z-ai Open weights Reasoning

GLM 4.7 pricing & benchmarks

Released Dec 22, 2025 · served by 9 providers · ranked #48 by intelligence in our index

Input / 1M tokens$0.400
Output / 1M tokens$1.75
Context window205K
Cached input$0.080
Intelligence index33.7
Coding index45.3
Agentic index25.4
1M in + 300K out$0.93

What GLM 4.7 is

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...

Providers and prices for GLM 4.7

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
DeepInfracheapest $0.400 $1.75 203K fp4 99.8%
StreamLake $0.480 $1.76 200K fp8 86.2%
AtlasCloud $0.520 $1.85 203K fp8 94.1%
Novita $0.540 $1.98 205K fp8 88.8%
Z.AI $0.600 $2.20 203K fp4 83.8%
Google $0.600 $2.20 200K 99.9%
Venice $0.550 $2.65 198K fp4 99.3%
Cerebras $2.25 $2.75 131K fp16 100.0%
Phala $0.850 $3.30 131K 95.9%

GLM 4.7 benchmark results

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

CategoryArenaRankEloWin rate
mobileapps agents #18 1185 49.5%
asciiart models #20 1204 48.2%
androidnative agents #24 1103 56%
fullstack agents #24 1098 44.9%
godotgamedev agents #28 1058 35.8%
3d models #32 1248 54.3%
svg models #32 1193 54.3%
codecategories models #34 1248 54.8%
website models #34 1251 55.3%
gamedev models #35 1245 55.2%
uicomponent models #37 1235 51%
dataviz models #40 1225 51.2%

Cheaper models in the same class

Models scoring within 4 points of GLM 4.7 on the Intelligence Index, but with a lower output price.

FAQ

How much does the GLM 4.7 API cost?

$0.400 per 1M input tokens and $1.75 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.93.

Is GLM 4.7 free?

No. It is a paid model starting at $0.400 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for GLM 4.7?

DeepInfra at $0.400 input / $1.75 output per 1M tokens (fp4 quantization).

Can I self-host GLM 4.7?

Yes — weights are published as zai-org/GLM-4.7 on Hugging Face, so you can run it on your own hardware.