modelbenchmark.io

GLM-5.3-Flash

Zhipu · glm-5-3-flash

Compare

Native multimodal GLM model for efficient coding and long-horizon agent tasks

Specification

zhipuai listing

Context
1M
Max output
131K
Released
2026-08-26
Knowledge cutoff
Retires
Open weights
yes
Input
text, image, video, pdf
Output
text

Price

US dollars per million tokens · zhipuai list price

Input
$0.075
Output
$0.25
Cache read
$0.015
Cache write
free

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Priority inputfireworks_ai$0.1875
Priority outputfireworks_ai$0.625

Quality

7 benchmarks · 2 sources

Composite
61st
percentile of 334 scored models
Rank
131 / 334
±0.09 sd
Evidence
7 × 2
3 or more benchmarks, from 2 or more sources
Effort range
one configuration only
reasoning62nd3/4 bench
math72nd3/7 bench
general23rd1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
OTIS Mock AIME 2024-202593.9 ±2.2maxEpoch AI2026-08-26
GPQA diamond90.2 ±1.7maxEpoch AI2026-08-26
FrontierMath-Tiers-1-3-v255.8 ±2.9maxEpoch AI2026-08-27
Chess Puzzles14.0 ±3.5maxEpoch AI2026-08-26
FrontierMath-Tier-4-v217.1 ±5.9maxEpoch AI2026-08-27
LiveBench71.1default · 23 runsLiveBench2026-06-25
Mystery Game Puzzles8.0 ±2.7maxEpoch AI2026-08-28

