90.7%71.1%
Makora
84.2%76.7%
Fireworks
86.4%73.7%
Baidu Qianfan
84.9%73.1%
Makora
81.0%75.3%
+28 more providers
Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.91%

Availability over the last 3 days

Last 72 hours
Availability 99.91%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.89%
Without Routing
95.83%

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.
3.01Ttokens
2.
Favicon for https://www.gohighlevel.com/
HighLevel
new
1Ttokens
3.
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.
959Btokens
4.
Favicon for https://www.gohighlevel.com/
schema-markup-generation
new
310Btokens
5.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
201Btokens

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 $0.4805/M input tokens and $1.51/M output tokens, with separate rates for Cache Read at $0.08923/M tokens.

GLM 5.2 has a 1,048,576 token context window. It supports up to 128,000 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 24 providers on OpenRouter: StreamLake, Baidu Qianfan (fp4), DeepInfra, Ambient, NovitaAI, DigitalOcean, CoreWeave, AtlasCloud and 16 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.