Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • EU routing
  • 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
  • AI Site Map

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
$0.0699 / $1.40per 1M
Context
1.0M
Released
Aug 18, 2026
Compare
ProvidersPricingPerformanceUptimeAppsActivityFAQExplore

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 Floor (cheapest).

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.

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.

API

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.

Z.ai: GLM versions

Available through EU in-region routing

Z.ai: GLM 5.3 is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in Europe
Inceptron, Mistral
Prices in Europe
  • Inceptron: $0.60/M tokens input, $2.80/M tokens output
  • Mistral: $1.54/M tokens input, $4.84/M tokens output
Base URL
https://eu.openrouter.ai/api/v1
Plan
Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs

Explore more models

AI Model RankingsRanking
Latency / throughput
$0.0699$1.4000$0.06890.42s133 tps
99.36%
$0.1790$1.4000$0.17800.33s121 tps
99.71%
$0.0800$3.6000$0.07600.64s111 tps
100.00%
$0.0800$3.6000$0.07600.48s104 tps
100.00%
$0.8400$2.7100$0.19000.71s140 tps
100.00%
$0.6000$2.8000$0.12000.57s108 tps
99.97%
$0.0703$4.3843$0.07031.26s89 tps
100.00%
$0.1400$4.4000$0.10001.30s100 tps
95.60%
$1.4000$4.4000$0.26000.72s106 tps
100.00%
30% off
$0.20$0.1400$6.00$4.2000$0.15$0.10500.53s75 tps
98.90%
38% off
$0.90$0.5625$4.00$2.5000$0.20$0.12500.85s75 tps
99.55%
$1.4000$4.4000$0.26000.61s150 tps
99.97%
$1.4000$4.4000$0.26000.59s133 tps
99.94%
$0.2500$2.9500$0.18000.94s75 tps
99.92%
$1.4000$4.4000$0.14001.45s99 tps
100.00%
$1.4000$4.4000$0.26000.72s98 tps
99.76%
$0.9800$3.0800$0.18200.63s104 tps
100.00%
$1.4000$4.4000$0.14001.10s93 tps
98.37%
$1.4000$4.4000$0.14001.51s76 tps
99.62%
$0.6690$4.4000$0.16700.65s52 tps
98.72%
$1.6800$5.2800$0.31201.64s140 tps
98.35%
$1.4000$4.4000$0.26001.22s61 tps
99.47%
55% off
$1.40$0.6300$4.40$1.9800$0.26$0.11702.21s48 tps
100.00%
10% off
$1.40$1.2600$4.40$3.9600$0.26$0.23400.74s80 tps
100.00%
$1.2000$4.0000$0.19001.09s63 tps
93.63%
$0.1900$4.4000$0.19001.90s48 tps
99.88%
Fast
$2.1000$6.6000$0.39001.14s97 tps
98.90%
$1.4000$4.4000$0.26000.44s87 tps
98.42%
$1.4000$4.4000$0.26003.32s45 tps
100.00%
20% off
$1.75$1.4000$5.50$4.4000$0.325$0.26000.85s65 tps
97.13%
50% off
$1.40$0.7000$4.40$2.2000$0.26$0.13002.85s47 tps
99.94%
40% off
$1.40$0.8400$4.40$2.6400$0.26$0.15604.91s25 tps
100.00%
$1.4000$4.4000$0.26002.50s31 tps
100.00%
$2.1000$6.6000$0.40000.34s85 tps
93.33%
Prime
$2.8000$8.8000$0.56001.58s63 tps
100.00%
$1.4000$4.4000$0.26005.70s18 tps
100.00%
$0.9800$3.0800$0.18200.90s97 tps
100.00%
$0.6000$2.5000$0.10000.78s86 tps
100.00%
$0.9100$2.8600$0.16900.85s106 tps
100.00%
$1.4000$4.4000$0.14000.75s120 tps
100.00%
$1.4000$4.4000$0.26001.07s48 tps
100.00%
$1.1900$3.7400$0.23802.22s38 tps
100.00%
50% off
$1.40$0.7000$4.40$2.2000$0.26$0.13003.89s35 tps
100.00%
$0.5000$2.0000$0.08000.88s74 tps
100.00%
$0.5000$2.0000$0.08000.53s109 tps
100.00%
Fast
$2.1000$6.6000$0.21001.08s133 tps
99.82%
Fast
$2.1000$6.6000$0.21001.71s94 tps
99.84%
Not used in Standard routing:Why these endpoints are not used
$1.5400$4.8400$0.15400.75s130 tps
100.00%
Throughput
150tok/s

P50, best across providers

Latency
0.33s

P50, best provider

AutoExacto benchmarks
GPQA DiamondTAU-BenchOpenInference87.9%--Z.ai88.7%78.1%Venice87.3%79.0%DeepInfra87.5%78.3%Baseten (fp8) (US)83.6%81.8%Baseten (fp4) (US)85.4%77.5%Baseten (fp4)85.0%77.3%Baseten (fp8)84.1%74.9%
+35 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.
99.93%

Availability over the last 3 days

Last 72 hours
Availability 99.93%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.93%
Without Routing
83.11%

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 provider routing 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.
2.59Ttokens
2.
Favicon for https://strix.ai/
Strix
new
1.13Ttokens
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.
773Btokens
4.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
571Btokens
5.
Favicon for https://omp.sh/
omp
new
491Btokens

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 $0.0699/M input tokens and $1.40/M output tokens, with separate rates for Cache Read at $0.0689/M tokens.

GLM 5.3 has a 1,048,576 token context window. It supports up to 1,048,576 completion tokens.

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

GLM 5.3 is served by 37 providers on OpenRouter: Wafer, Relace, inference.net, Reka AI, Makora, AkashML, DekaLLM, Sail Research and 29 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.