z-ai Open weights Reasoning

GLM 5.1 pricing & benchmarks

Released Apr 7, 2026 · served by 19 providers · ranked #29 by intelligence in our index

Input / 1M tokens$0.952
Output / 1M tokens$2.99
Context window205K
Cached input$0.179
Intelligence index40.2
Coding index55.8
Agentic index29.9
1M in + 300K out$1.85

What GLM 5.1 is

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...

Providers and prices for GLM 5.1

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
Baiducheapest $0.952 $2.99 203K fp8 99.7%
StreamLake $0.966 $3.04 200K fp8 99.5%
Chutes $0.980 $3.08 203K fp8 80.3%
GMICloud $0.980 $3.08 203K fp8 98.1%
Wafer $1.00 $3.20 203K fp4 99.7%
DeepInfra $1.05 $3.50 203K fp4 99.8%
SiliconFlow $1.19 $3.74 205K fp8 99.5%
AtlasCloud $1.26 $3.96 203K fp8 99.3%
Phala $1.21 $4.20 203K 76.3%
DigitalOcean $0.975 $4.30 164K 93.8%
Crusoe $1.20 $4.40 203K fp8 99.6%
Novita $1.38 $4.40 205K fp8 99.3%
Nebius $1.40 $4.40 203K fp8 90.5%
Parasail $1.40 $4.40 203K fp8 99.8%
Fireworks $1.40 $4.40 203K 99.6%
CoreWeave $1.40 $4.40 203K fp8 99.0%
Friendli $1.40 $4.40 203K 100.0%
Z.AI $1.40 $4.40 203K fp8 99.2%
Venice $1.54 $4.84 200K fp8 98.8%

GLM 5.1 benchmark results

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

CategoryArenaRankEloWin rate
agenticslides agents #3 1245 54.4%
dataviz models #3 1366 67%
agenticslides(python-pptx) agents #4 1240 53.3%
pptxslides agents #4 1241 53.5%
3d models #5 1336 62.6%
python-pptxslides agents #5 1258 54.2%
agentichtmlslides agents #6 1205 52%
agenticslides(html) agents #6 1204 51.8%
svg models #7 1270 59.5%
gamedev models #9 1326 61.2%
mobileapps agents #10 1226 53.9%
androidnative agents #11 1234 53%
htmlslides agents #11 1203 51.4%
uicomponent models #11 1313 59.6%
codecategories models #13 1308 58.1%
fullstack agents #13 1214 55.9%
agenticgamedev agents #14 1178 50.7%
website models #15 1299 55.9%
webapps agents #17 1225 53.5%
godotgamedev agents #25 1104 39.5%
asciiart models #30 1184 47.8%

Cheaper models in the same class

Models scoring within 4 points of GLM 5.1 on the Intelligence Index, but with a lower output price.

FAQ

How much does the GLM 5.1 API cost?

$0.952 per 1M input tokens and $2.99 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $1.85.

Is GLM 5.1 free?

No. It is a paid model starting at $0.952 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for GLM 5.1?

Baidu at $0.952 input / $2.99 output per 1M tokens (fp8 quantization).

Can I self-host GLM 5.1?

Yes — weights are published as zai-org/GLM-5.1 on Hugging Face, so you can run it on your own hardware.