142 open models, one API

Pick a job, then compare its open models on public benchmarks and Serverless price.

Chat, structured output and reading images 10 models

Chat Coding agents Structured output Image questions Doc field extraction Screenshot mining

Qwen3.8 27B

Qwen/Qwen3.8-27B-FP8

98.9%

Rules kept when customers push · 275 pushes

0.74 s

Time per complete reply

$135

Cost per 100,000 conversations

See the comparison on Chat
GLM-5.3-Flash

zai-org/GLM-5.3-Flash

91.6%

Tool calls right · 600 calls

$0.0634

Cost per 1,000 tool calls

See the comparison on Coding agents
Gemma 4 31B

google/gemma-4-31B-it

94.3%

Exact field values · 546 documents

$2.12

Cost per 1,000 documents

See the comparison on Doc field extraction

Chat, structured output and reading images
Model	MMLU-Pro, answers right	Time per request	Serverless price	Size
Qwen3.8 27B Qwen	Not measured	0.74 s per complete reply	$0.25 in · $2.75 out per 1M tokens	27.8B
GLM-5.3-Flash zai-org	Not measured	Not timed	$0.15 in · $0.50 out per 1M tokens	321.3B
Gemma 4 31B google	Not measured	Not timed	$0.45 in · $1.50 out per 1M tokens	31.3B
Qwen3.5 4B Qwen	59.3%	Not timed	$0.305 in · $1.53 out per 1M tokens	4.7B
Qwen3 4B Instruct 2507 Qwen	53.3%	Not timed	Run in your cloud	4.0B
Qwen3 0.6B Qwen	23.7%	Not timed	Run in your cloud	752M

4 more models served

Chat, structured output and reading images: 4 more models served
Model	MMLU-Pro, answers right	Time per request	Serverless price	Size
donut base finetuned cord v2 naver-clova-ix	Not measured	Not timed	Run in your cloud	110M
donut base finetuned docvqa naver-clova-ix	Not measured	Not timed	Run in your cloud	110M
Florence 2 FT DocVQA mynkchaudhry	Not measured	Not timed	Run in your cloud	271M
Qwen3.6 27B Qwen	Not measured	Not timed	Run in your cloud	27.8B

Translation 2 models

Translation

Hy-MT2 1.8B

tencent/Hy-MT2-1.8B

48.1

Match with the human translation · 1,488 segments

$3.15

Cost per 1M characters

See the comparison on Translation

Translation
Model	WMT24++, 1,488 segments, chrF++	Time per request	Serverless price	Size
Hy-MT2 1.8B tencent	48.1	Not timed	$1.13 in · $5.63 out per 1M tokens	2.0B
MADLAD-400 3B google	44.6	Not timed	$0.999 in · $5.00 out per 1M tokens	2.9B

Classify text and yes/no decisions 11 models

Classify text Yes/no decisions

GLiNER2.5 Decide

fastino/GLiNER2.5-Decide

87.5%

Labelled correctly · 400 messages

13.1 ms

Time per message

$0.0035

Cost per 1,000 messages

See the comparison on Classify text
DeBERTa v3 large zero-shot v2.0

MoritzLaurer/deberta-v3-large-zeroshot-v2.0

90.70%

Decided correctly · 1,560 comments

13.8 ms

Time per decision

$0.0084

Cost per 1,000 decisions

See the comparison on Yes/no decisions

Classify text and yes/no decisions
Model	AG News, labelled correctly	Time per request	Serverless price	Size
GLiNER2.5 Decide fastino	Not measured	13.1 ms per message	$0.28 per 1M tokens	486M
DeBERTa v3 large zero-shot v2.0 MoritzLaurer	88.6%	13.8 ms per decision	$0.129 per 1M tokens	435M
deberta v3 base zeroshot v2.0 MoritzLaurer	88.1%	Not timed	Run in your cloud	184M
ModernBERT base zeroshot v2.0 MoritzLaurer	84.3%	Not timed	Run in your cloud	150M
gliclass instruct large v1.0 knowledgator	76.9%	Not timed	$0.19 per 1M tokens	439M
gliclass large v1.0 knowledgator	76.3%	Not timed	Run in your cloud	438M
gliclass large v3.0 knowledgator	74.3%	Not timed	Run in your cloud	439M
gliclass small v1.0 knowledgator	72.8%	Not timed	Run in your cloud	144M

