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

35% off

$0.4875 / $1.56per 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
35% off
$0.75$0.4875$2.40$1.56$0.14$0.0911.55s39 tps
99.47%
$0.50$3.15$0.1151.26s21 tps
99.99%
$0.60$2.00$0.1514.58s29 tps
95.20%
51% off
$1.40$0.693$4.40$2.178$0.26$0.12871.85s45 tps
99.66%
$0.70$2.20$0.1051.08s52 tps
99.64%
$0.71$2.35$0.120.84s47 tps
99.12%
47% off
$1.40$0.742$4.40$2.332$0.26$0.13783.14s28 tps
99.83%
$0.76$2.42$0.140.55s117 tps
99.85%
$0.966$3.036$0.19321.95s42 tps
99.96%
25% off
$1.40$1.05$4.40$3.30$0.26$0.1954.02s27 tps
99.62%
$1.10$3.75$0.202.31s33 tps
99.10%
15% off
$1.40$1.19$4.40$3.74$0.26$0.2212.13s31 tps
100.00%
$1.26$3.00$0.224.66s35 tps
99.87%
10% off
$1.40$1.26$4.40$3.96$0.26$0.2343.09s37 tps
99.66%
$1.40$4.40$0.261.33s47 tps
99.84%
$1.40$4.40$0.142.07s76 tps
99.90%
$1.40$4.40$0.141.95s55 tps
99.92%
$1.40$4.40$0.141.42s56 tps
99.80%
$1.40$4.40$0.141.80s58 tps
99.98%
$1.40$4.40$0.141.26s52 tps
99.38%
$1.40$4.40$0.262.72s46 tps
99.95%
$1.40$4.40$0.263.20s40 tps
99.77%
$1.40$4.40$0.261.04s59 tps
99.96%
$1.40$4.40$0.260.75s83 tps
99.72%
$1.40$4.40$0.260.95s51 tps
99.35%
$1.40$4.40$0.260.68s57 tps
99.85%
$1.54$4.84$0.1541.84s49 tps
--
$2.10$6.60$0.211.85s96 tps
99.87%
$2.10$6.60$0.211.77s46 tps
99.81%
$2.10$6.60$0.211.59s54 tps
66.77%
$2.10$6.60$0.211.53s62 tps
96.31%
$2.31$7.26$0.4621.25s41 tps
99.99%
$1.40$4.40$0.260.80s63 tps
97.91%
43% off
$1.20$0.684$4.00$2.28$0.20$0.1140.76s81 tps
99.56%

Throughput

117tok/s

P50, best across providers

Latency

0.55s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-Bench
Fireworks Fast (US)
86.2%--
Ionstream
85.2%--
Wafer Fast
92.2%71.7%
Fireworks Fast
85.4%76.7%
Reka AI
90.5%71.1%
Makora
84.2%76.7%
Fireworks
86.1%74.0%
Wafer
83.2%73.8%
Makora
81.0%75.3%
+29 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
99.92%
Without Routing
95.37%

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.
1.22Ttokens
3.
Favicon for https://www.gohighlevel.com/
schema-markup-generation
new
774Btokens
4.
Favicon for https://www.gohighlevel.com/
HighLevel
new
696Btokens
5.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
237Btokens

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 $0.4875/M input tokens and $1.56/M output tokens, with separate rates for Cache Read at $0.091/M tokens.

GLM 5.2 has a 1,048,576 token context window. It supports up to 163,840 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: DeepInfra, Sail Research, Ambient, Decart, StreamLake, DigitalOcean, Inceptron, NovitaAI 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.