GLM-5.2

ChatInput: TextReleased Jun 16, 2026

Built by Z.ai (Zhipu AI) · China · z.ai

Opus-class on coding benchmarks, 46% of the cost with caching

How to use

model: "zhipu/glm-5.2"

Cap quality here and save

Hard questions go to this model, easy ones drop to something cheaper. Set a savings target (0–0.8) and the router tunes itself until realized savings converge on it.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "zhipu/glm-5.2",
    "savings_target": 0.4
  }
}

Naming a model directly gets you that model — savings controls don't apply.

Context

1.0M

Max output

131K

Input $/1M

$0.85

Output $/1M

$2.68

Features

Tool callingJSON

Serving providers

DeepInfraNovitaFireworksFriendliW&B Inference

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Benchmark quality scores, and measured speed per provider.

Quality

Epoch Capabilities IndexComposite over 50+ benchmarks

151.6

GPQA DiamondPhD-level science questions

91.9%

AIMECompetition mathematics

86.4%

SWE-bench VerifiedReal GitHub issue resolution

78.7%

SciCodeScientific code generation

50.5%

ARC-AGI-2Abstract reasoning

22.8%

SimpleQA VerifiedFactual accuracy

38.1%

At each model's best reasoning effort. Benchmarks it wasn't run on are omitted.

Speed

Loading provider metrics…