Show 3 more models Show fewer models

Classify text and yes/no decisions: 3 more models
Model	AG News, labelled correctly	Time per request	Serverless price	Size
gliclass base v1.0 knowledgator	71.9%	Not timed	Run in your cloud	186M
bart large mnli facebook	67.1%	Not timed	Run in your cloud	407M
nli deberta v3 base cross-encoder	65.0%	Not timed	Run in your cloud	184M

Doc to Markdown and OCR 6 models

Doc to Markdown OCR

LightOnOCR-3

lightonai/LightOnOCR-3-4B

73.2%

Document checks passed · 8,234 checks

$2.05

Cost per 1,000 pages

See the comparison on Doc to Markdown
GLM-OCR

zai-org/GLM-OCR

71.0%

Photos read correctly · 372 photos

$0.25

Cost per 1,000 photos

See the comparison on OCR

Doc to Markdown and OCR
Model	olmOCR-Bench, checks passed	Time per request	Serverless price	Size
LightOnOCR-3 lightonai	Not measured	Not timed	$0.14 in · $1.37 out per 1M tokens	4.5B
GLM-OCR zai-org	73.8%	Not timed	$0.25 per 1,000 images	1.3B
LightOnOCR 2 1B lightonai	77.7%	Not timed	$2.00 per 1,000 pages	1.0B
MinerU2.5 Pro 2604 1.2B opendatalab	59.1%	Not timed	Run in your cloud	1.2B
PaddleOCR VL 1.5 PaddlePaddle	51.7%	Not timed	Run in your cloud	959M
docling	31.7%	Not timed	$0.398 per 1,000 pages	80M

Speech to text 2 models

Speech to text

Parakeet TDT 0.6B v3

nvidia/parakeet-tdt-0.6b-v3

$45

Cost per 1,000 audio hours

See the comparison on Speech to text

Speech to text
Model	LibriSpeech, 256 clean clips, word error rate	Time per request	Serverless price	Size
Parakeet TDT 0.6B v3 nvidia	Not measured	Not timed	$0.00075 per audio minute	627M
whisper large v3 turbo openai	1.7%	Not timed	$0.00276 per audio minute	809M

Detect 8 models

Detect

SAM 3

facebook/sam3

0.62

Objects boxed correctly

82.2 ms

Time per photo

$0.25

Cost per 1,000 photos

See the comparison on Detect

Detect
Model	COCO, average precision	Time per request	Serverless price	Size
SAM 3 facebook	Not measured	82.2 ms per photo	$0.25 per 1,000 images	860M
grounding dino base IDEA-Research	0.486	Not timed	$0.31 per 1,000 images	233M
owlv2 base patch16 ensemble google	0.434	Not timed	$0.233 per 1,000 images	155M
owlv2 large patch14 ensemble google	0.428	Not timed	Run in your cloud	438M
grounding dino tiny IDEA-Research	0.403	Not timed	Run in your cloud	172M
Florence 2 base ft microsoft	0.295	Not timed	Run in your cloud	232M
Florence 2 large microsoft	0.294	Not timed	Run in your cloud	777M
Florence 2 base microsoft	0.279	Not timed	Run in your cloud	232M

