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 5.3

z-ai/glm-5.3

Model weights
Compare

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.

Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.

Modalities

In / Out Price

50% off

$0.70 / $2.20per 1M

Context

1.3M

Released

Aug 18, 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
50% off
$1.40$0.70$4.40$2.20$0.26$0.132.28s34 tps
99.30%
14% off
$1.17$1.007$3.96$3.41$0.234$0.20151.73s28 tps
99.01%
22% off
$1.40$1.092$4.40$3.432$0.26$0.20282.10s44 tps
99.95%
$1.12$3.52$0.2241.40s72 tps
98.30%
20% off
$1.40$1.12$4.40$3.52$0.26$0.2082.65s52 tps
99.26%
10% off
$1.25$1.125$4.80$4.32$0.29$0.2611.15s83 tps
99.55%
$1.15$4.40$0.230.80s58 tps
97.44%
10% off
$1.30$1.17$4.40$3.96$0.26$0.2340.67s143 tps
99.52%
$1.19$4.40$0.261.79s51 tps
99.56%
$1.20$4.00$0.121.51s85 tps
96.99%
10% off
$1.40$1.26$4.40$3.96$0.26$0.2340.93s113 tps
100.00%
$1.35$4.40$0.230.92s108 tps
95.41%
$1.40$4.40$0.264.93s122 tps
98.17%
$1.40$4.40$0.261.27s59 tps
99.98%
$1.40$4.40$0.264.67s30 tps
98.92%
$1.40$4.40$0.262.20s49 tps
99.90%
$1.40$4.40$0.261.00s37 tps
98.93%
$1.40$4.40$0.260.84s62 tps
99.06%
$1.40$4.40$0.260.81s77 tps
99.54%
$1.40$4.40$0.141.23s80 tps
98.25%
$1.40$4.40$0.261.35s57 tps
99.93%
$1.40$4.40$0.262.68s61 tps
98.80%
$1.40$4.40$0.266.60s58 tps
97.61%
$1.40$4.40$0.263.33s44 tps
99.90%
$1.75$5.50$0.3250.73s68 tps
97.94%
$2.10$6.60$0.211.27s91 tps
99.88%
15% off
$1.40$1.19$4.40$3.74$0.23$0.19551.73s66 tps
96.16%
$1.40$4.40$0.260.40s109 tps
95.43%

Throughput

143tok/s

P50, best across providers

Latency

0.40s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-Bench
Wafer
92.6%78.0%
DigitalOcean
90.6%79.3%
Crusoe
82.8%--
auto-routing
84.8%80.0%
Baseten
86.2%77.9%
Baseten
85.6%77.0%
+23 more providers
Uptime (3d)

100.00%

Availability (3d)

99.76%

Availability over the last 3 days

Last 72 hours
Availability 99.76%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.91%
Without Routing
95.80%

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://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.
503Btokens
2.
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.
428Btokens
3.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
229Btokens
4.
Favicon for https://omp.sh/
Oh-My-Pi
new
209Btokens
5.
Favicon for https://strix.ai/
Strix
new
201Btokens

Frequently asked questions

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency. Reasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.

GLM 5.3 costs $0.70/M input tokens and $2.20/M output tokens, with separate rates for Cache Read at $0.13/M tokens.

GLM 5.3 has a 1,310,720 token context window. It supports up to 128,000 completion tokens.

Yes. GLM 5.3 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

GLM 5.3 is served by 27 providers on OpenRouter: StreamLake, Reka AI, NovitaAI, Morph, GMICloud, io.net, Inceptron, AkashML 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 5.3 was released on August 18, 2026.