GLM 5.1

ChatInput: TextReleased Apr 7, 2026

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

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...

How to use

model: "zhipu/glm-5.1"

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-5.1",
    "savings_target": 0.4
  }
}

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

Context

205K

Max output

128K

Input $/1M

$1.05

Output $/1M

$3.50

Features

Tool callingJSON

Serving providers

DeepInfraNovitaFriendliW&B InferenceFireworks

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

150.4

GPQA DiamondPhD-level science questions

85.5%

AIMECompetition mathematics

92.2%

FrontierMathResearch-level mathematics

33.5%

SWE-bench VerifiedReal GitHub issue resolution

74.2%

SciCodeScientific code generation

43.8%

SimpleQA VerifiedFactual accuracy

37.3%

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

Speed

Loading provider metrics…