Skip to content

Compare model prices

Input, output, cached and batch prices, every route and a month of tokens, side by side.

GLM 5.3 FlashGLM 5.3 Prime

A month of tokens

  • GLM 5.3 Flash$7.30
  • GLM 5.3 Prime$456.00

100M input and 20M output tokens, list price. Use your own numbers.

Side by side

GLM 5.3 FlashGLM 5.3 Prime
Input per 1M$0.045$2.8
Output per 1M$0.14$8.8
Cached input$0.01$0.56
Batch in / outn/an/a
Blended (3:1)$0.069$4.3
Context1.31M1M
Routes302
ReleasedAug 26, 2026Sep 23, 2026
Leadersboard scoren/an/a

On the price map

$0.03$0.1$0.3$1$3$10$30$100$0.03$0.1$0.3$1$3$10$30$100$300Input $ per 1M tokensOutput $ per 1M tokensxxZZDMOOOOOOOOOOOOOOOOZDGMMDMGDQMGGMMZGGDDGGGGGGGGMOOOZQAQQAQQQAAAQAQxQQAQQAQAAAAQQQQxxxOOOOOOOOOOOOOOOOOAAOMMQQQMGGMQQQQQQQMMMMQQQQQQQMQQQQxMMCZZZZZZZAAAOAOOOOOOOACDDDDDMDDMGGZMOQQQMOOZZQMMQQQQQGGGMMMMMMOOOMQCAOCCOOOOOOMQGGGZMDMMGMMQQQ
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper

Every route

GLM 5.3 Flash

Way to buyIn / out per 1M
InferenceNet
fp4 · cached $0.01
$0.045 / $0.14Same as list
DeepInfra
fp4 · cached $0.015
$0.075 / $0.25+73% vs list
Relace
Default region · cached $0.02
$0.07 / $0.28+78% vs list
Inceptron
fp8 · cached $0.07
$0.09 / $0.28+100% vs list
GMICloud
fp8 · cached $0.018
$0.09 / $0.3+107% vs list
Morph
Default region · cached $0.018
$0.088 / $0.308+108% vs list
Wafer
Default region · cached $0.03
$0.089 / $0.35+124% vs list
Io Net
fp8 · cached $0.025
$0.125 / $0.42+189% vs list
OpenInference
fp4 · cached $0.025
$0.1 / $0.5+191% vs list
Phala
fp8 · cached $0.025
$0.128 / $0.425+194% vs list
Novita AI
fp8 · cached $0.026
$0.132 / $0.44+204% vs list
StreamLake
fp8 · cached $0.028
$0.141 / $0.47+225% vs list
Sail Research
us, fp8 · cached $0.029
$0.143 / $0.475+228% vs list
AtlasCloud
fp8 · cached $0.03
$0.15 / $0.5+245% vs list
Baseten
fp8 · cached $0.03
$0.15 / $0.5+245% vs list
CoreWeave
nvfp4 · cached $0.05
$0.15 / $0.5+245% vs list
Crusoe
fp4 · cached $0.03
$0.15 / $0.5+245% vs list
DigitalOcean
Default region · cached $0.03
$0.15 / $0.5+245% vs list
Fireworks AI
Default region · cached $0.03
$0.15 / $0.5+245% vs list
Friendli
Default region · cached $0.03
$0.15 / $0.5+245% vs list
Near AI
fp8 · cached $0.035
$0.15 / $0.5+245% vs list
Parasail
fp8 · cached $0.03
$0.15 / $0.5+245% vs list
Reka
fp8 · cached $0.03
$0.15 / $0.5+245% vs list
SiliconFlow
fp8 · cached $0.03
$0.15 / $0.5+245% vs list
Together AI
Default region · cached $0.03
$0.15 / $0.5+245% vs list
Venice
Default region · cached $0.03
$0.15 / $0.5+245% vs list
Z.ai
fp8 · cached $0.03
$0.15 / $0.5+245% vs list
NextBit
fp8 · cached $0.033
$0.165 / $0.55+280% vs list
Cloudflare Workers AI
Default region · cached $0.03
$0.3 / $1+591% vs list
Modal
fp8 · cached $0.09
$0.45 / $1.5+936% vs list

GLM 5.3 Prime

Way to buyIn / out per 1M
Z.ai API
The lab's own API · cached $0.56
$2.8 / $8.8List price
Qwen (Alibaba)
Default region · cached $0.56
$2.8 / $8.8Same as list

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.