Skip to content
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
  • 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

70% off

$0.4186 / $1.316per 1M

Context

1M

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
70% off
$1.40$0.4186$4.40$1.316$0.26$0.077741.00s59 tps
99.98%
70% off
$1.40$0.42$4.40$1.32$0.26$0.0781.35s46 tps
99.63%
35% off
$0.75$0.4875$2.40$1.56$0.14$0.0911.01s43 tps
98.36%
$0.50$3.15$0.1150.97s22 tps
99.99%
$0.60$2.00$0.1523.24s12 tps
94.71%
43% off
$1.20$0.684$4.00$2.28$0.20$0.1141.02s46 tps
99.84%
$0.70$2.20$0.1050.85s35 tps
99.62%
$0.71$2.35$0.120.43s42 tps
97.99%
47% off
$1.40$0.742$4.40$2.332$0.26$0.13781.22s22 tps
99.98%
$0.76$2.42$0.140.48s113 tps
99.83%
$0.966$3.036$0.19321.16s41 tps
99.94%
25% off
$1.40$1.05$4.40$3.30$0.26$0.1952.34s47 tps
99.75%
$1.10$3.75$0.200.49s46 tps
99.78%
15% off
$1.40$1.19$4.40$3.74$0.26$0.2211.58s56 tps
99.97%
$1.26$3.00$0.221.05s56 tps
99.96%
10% off
$1.40$1.26$4.40$3.96$0.26$0.2341.30s44 tps
99.88%
$1.40$4.40$0.142.12s30 tps
99.64%
$1.40$4.40$0.141.96s48 tps
98.75%
$1.40$4.40$0.141.97s143 tps
99.02%
$1.40$4.40$0.141.58s32 tps
99.13%
$1.40$4.40$0.141.02s59 tps
99.58%
$1.40$4.40$0.262.22s35 tps
97.22%
$1.40$4.40$0.262.59s50 tps
99.32%
$1.40$4.40$0.261.29s33 tps
99.71%
$1.40$4.40$0.260.50s106 tps
98.08%
$1.40$4.40$0.260.77s55 tps
99.78%
$1.40$4.40$0.260.86s43 tps
99.17%
$1.40$4.40$0.260.45s91 tps
99.46%
$1.54$4.84$0.1540.65s126 tps
100.00%
$2.10$6.60$0.212.07s45 tps
99.70%
$2.10$6.60$0.212.10s35 tps
99.06%
$2.10$6.60$0.210.66s185 tps
97.10%
$2.10$6.60$0.210.90s55 tps
94.85%
$2.31$7.26$0.4621.23s41 tps
99.99%

Throughput

156tok/s

P50, best across providers

Latency

0.50s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-Bench
Fireworks Fast (US)
86.2%--
Wafer Fast
92.2%72.9%
Fireworks Fast
85.4%76.4%
Reka AI
90.5%71.1%
Makora
84.2%76.7%
Ionstream
85.2%75.3%
Fireworks
86.1%73.9%
Wafer
83.2%73.8%
Makora
81.0%75.3%
+30 more providers
Uptime (3d)

100.00%

Availability (3d)

99.92%

Availability over the last 3 days

Last 72 hours
Availability 99.92%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.93%
Without Routing
95.16%

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.
4.21Ttokens
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.
1.24Ttokens
3.
Favicon for https://www.gohighlevel.com/
schema-markup-generation
new
774Btokens
4.
Favicon for https://www.gohighlevel.com/
HighLevel
new
680Btokens
5.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
244Btokens

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 $0.4186/M input tokens and $1.316/M output tokens, with separate rates for Cache Read at $0.07774/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 26 providers on OpenRouter: Baidu Qianfan, StreamLake, DeepInfra, Sail Research, Ambient, Decart, DigitalOcean, Inceptron and 18 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.