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 66 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
zhipuaivendor$0.075$0.25$0.015free1M131K
kenarifreefree1M131K
nvidia · z-aifreefree1M131K
scnet-token-planfreefreefree1M131K
volcengine-coding-planfreefreefree1M131K
zai-coding-planfreefreefreefree1M131K
zhipuai-coding-planfreefreefreefree1M131K
merge-gateway · zai$0.015$0.05$0.0031M131K
crof$0.07$0.22$0.011M131K
302ai$0.075$0.251M131K
empiriolabs$0.075$0.25$0.0751M131K
nano-gpt · z-ai$0.075$0.25$0.0151M131K
orcarouter · z-ai$0.075$0.251M128K
tokengo · z-ai$0.075$0.025$0.0151M131K
zai$0.075$0.25$0.015free1M131K
llmgateway$0.088$0.25$0.0251M131K
llmgateway-providers · scx-ai-gp$0.088$0.25$0.0251M131K
cortecs$0.10$0.35$0.0181M1M
llmgateway-providers · consensusprotocol$0.10$0.25$0.021M131K
runinfra · zai-org$0.10$0.40$0.011M33K
aihubmix$0.1127$0.3944$0.02821M128K
melious$0.1159$0.4637$0.02321M131K
bothub$0.12$0.441M131K
vancine$0.12$0.40$0.0241M131K
greenpt$0.1278$0.511$0.02561M131K
baseten · zai-org$0.15$0.501M131K
cline-pass · cline-pass$0.15$0.50$0.031M131K
cloudflare-workers-ai · cf$0.15$0.50$0.031.3M1M
crossmodel · z-ai$0.15$0.50$0.03$0.151M128K
databricks$0.15$0.50$0.03$0.151M131K
deepinfra · zai-org$0.15$0.50$0.031M131K
digitalocean$0.15$0.50$0.031M1M
edenai · zai$0.15$0.50$0.031M131K
fireworks_ai$0.15$0.50$0.031M
fireworks-ai · accounts$0.15$0.50$0.031M131K
friendli · zai-org$0.15$0.50$0.031M131K
friendliai · friendliai$0.15$0.50$0.031M1M
huggingface · zai-org$0.15$0.501M131K
kilo · z-ai$0.15$0.50$0.031M131K
llmgateway-providers$0.15$0.50$0.031M131K
llmgateway-providers · runware$0.15$0.50$0.031M131K
llmgateway-providers · vichar-ai$0.15$0.50$0.031M128K
llmgateway-providers · zai$0.15$0.50$0.031M131K
nano-gpt · tee$0.15$0.50$0.031M131K
nebius$0.15$0.501M1M
nebius · zai-org$0.15$0.50$0.151M1M
neon$0.15$0.50$0.031M131K
ofox · z-ai$0.15$0.50$0.031M131K
ollama-cloud$0.15$0.50$0.031M131K
opencode$0.15$0.50$0.031M131K
opencode-go$0.15$0.50$0.031M131K
openrouter$0.15$0.50$0.031.3M131K
openrouter · z-ai$0.15$0.50$0.031.3M131K
perplexity$0.15$0.50$0.03
together_ai$0.15$0.50$0.031M128K
togetherai · zai-org$0.15$0.50$0.031M400K
vercel · zai$0.15$0.50$0.031M131K
vivgrid$0.15$0.50$0.041M131K
wandb · zai-org$0.15$0.50$0.051M1M
zai · zai$0.15$0.50$0.03free1M128K
hyper$0.1633$0.5444$0.03161M131K
above$0.165$0.55$0.03191M131K
requesty$0.20$0.60$0.071M262K
berget · zai-org$0.29$0.58524K16K
tinfoil$0.40$1.25$0.101M131K
modal · zai-org$0.45$1.50$0.091M131K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02cortecsCache read$0.05
2026-09-12cortecsCache read$0.018
2026-09-02crossmodel · z-aiCache read$0.015
2026-09-10crossmodel · z-aiCache read$0.03
2026-09-02fireworks-ai · accountsCache read$0.029
2026-09-02fireworks-ai · accountsCache read$0.03
2026-09-02llmgatewayCache read$0.024
2026-09-05llmgatewayCache read$0.015
2026-09-06llmgatewayCache read$0.02
2026-09-10llmgatewayCache read$0.025
2026-09-02llmgateway-providers · scx-ai-gpCache read$0.024
2026-09-10llmgateway-providers · scx-ai-gpCache read$0.025
2026-09-02merge-gateway · zaiCache read$0.003
2026-09-05merge-gateway · zaiCache read$0.015
2026-09-06merge-gateway · zaiCache read$0.003
2026-09-02ofox · z-aiCache read$0.015
2026-09-11ofox · z-aiCache read$0.03
2026-09-02opencode-goCache read$0.015
2026-09-10opencode-goCache read$0.03
2026-09-02openrouter · z-aiCache read$0.015
2026-09-10openrouter · z-aiCache read$0.014
2026-09-11openrouter · z-aiCache read$0.03
2026-09-02requestyCache read$0.015
2026-09-03requestyCache read$0.07
2026-09-02vancineCache read$0.012
2026-09-15vancineCache read$0.024
2026-09-02crossmodel · z-aiCache write$0.075
2026-09-10crossmodel · z-aiCache write$0.15
2026-09-02cortecsInput$0.201
2026-09-12cortecsInput$0.10
2026-09-02crossmodel · z-aiInput$0.075
2026-09-10crossmodel · z-aiInput$0.15
2026-09-02llmgatewayInput$0.13
2026-09-05llmgatewayInput$0.075
2026-09-06llmgatewayInput$0.10
2026-09-10llmgatewayInput$0.088
2026-09-02llmgateway-providers · scx-ai-gpInput$0.13
2026-09-10llmgateway-providers · scx-ai-gpInput$0.088
2026-09-02merge-gateway · zaiInput$0.015
2026-09-05merge-gateway · zaiInput$0.075
2026-09-06merge-gateway · zaiInput$0.015
2026-09-02ofox · z-aiInput$0.075
2026-09-11ofox · z-aiInput$0.15
2026-09-02opencode-goInput$0.075
2026-09-10opencode-goInput$0.15
2026-09-02openrouter · z-aiInput$0.075
2026-09-10openrouter · z-aiInput$0.07
2026-09-11openrouter · z-aiInput$0.15
2026-09-02requestyInput$0.075
2026-09-03requestyInput$0.20
2026-09-02vancineInput$0.06
2026-09-15vancineInput$0.12
2026-09-02cortecsOutput$0.50
2026-09-12cortecsOutput$0.35
2026-09-02crossmodel · z-aiOutput$0.25
2026-09-10crossmodel · z-aiOutput$0.50
2026-09-02llmgatewayOutput$0.40
2026-09-05llmgatewayOutput$0.25
2026-09-02llmgateway-providers · scx-ai-gpOutput$0.40
2026-09-10llmgateway-providers · scx-ai-gpOutput$0.25
2026-09-02merge-gateway · zaiOutput$0.05
2026-09-05merge-gateway · zaiOutput$0.25
2026-09-06merge-gateway · zaiOutput$0.05
2026-09-02ofox · z-aiOutput$0.25
2026-09-11ofox · z-aiOutput$0.50
2026-09-02opencode-goOutput$0.25
2026-09-10opencode-goOutput$0.50
2026-09-02openrouter · z-aiOutput$0.25
2026-09-10openrouter · z-aiOutput$0.2333
2026-09-11openrouter · z-aiOutput$0.50
2026-09-02requestyOutput$0.25
2026-09-03requestyOutput$0.50
2026-09-09requestyOutput$0.60
2026-09-02vancineOutput$0.20
2026-09-15vancineOutput$0.40
2026-09-05llmgateway-providersCache read$0.015
2026-09-06llmgateway-providersCache read$0.03
2026-09-05llmgateway-providersInput$0.075
2026-09-06llmgateway-providersInput$0.15
2026-09-05llmgateway-providersOutput$0.25
2026-09-06llmgateway-providersOutput$0.50
2026-09-06openrouterCache read$0.015
2026-09-13openrouterCache read$0.03
2026-09-06openrouterInput$0.075
2026-09-13openrouterInput$0.15
2026-09-06openrouterOutput$0.25
2026-09-13openrouterOutput$0.50

Other listings of this model

same model, different key

More from Zhipu

most-hosted first