Skip to content

GLM 5.2 (batch)

text → textHugging Face OpenRouter Cost calculator →

Best price · blended / 1M

$0.698

at DeepInfra

Input / output
$0.45 / $1.44
Providers
23
Spread
3.9×
7 days
0%
30 days
—
Context
1M
Prices per 1M tokens, blended: DeepInfra (fp4/flex) $0.698, Relace $0.833, DeepInfra $0.872, StreamLake $0.94, Ambient $0.95, Baidu $0.95, Morph $0.977, Novita $0.998, SiliconFlow $1.00, CoreWeave $1.07, DigitalOcean $1.075, DeepInfra (fp4/priority) $1.31, AtlasCloud $1.44, Alibaba $1.48, Wafer (us) $1.71, Alibaba (fp8/us-east-1) $1.72, Cloudflare $2.14, Wafer $2.14, BaseTen $2.15, BaseTen (fp8/us) $2.15, Friendli $2.15, GMICloud $2.15, Mistral (zdr) $2.15, Nebius $2.15, Parasail $2.15, Together $2.15, Venice $2.15, Z.AI $2.15, Mistral (eu) $2.365, BaseTen (fast) $3.225, BaseTen (us/fast) $3.225, Alibaba (fast) $3.55, Baidu (fast) $3.66.

Providers

  • DeepInfraCheapest
    fp4/flex
    $0.698
    $0.45 in · $1.44 out
    −26% vs ref
    1M ctx100% uptimefp4·−25% discount
  • $0.833
    $0.31 in · $2.40 out
    −11% vs ref
    1M ctx100% uptimefp4
  • $0.872
    $0.563 in · $1.80 out
    −7.2% vs ref
    1M ctx98.3% uptimefp4·−25% discount
  • $0.94
    $0.612 in · $1.92 out
    ref vs ref
    1M ctx100% uptimefp8·−56% discount
  • $0.95
    $0.60 in · $2.00 out
    +1.1% vs ref
    198K ctx87.5% uptimefp8
  • $0.95
    $0.619 in · $1.94 out
    +1.1% vs ref
    1M ctx100% uptimefp8·−56% discount
  • $0.977
    $0.643 in · $1.978 out
    +4.0% vs ref
    1M ctx100% uptimefp8
  • $0.998
    $0.65 in · $2.04 out
    +6.2% vs ref
    1M ctx100% uptimefp8·−54% discount
  • $1.00
    $0.651 in · $2.046 out
    +6.4% vs ref
    1M ctx100% uptimefp8·−50% discount
  • $1.07
    $0.62 in · $2.42 out
    +14% vs ref
    1M ctx100% uptimefp4
  • $1.075
    $0.70 in · $2.20 out
    +14% vs ref
    1M ctx99.5% uptime
  • fp4/priority
    $1.31
    $0.844 in · $2.70 out
    +39% vs ref
    1M ctx98.1% uptimefp4·−25% discount
  • $1.44
    $0.938 in · $2.948 out
    +53% vs ref
    1M ctx100% uptimefp8·−33% discount
  • $1.48
    $0.966 in · $3.036 out
    +58% vs ref
    1M ctx98.8% uptimefp8
  • $1.71
    $0.007 in · $6.80 out
    +81% vs ref
    1M ctx100% uptimefp4
  • fp8/us-east-1
    $1.72
    $1.12 in · $3.52 out
    +83% vs ref
    1M ctx100% uptimefp8
  • $2.14
    $0.19 in · $8.00 out
    +128% vs ref
    256K ctx100% uptime
  • $2.14
    $0.19 in · $8.00 out
    +128% vs ref
    1M ctx100% uptimefp4
  • $2.15
    $1.40 in · $4.40 out
    +129% vs ref
    1M ctx100% uptimefp8
  • fp8/us
    $2.15
    $1.40 in · $4.40 out
    +129% vs ref
    1M ctx100% uptimefp8
  • $2.15
    $1.40 in · $4.40 out
    +129% vs ref
    1M ctx98.7% uptime
  • $2.15
    $1.40 in · $4.40 out
    +129% vs ref
    1M ctx100% uptimefp8
  • $2.15
    $1.40 in · $4.40 out
    +129% vs ref
    1M ctx100% uptime
  • $2.15
    $1.40 in · $4.40 out
    +129% vs ref
    1M ctx0.0% uptimefp4
  • $2.15
    $1.40 in · $4.40 out
    +129% vs ref
    256K ctx100% uptimefp4
  • $2.15
    $1.40 in · $4.40 out
    +129% vs ref
    1M ctx99.7% uptime
  • $2.15
    $1.40 in · $4.40 out
    +129% vs ref
    1M ctx99.8% uptimefp8
  • $2.15
    $1.40 in · $4.40 out
    +129% vs ref
    1M ctx100% uptimefp8
  • $2.365
    $1.54 in · $4.84 out
    +152% vs ref
    1M ctx99.5% uptime
  • $3.225
    $2.10 in · $6.60 out
    +243% vs ref
    1M ctx100% uptimefp8
  • us/fast
    $3.225
    $2.10 in · $6.60 out
    +243% vs ref
    1M ctx100% uptimefp8
  • $3.55
    $2.31 in · $7.26 out
    +278% vs ref
    1M ctx97.6% uptimefp8
  • fast
    $3.66
    $2.25 in · $7.88 out
    +289% vs ref
    1M ctx100% uptimefp4
Blended = (3 × input + output) / 4. Ref $0.94 = median of cheapest 20%.

