Skip to content

Compare model prices

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

GLM 5.3GLM 5.3 Prime

A month of tokens

  • GLM 5.3$91.43
  • GLM 5.3 Prime$456.00

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

Side by side

GLM 5.3GLM 5.3 Prime
Input per 1M$0.561$2.8
Output per 1M$1.76$8.8
Cached input$0.104$0.56
Batch in / outn/an/a
Blended (3:1)$0.862$4.3
Context1.31M1M
Routes352
ReleasedAug 18, 2026Sep 23, 2026
Leadersboard score8 (#21)n/a

On the price map

Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper

Every route

GLM 5.3

Way to buyIn / out per 1M
Baidu
fp8 · cached $0.104
$0.561 / $1.76Same as list
Morph
Default region · cached $0.108
$0.655 / $2.06+17% vs list
DeepInfra
fp4 · cached $0.125
$0.563 / $2.5+21% vs list
InferenceNet
Default region · cached $0.114
$0.684 / $2.28+26% vs list
Novita AI
fp8 · cached $0.145
$0.783 / $2.46+39% vs list
Reka
Default region · cached $0.152
$0.761 / $2.57+41% vs list
Io Net
fp8 · cached $0.14
$0.78 / $2.62+44% vs list
Inceptron
fp4 · cached $0.203
$0.786 / $2.65+45% vs list
Phala
Default region · cached $0.156
$0.84 / $2.64+50% vs list
DigitalOcean
Default region · cached $0.169
$0.91 / $2.86+62% vs list
GMICloud
fp8 · cached $0.182
$0.98 / $3.08+75% vs list
Sail Research
fp8 · cached $0.19
$0.77 / $4+83% vs list
Sail Research
us, fp8 · cached $0.19
$0.77 / $4+83% vs list
SiliconFlow
fp8 · cached $0.208
$1.12 / $3.52+100% vs list
Decart
fp4 · cached $0.196
$1.19 / $3.74+112% vs list
Qwen (Alibaba)
Default region · cached $0.238
$1.19 / $3.74+112% vs list
Makora
fp4 · cached $0.19
$1.05 / $4.2+113% vs list
Friendli
Default region · cached $0.234
$1.26 / $3.96+124% vs list
AkashML
fp8 · cached $0.26
$1.3 / $4.4+141% vs list
AtlasCloud
fp8 · cached $0.26
$1.4 / $4.4+149% vs list
Baseten
fp4 · cached $0.14
$1.4 / $4.4+149% vs list
Cloudflare Workers AI
Default region · cached $0.26
$1.4 / $4.4+149% vs list
Crusoe
fp4 · cached $0.26
$1.4 / $4.4+149% vs list
Fireworks AI
Default region · cached $0.26
$1.4 / $4.4+149% vs list
Mistral AI
nvfp4 · cached $0.14
$1.4 / $4.4+149% vs list
Modal
Default region · cached $0.26
$1.4 / $4.4+149% vs list
Parasail
fp8 · cached $0.26
$1.4 / $4.4+149% vs list
PrimeIntellect
Default region · cached $0.26
$1.4 / $4.4+149% vs list
Together AI
Default region · cached $0.26
$1.4 / $4.4+149% vs list
Venice
Default region · cached $0.26
$1.4 / $4.4+149% vs list
Wafer
Default region · cached $0.36
$1.4 / $4.4+149% vs list
Wafer
us · cached $0.26
$1.4 / $4.4+149% vs list
Z.ai
fp8 · cached $0.26
$1.4 / $4.4+149% vs list
Baseten
fast, fp8 · cached $0.21
$2.1 / $6.6+274% vs list
Qwen (Alibaba)
fast · cached $0.56
$2.8 / $8.8+399% 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

Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Price changes by email

Thursdays, only in weeks when an LLM API list price changed.

Double opt-in. Unsubscribe any time.