ModelPriceWatch.com
Last scan 2026-08-01 Models tracked 181 Providers 27 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

GLM-5.2

by Z.AI

Current flagship open weights mid tier
Email me when GLM-5.2 gets cheaper

Today's price · per 1M tokens

Input

$1.40

per 1M tokens

Output

$4.40

per 1M tokens

Blended

$2.90

avg of input & output $/1M

Cached input

$0.260

19% of input — prompt caching

Source: official Z.AI pricing · read Jun 25, 2026 MODELPRICEWATCH.COM · 2026-08-01

Available on 3 hosts

cheapest blended first · $ per 1M tokens

GLM 5.2 is sold by 3 providers. Prices are per 1M tokens (blended = avg of input & output). The first-party row is the model maker; “vs first-party” shows each host’s blended price relative to it.

GLM 5.2 price on every host still selling it, per 1M tokens, cheapest blended first
Host Input Output Blended vs first-party
Fireworks details → $1.40 $4.40 $2.90 0%
Together details → $1.40 $4.40 $2.90 0%
Z.AI first-party $1.40 $4.40 $2.90 —
Each host links to its provider page and official pricing. Prices refresh twice daily. MODELPRICEWATCH.COM · 2026-08-01

Overview

Z.AI's flagship open-weights model — a 744B-parameter Mixture-of-Experts (~40B active per token) with a 1M-token context and MIT-licensed weights. Tops open-weight leaderboards and rivals frontier models on long-horizon coding. ~$1.40/$4.40 per 1M tokens via hosts.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 1/5
Text ✓ Image Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 3/9
Prompt caching ✓ Reasoning Coding Fast inference Long context ✓ Open weights ✓ Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Avg benchmark score76%
Perf per $/Mtok26.2
GPQA Diamond
91.2%
SWE-Bench Verified vendor
45%
Terminal-Bench 2.1
81%
MCP Atlas
77%
Humanity's Last Exam
54.7%
ARC-AGI 2 vendor
30%
AIME 2025 vendor
70%
MMMLU vendor
80%
BFCL vendor
70%
HumanEval vendor
84%
MATH 500 vendor
76%
AIME 2026 *
99.2%
Independent composite scores
  • AA Intelligence Index: 51.1 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA Agentic Index: 43.1 (Tool use, planning, autonomy)
  • AA-Omniscience Index: 4 (−100–100)
  • GDPval-AA v2: 1510 ELO (Real-world work tasks, human baseline = 1000)
  • LMSYS Chatbot Arena: 1469.4 ELO (Human preference)
How it stacks up
  • Ranks #23 of 68 benchmarked models by average score
  • Ranks #21 of 133 comparably-measured models by percentile score, across 9 independent measurements
  • Ranks #55 of 133 comparably-tested models by normalized performance per dollar
  • Strongest at AIME 2026 — 99.2%, #1 of 8

347 tokens/sec output 1.14s latency to first token (TTFT)

Source: Vellum LLM Leaderboard · updated Aug 1, 2026 · See full rankings →

Specifications

Provider
Z.AI
Context window
1M tokens
Modality
text
Parameters
Proprietary
Open source
Yes — open weights available
Released
Jun 13, 2026
Status
Current
Last updated
Jun 25, 2026
Tags
open-weightsflagshipcaching

Availability verified: Jul 20, 2026 — listed on Z.AI's own page

Try on Z.AI Official pricing page