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
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Customers
  • 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 5.1

z-ai/glm-5.1

Model weights
Compare

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.

Modalities
In / Out Price
$0.90 / $2.90per 1M
Context
205K
Released
Apr 7, 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 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.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Z.ai: GLM 5.1 (Artificial Analysis, Design Arena and Vals AI)
SourceBenchmarkScore
Artificial AnalysisGLM-5.1 (Non-reasoning) GPQA Diamond83.9%
Artificial AnalysisGLM-5.1 (Non-reasoning) HLE27.9%
Artificial AnalysisGLM-5.1 (Non-reasoning) IFBench52.0%
Artificial AnalysisGLM-5.1 (Non-reasoning) τ²-Bench Telecom97.1%
Artificial AnalysisGLM-5.1 (Non-reasoning) AA-LCR53.3%
Artificial AnalysisGLM-5.1 (Non-reasoning) CritPt0.0%
Artificial AnalysisGLM-5.1 (Non-reasoning) Terminal-Bench Hard35.6%
Artificial AnalysisGLM-5.1 (Reasoning) Coding Index55.8
Artificial AnalysisGLM-5.1 (Reasoning) Agentic Index23.9
Artificial AnalysisGLM-5.1 (Reasoning) GPQA Diamond86.8%
Artificial AnalysisGLM-5.1 (Reasoning) HLE30.1%
Artificial AnalysisGLM-5.1 (Reasoning) IFBench76.3%
Artificial AnalysisGLM-5.1 (Reasoning) τ²-Bench Telecom97.7%
Artificial AnalysisGLM-5.1 (Reasoning) AA-LCR73.7%
Artificial AnalysisGLM-5.1 (Reasoning) τ-Bench Banking13.6%
Artificial AnalysisGLM-5.1 (Reasoning) GDPval-AA31.3%
Artificial AnalysisGLM-5.1 (Reasoning) CritPt4.6%
Artificial AnalysisGLM-5.1 (Reasoning) SciCode44.8%
Artificial AnalysisGLM-5.1 (Reasoning) Terminal-Bench Hard43.2%
Artificial AnalysisGLM-5.1 (Reasoning) Terminal-Bench 4.02.0%
Artificial AnalysisGLM-5.1 (Reasoning) Terminal-Bench 2.161.8%
Design ArenaGLM 5.1 Models Arena 3D Elo1246
Design ArenaGLM 5.1 Models Arena Asciiart Elo1139
Design ArenaGLM 5.1 Models Arena Code Categories Elo1267
Design ArenaGLM 5.1 Models Arena Data Visualization Elo1260
Design ArenaGLM 5.1 Models Arena Game Development Elo1263
Design ArenaGLM 5.1 Models Arena SVG Elo1216
Design ArenaGLM 5.1 Models Arena UI Component Elo1265
Design ArenaGLM 5.1 Models Arena Website Elo1265
Design ArenaGLM 5.1 Agents Arena Agenticgamedev Elo1125
Design ArenaGLM 5.1 Agents Arena Agentichtmlslides Elo1205
Design ArenaGLM 5.1 Agents Arena Agenticslides Elo1245
Design ArenaGLM 5.1 Agents Arena Agenticslides(Html) Elo1204
Design ArenaGLM 5.1 Agents Arena Agenticslides(Python-Pptx) Elo1240
Design ArenaGLM 5.1 Agents Arena Androidnative Elo1183
Design ArenaGLM 5.1 Agents Arena Full Stack Elo1167
Design ArenaGLM 5.1 Agents Arena Godotgamedev Elo1053
Design ArenaGLM 5.1 Agents Arena Htmlslides Elo1066
Design ArenaGLM 5.1 Agents Arena Mobile Apps Elo1160
Design ArenaGLM 5.1 Agents Arena Pptxslides Elo1241
Design ArenaGLM 5.1 Agents Arena Python-Pptxslides Elo1258
Design ArenaGLM 5.1 Agents Arena Python-Pptxslides Elo1144
Design ArenaGLM 5.1 Agents Arena Spreadsheet Elo1315
Design ArenaGLM 5.1 Agents Arena Webapps Elo1175
Design ArenaGLM 5.1 Models Arena 3D Elo1336
Design ArenaGLM 5.1 Models Arena Data Visualization Elo1366
Design ArenaGLM 5.1 Models Arena UI Component Elo1292
Design ArenaGLM 5.1 Models Arena Website Elo1290
Vals AIGLM 5.1 AIME91.9%
Vals AIGLM 5.1 CaseLaw v251.6%
Vals AIGLM 5.1 Code Migration25.8%
Vals AIGLM 5.1 CorpFin v264.5%
Vals AIGLM 5.1 Finance Agent (v2)44.8%
Vals AIGLM 5.1 GPQA Diamond84.5%
Vals AIGLM 5.1 Harvey's Legal Agent Benchmark v10.0%
Vals AIGLM 5.1 LiveCodeBench81.4%
Vals AIGLM 5.1 LegalBench84.4%
Vals AIGLM 5.1 Legal Research Bench27.9%
Vals AIGLM 5.1 MedCode41.6%
Vals AIGLM 5.1 MedScribe72.3%
Vals AIGLM 5.1 MMLU Pro86.9%
Vals AIGLM 5.1 ProgramBench0.0%
Vals AIGLM 5.1 ProofBench v122.2%
Vals AIGLM 5.1 SWE-bench76.4%
Vals AIGLM 5.1 TaxEval v271.2%
Vals AIGLM 5.1 Terminal-Bench 2.156.9%
Vals AIGLM 5.1 Vals Index52.5%
Vals AIGLM 5.1 Vibe Code Bench v1.131.5%