Price history

USD per 1M tokens · each step is a price change

Prices in USD / 1M tokens.

Other pricing

Offered byCache read
DeepInfra (fp4/flex)$0.084
Relace$0.075
DeepInfra, DigitalOcean$0.105
StreamLake$0.114
Ambient$0.15
Baidu$0.115
Morph$0.217
Novita$0.121
SiliconFlow$0.13
CoreWeave, BaseTen +3$0.14
DeepInfra (fp4/priority)$0.158
AtlasCloud$0.174
Alibaba$0.193
Wafer (us)$0.006
Alibaba (fp8/us-east-1)$0.224
Cloudflare$0.19
Wafer$0.18
Friendli, GMICloud +4$0.26
Mistral (eu)$0.154
BaseTen (fast), BaseTen (us/fast)$0.21
Alibaba (fast)$0.462
Baidu (fast)$0.56

Changes

  • Discount price,
    —→56%—
  • Cache read price,
    $0.26→$0.115−55.8%
  • Output price,
    $4.40→$1.94−55.8%
  • Input price,
    $1.40→$0.619−55.8%
  • Discount price,
    56%→56%+0.2%
  • Cache read price,
    $0.114→$0.114−0.2%
  • Output price,
    $1.93→$1.92−0.2%
  • Input price,
    $0.613→$0.612−0.2%
  • Cache read price,
    $0.0066→$0.075+1036%
  • Output price,
    $7.98→$2.40−69.9%
  • Input price,
    $0.0066→$0.31+4597%
  • No longer served,
    Delisted
  • GLM 5.2 (batch)
    New model,
    New model
  • GLM 5.2 (batch)
    Model retired,
    Retired
  • Cache read price,
    $0.217→$0.201−7.4%

About

The cheapest provider for GLM 5.2 (batch) is DeepInfra at $0.698 per 1M tokens (blended), charging $0.45 per 1M input and $1.44 per 1M output tokens. 23 providers serve it; the most expensive charges 3.9× the typical price. Context window: 1M tokens. Prices tracked since Nov 8, 2026.

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Released
Jun 16, 2026
First tracked
Nov 8, 2026
Canonical slug
z-ai/glm-5.2-20260616
Weights
zai-org/GLM-5.2