GLM 5.3 Flash

z-ai/glm-5.3-flash

context: 1.05M
modalities: text, image, video → text
capabilities: Tool use, Reasoning, Vision, Structured output, Long context, Low cost

Overview

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

Providers

AtlasCloudView AtlasCloud
BaseTenView BaseTen
CloudflareView Cloudflare
CohereView Cohere
CoreWeaveView CoreWeave
CrusoeView Crusoe
DarkbloomView Darkbloom
DecartView Decart
DeepInfraView DeepInfra
DekaLLMView DekaLLM
DigitalOceanView DigitalOcean
FireworksView Fireworks
FriendliView Friendli
GMICloudView GMICloud
InceptronView Inceptron
InferenceNetView InferenceNet
Io NetView Io Net
MakoraView Makora
MistralView Mistral
ModalView Modal
MorphView Morph
Near AIView Near AI
NebiusView Nebius
NextBitView NextBit
NovitaView Novita
OpenInferenceView OpenInference
ParasailView Parasail
Particle AIView Particle AI
PhalaView Phala
PrimeIntellectView PrimeIntellect
RekaView Reka
RelaceView Relace
Sail ResearchView Sail Research
SiliconFlowView SiliconFlow
StreamLakeView StreamLake
TogetherView Together
VeniceView Venice
WaferView Wafer
Z.AIView Z.AI

Access method depends on provider and account setup.

Pricing

Price per 1M tokens by provider
provider	input / 1M	output / 1M
AtlasCloud	$0.15	$0.50
BaseTenbaseten/fp8 · fp8	$0.15	$0.50
BaseTenbaseten/fp8/us · fp8	$0.15	$0.50
Cloudflare	$0.30	$1.00
Cohere	$0.15	$0.50
CoreWeave	$0.12	$0.38
Crusoe	$0.15	$0.50
Darkbloom	$0.065	$0.18
Decart	$0.0825	$0.275
DeepInfra	$0.15	$0.50
DekaLLM	$0.10	$1.00
DigitalOcean	$0.1125	$0.375
Fireworksfireworks	$0.15	$0.50
Fireworksfireworks/us	$0.225	$0.75
Friendli	$0.15	$0.50
GMICloud	$0.075	$0.25
Inceptron	$0.19	$0.60
InferenceNetinference-net/fp4 · fp4	$0.108	$0.35
InferenceNetinference-net/us · fp4	$0.108	$0.35
Io Net	$0.1125	$0.375
Makora	$0.14	$0.24
Mistral	$0.15	$0.50
Modalmodal/fp4 · fp4	$0.15	$0.50
Modalmodal/fp8 · fp8	$0.45	$1.50
Modalmodal/nvfp4 · nvfp4	$0.15	$0.50
Morphmorph	$0.098	$0.343
Morphmorph/fp8 · fp8	$0.042	$0.30
Near AI	$0.08	$0.50
Nebius	$0.15	$0.50
NextBitnextbit/fp4 · fp4	$0.11	$0.45
NextBitnextbit/fp8 · fp8	$0.165	$0.55
Novita	$0.084	$0.28
OpenInference	$0.03	$0.16
Parasailparasail/fast · fp4	$0.1875	$0.625
Parasailparasail/fp4 · fp4	$0.15	$0.50
Parasailparasail/fp8 · fp8	$0.15	$0.50
Particle AI	$0.10	$0.50
Phalaphala/fp8 · fp8	$0.1125	$0.375
Phalaphala/nvfp4 · nvfp4	$0.1125	$0.375
PrimeIntellect	$0.15	$0.50
Rekareka	$0.12	$0.30
Rekareka/fp8 · fp8	$0.15	$0.50
Relacerelace	$0.0457	$0.0701
Relacerelace/fp4 · fp4	$0.0285	$0.0923
Sail Researchsail-research/fp4 · fp4	$0.35	$1.25
Sail Researchsail-research/fp8 · fp8	$0.045	$0.60
Sail Researchsail-research/us · fp4	$0.225	$0.75
SiliconFlow	$0.15	$0.50
StreamLake	$0.0885	$0.295
Together	$0.15	$0.50
Venice	$0.15	$0.50
Waferwafer	$0.12	$0.50
Waferwafer/nvfp4 · nvfp4	$0.054	$0.20
Waferwafer/us · nvfp4	$0.044	$0.20
Z.AI	$0.15	$0.50

