z-ai Open weights Reasoning

GLM 5 pricing & benchmarks

Released Feb 11, 2026 · served by 14 providers

Input / 1M tokens$0.600
Output / 1M tokens$1.92
Context window205K
Cached input$0.200
1M in + 300K out$1.18

What GLM 5 is

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

Providers and prices for GLM 5

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
StreamLakecheapest $0.600 $1.92 198K fp8 99.4%
GMICloud $0.600 $1.92 203K fp8 99.3%
DeepInfra $0.600 $2.08 203K fp4 99.9%
Baidu $0.700 $2.24 203K fp8 99.1%
DigitalOcean $0.750 $2.40 64K 97.8%
SiliconFlow $0.950 $2.55 205K fp8 99.0%
Chutes $0.950 $2.55 203K fp8 90.8%
AtlasCloud $0.950 $3.15 203K fp8 99.5%
Amazon Bedrock $1.00 $3.20 203K 84.5%
Novita $1.00 $3.20 203K fp8 100.0%
Z.AI $1.00 $3.20 203K fp8 96.8%
Parasail $1.00 $3.20 203K fp8 98.9%
Venice $1.00 $3.20 198K fp8 99.7%
Phala $1.20 $3.50 203K 89.4%

GLM 5 benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
androidnative agents #12 1225 59.6%
mobileapps agents #14 1215 52.5%
godotgamedev agents #16 1144 46.7%
htmlslides agents #16 1167 44.4%
fullstack agents #17 1169 51.7%
3d models #22 1286 56.3%
gamedev models #22 1290 57.4%
codecategories models #23 1278 55.5%
svg models #23 1218 54.4%
website models #25 1274 55%
dataviz models #28 1259 53%
asciiart models #29 1186 48%
uicomponent models #29 1267 53.6%

FAQ

How much does the GLM 5 API cost?

$0.600 per 1M input tokens and $1.92 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $1.18.

Is GLM 5 free?

No. It is a paid model starting at $0.600 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for GLM 5?

StreamLake at $0.600 input / $1.92 output per 1M tokens (fp8 quantization).

Can I self-host GLM 5?

Yes — weights are published as zai-org/GLM-5 on Hugging Face, so you can run it on your own hardware.