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.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

AI Model RankingsRanking
Latency / throughput
$0.900$2.900$0.09002.09s36 tps
99.35%
31% off
$1.40$0.966$4.40$3.036$0.26$0.17942.50s28 tps
99.64%
$1.210$4.200$0.60001.91s38 tps
96.91%
$1.260$3.960$0.23401.04s60 tps
99.43%
$1.330$4.180$0.24700.90s70 tps
95.43%
$1.380$4.400$0.26003.49s37 tps
100.00%
$1.400$4.400$0.26000.75s32 tps
99.68%
$1.400$4.400$0.26000.99s55 tps
100.00%
$1.400$4.400$0.26001.66s62 tps
100.00%
$1.400$4.400$0.26000.40s131 tps
99.93%
$1.400$4.400$0.26002.34s41 tps
99.66%
9% off
$1.54$1.401$4.84$4.404$0.286$0.26030.92s68 tps
99.20%
$1.190$3.740$0.60001.11s61 tps
99.94%
Throughput
131tok/s

P50, best across providers

Latency
0.40s

P50, best provider

AutoExacto benchmarks
GPQA DiamondTAU-BenchVenice89.0%76.2%Phala86.5%75.3%Alibaba Cloud Int.86.5%75.0%StreamLake85.4%74.5%Z.ai84.3%74.0%
+9 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.
99.60%

Availability over the last 3 days

Last 72 hours
Availability 99.60%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.59%
Without Routing
95.41%

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://mira.tg/
Mira
Mira is a Telegram-native AI assistant.
13.2Btokens
2.
Favicon for https://janitorai.com/
Janitor AI
Janitor AI is a chatbot platform where users create and chat with custom AI characters for interactive roleplay, storytelling, and immersive fiction.
6.4Btokens
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.
3.2Btokens
4.
Favicon for https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
2.85Btokens
5.
Favicon for https://sillytavern.app/
SillyTavern
SillyTavern is the LLM frontend for power users, a chat interface that connects to any model and gives deep control through character creation, roleplay, and prompt customization.
2.03Btokens

Frequently asked questions

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete,...

GLM 5.1 costs $0.90/M input tokens and $2.90/M output tokens, with separate rates for Cache Read at $0.09/M tokens.

GLM 5.1 has a 204,800 token context window. It supports up to 65,535 completion tokens.

Yes. GLM 5.1 accepts tools and tool_choice for function calling on 12 of the 13 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.

GLM 5.1 is served by 13 providers on OpenRouter: Chutes, StreamLake, SiliconFlow, Phala, AtlasCloud, Alibaba Cloud Int., NovitaAI, Nebius Token Factory and 5 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 5.1 was released on April 7, 2026.