AtlasCloud
input / 1M
$0.15
output / 1M
$0.50
BaseTen
baseten/fp8 · fp8
input / 1M
$0.15
output / 1M
$0.50
BaseTen
baseten/fp8/us · fp8
input / 1M
$0.15
output / 1M
$0.50
Cloudflare
input / 1M
$0.30
output / 1M
$1.00
Cohere
input / 1M
$0.15
output / 1M
$0.50
CoreWeave
input / 1M
$0.12
output / 1M
$0.38
Crusoe
input / 1M
$0.15
output / 1M
$0.50
Darkbloom
input / 1M
$0.065
output / 1M
$0.18
Decart
input / 1M
$0.0825
output / 1M
$0.275
DeepInfra
input / 1M
$0.15
output / 1M
$0.50
DekaLLM
input / 1M
$0.10
output / 1M
$1.00
DigitalOcean
input / 1M
$0.1125
output / 1M
$0.375
Fireworks
fireworks
input / 1M
$0.15
output / 1M
$0.50
Fireworks
fireworks/us
input / 1M
$0.225
output / 1M
$0.75
Friendli
input / 1M
$0.15
output / 1M
$0.50
GMICloud
input / 1M
$0.075
output / 1M
$0.25
Inceptron
input / 1M
$0.19
output / 1M
$0.60
InferenceNet
inference-net/fp4 · fp4
input / 1M
$0.108
output / 1M
$0.35
InferenceNet
inference-net/us · fp4
input / 1M
$0.108
output / 1M
$0.35
Io Net
input / 1M
$0.1125
output / 1M
$0.375
Makora
input / 1M
$0.14
output / 1M
$0.24
Mistral
input / 1M
$0.15
output / 1M
$0.50
Modal
modal/fp4 · fp4
input / 1M
$0.15
output / 1M
$0.50
Modal
modal/fp8 · fp8
input / 1M
$0.45
output / 1M
$1.50
Modal
modal/nvfp4 · nvfp4
input / 1M
$0.15
output / 1M
$0.50
Morph
morph
input / 1M
$0.098
output / 1M
$0.343
Morph
morph/fp8 · fp8
input / 1M
$0.042
output / 1M
$0.30
Near AI
input / 1M
$0.08
output / 1M
$0.50
Nebius
input / 1M
$0.15
output / 1M
$0.50
NextBit
nextbit/fp4 · fp4
input / 1M
$0.11
output / 1M
$0.45
NextBit
nextbit/fp8 · fp8
input / 1M
$0.165
output / 1M
$0.55
Novita
input / 1M
$0.084
output / 1M
$0.28
OpenInference
input / 1M
$0.03
output / 1M
$0.16
Parasail
parasail/fast · fp4
input / 1M
$0.1875
output / 1M
$0.625
Parasail
parasail/fp4 · fp4
input / 1M
$0.15
output / 1M
$0.50
Parasail
parasail/fp8 · fp8
input / 1M
$0.15
output / 1M
$0.50
Particle AI
input / 1M
$0.10
output / 1M
$0.50
Phala
phala/fp8 · fp8
input / 1M
$0.1125
output / 1M
$0.375
Phala
phala/nvfp4 · nvfp4
input / 1M
$0.1125
output / 1M
$0.375
PrimeIntellect
input / 1M
$0.15
output / 1M
$0.50
Reka
reka
input / 1M
$0.12
output / 1M
$0.30
Reka
reka/fp8 · fp8
input / 1M
$0.15
output / 1M
$0.50
Relace
relace
input / 1M
$0.0457
output / 1M
$0.0701
Relace
relace/fp4 · fp4
input / 1M
$0.0285
output / 1M
$0.0923
Sail Research
sail-research/fp4 · fp4
input / 1M
$0.35
output / 1M
$1.25
Sail Research
sail-research/fp8 · fp8
input / 1M
$0.045
output / 1M
$0.60
Sail Research
sail-research/us · fp4
input / 1M
$0.225
output / 1M
$0.75
SiliconFlow
input / 1M
$0.15
output / 1M
$0.50
StreamLake
input / 1M
$0.0885
output / 1M
$0.295
Together
input / 1M
$0.15
output / 1M
$0.50
Venice
input / 1M
$0.15
output / 1M
$0.50
Wafer
wafer
input / 1M
$0.12
output / 1M
$0.50
Wafer
wafer/nvfp4 · nvfp4
input / 1M
$0.054
output / 1M
$0.20
Wafer
wafer/us · nvfp4
input / 1M
$0.044
output / 1M
$0.20
Z.AI
input / 1M
$0.15
output / 1M
$0.50

Use this model
through Nautili

Route requests to GLM 5.3 Flash through your Nautili gateway using a supported SDK or the Nautili SDK.

View integrations Read the docs

Connect your stack to Nautili

Route across supported providers through one control layer.

Start for Free Read the docs

Overview

Providers

Pricing

Use this model through Nautili

Connect your stack to Nautili

Use this model
through Nautili