Deprecated on Jul 10, 2026. 12 providers still list it at the prices below.

GLM 5.1Deprecated

ZhipuReleased Apr 7, 2026

Tool use Reasoning Prompt caching Structured output

Compare GLM 5.1 Count tokens for GLM 5.1

Context

205K

Max output

203K

Serving providers

Cheapest input

$1.05 /1M

On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis and Hugging Face leaderboards

Speed & latency

Output speed

66 t/s

tokens / second

Time to first token

1.71s

latency

Headline indices

Intelligence Index

26.1

of 100

Coding Index

55.8

of 100

Frozen Sep 9, 2026

Agentic Index

25.2

of 100

Frozen Sep 9, 2026

Individual benchmarks · click a row for effort variants

Benchmark

Best score

Effort

Cost / task

AA-BriefcaseUndated

24%

default

—

AIME 2026

95%

default

—

Automation Bench

0.2

default

—

CritPt

default

—

EvalComputeProxyFrozen Aug 18, 2026

1461.7

default

—

GDPval v2Frozen Aug 18, 2026

1257.8

default

—

GPQA Diamond

87%

default

—

Humanity's Last Exam

30%

default

—

IFBench

76%

default

—

IT-Bench SRE

40%

default

—

Long-Context Reasoning

74%

default

—

Omniscience

0.8

default

—

Omniscience Accuracy

0.3

reasoning: false

—

Omniscience Non Hallucination

0.7

default

—

SciCode

45%

default

—

SWE-bench Pro

58%

default

—

Terminal Bench40

0.0

default

—

TerminalBench Hard

43%

default

—

TerminalBench v2.1

62%

default

—

τ-bench Banking

14%

default

—

τ²-bench

98%

default

—

Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.

We cannot tell whether this benchmark is still being published. Treat these scores as undated.

Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $1.05 to $1.40 per 1M tokens across 12 providers, so the dearest route costs 33% more than the cheapest for the same model.

Serving provider

Input /1M

Output /1M

Endpoints

DeepInfraCheapest

$1.05

$3.50

Standarddeepinfra/zai-org/GLM-5.1

Component	Unit	Standard
Text cached in	/1M tok	$0.205
Text input	/1M tok	$1.05
Text output	/1M tok	$3.50

OpenRouter

$1.33

$4.18

Novita

$1.38

$4.40

Dashscope

$1.40

$4.40

Fireworks AI

$1.40

$4.40

Friendliai

$1.40

$4.40

Nebius

$1.40

$4.40

Qwen AI Platform

$1.40

$4.40

Dashscope is dearest at $1.40 / $4.40

Price history

listed seller prices, input and output per 1M tokens

Input Output

Input down 25% since first tracked

Cost calculator

estimate your monthly spend on this model

Input tokens / call

Output tokens / call

Calls / month

Serving provider

$490

estimated / month

Model IDs

copy the exact identifier for your platform

deepinfra/zai-org/GLM-5.1z-ai/glm-5.1novita/zai-org/glm-5.1fireworks_ai/accounts/fireworks/models/glm-5p1zai/glm-5.1dashscope/glm-5.1qwencloud/glm-5.1qwen_ai_platform/glm-5.1nebius/zai-org/GLM-5.1zai/glm-5.1friendliai/zai-org/GLM-5.1together_ai/zai-org/GLM-5.1

Frequently asked questions

GLM 5.1 pricing, context and availability

Is GLM 5.1 still available?

GLM 5.1 was deprecated on 2026-07-10, but 12 serving providers still list it.

How much does GLM 5.1 cost?

GLM 5.1 costs $1.05 per 1M input tokens from DeepInfra, and $3.50 per 1M output tokens from DeepInfra. Across 12 serving providers, input prices range from $1.05 to $1.40 per 1M tokens.