Image search and image classify 10 models

Image search Image classify

SigLIP so400m

google/siglip-so400m-patch14-384

83.1%

Right product first · 309 searches

$24

Cost per 1M photos

See the comparison on Image search

Image search and image classify
Model	Flickr30k image to text, nDCG@10	Time per request	Serverless price	Size
SigLIP so400m google	0.900	Not timed	$0.031 per 1M tokens $0.0233 per 1,000 images	878M
CLIP ViT H 14 laion2B s32B b79K laion	0.862	Not timed	Run in your cloud	986M
marqo fashionSigLIP Marqo	0.838	Not timed	Run in your cloud	203M
siglip so400m patch14 224 google	0.838	Not timed	Run in your cloud	877M
siglip2 base patch16 224 google	0.816	Not timed	$0.0231 per 1M tokens $0.0143 per 1,000 images	375M
clip vit large patch14 openai	0.782	Not timed	Run in your cloud	428M
CLIP ViT B 32 laion2B s34B b79K laion	0.774	Not timed	Run in your cloud	151M
clip vit base patch32 openai	0.716	Not timed	Run in your cloud	151M

Show 1 more model Show fewer models

Image search and image classify: 1 more model
Model	Flickr30k image to text, nDCG@10	Time per request	Serverless price	Size
marqo ecommerce embeddings B Marqo	0.608	Not timed	Run in your cloud	203M

1 more model served

Image search and image classify: 1 more model served
Model	Flickr30k image to text, nDCG@10	Time per request	Serverless price	Size
Qwen3 VL Embedding 2B Qwen	Not measured	Not timed	Run in your cloud	2.1B

Guardrails 3 models

Guardrails

Qwen3Guard 4B

Qwen/Qwen3Guard-Gen-4B

82.7%

Harmful caught, safe let through

$24.39

Cost per 1M checks

See the comparison on Guardrails

Guardrails
Model	ToxicChat, F1	Time per request	Serverless price	Size
Qwen3Guard 4B Qwen	Not measured	Not timed	$0.05 in · $0.75 out per 1M tokens	4.4B
gliguard LLMGuardrails 300M fastino	0.576	Not timed	$0.0929 per 1M tokens	208M
granite guardian 3.0 2b ibm-granite	0.247	Not timed	$0.15 in · $0.60 out per 1M tokens	2.5B

Redact (PII) 3 models

Redact (PII)

GLiNER PII and NuNER Zero

superlinked/pii-redact

90.9%

Personal data masked · 660 documents

61 ms

Time per document

$73

Cost per 1M documents

See the comparison on Redact (PII)

Redact (PII)
Model	SPIA, F1	Time per request	Serverless price	Size
GLiNER PII and NuNER Zero superlinked	Not measured	61 ms per document	$0.08 per 1M tokens	Not listed
NuNER Zero numind	0.463	Not timed	$0.05 per 1M tokens	449M
gliner multi pii v1 urchade	0.377	Not timed	$0.04 per 1M tokens	289M

Knowledge graph 4 models

Knowledge graph

GLiNER relex Large

knowledgator/gliner-relex-large-v1.0

110

Relations right · Claude Sonnet 5.5 = 100

$48

Cost per 1M articles

See the comparison on Knowledge graph

Knowledge graph
Model	FewRel, F1	Time per request	Serverless price	Size
GLiNER relex Large knowledgator	Not measured	Not timed	$0.22 per 1M tokens	467M
gliner2 large v1 fastino	0.435	Not timed	$0.186 per 1M tokens	486M
gliner2 base v1 fastino	0.400	Not timed	$0.0929 per 1M tokens	208M
glirel large v0 jackboyla	0.264	Not timed	Run in your cloud	467M

Search 34 models

Qwen3 Embedding 4B

Qwen/Qwen3-Embedding-4B

54.6%

Right result first · 8 public benchmarks

$0.06

Price per 1M tokens

See the comparison on Search

Search
Model	8 retrieval sets, mean nDCG@10	Time per request	Serverless price	Size
Qwen3 Embedding 4B Qwen	0.599	Not timed	$0.06 per 1M tokens	4.0B
Qwen3 Embedding 8B Qwen	0.620	Not timed	Run in your cloud	7.6B
SFR Embedding 2 R Salesforce	0.586	Not timed	Run in your cloud	7.1B
stella en 1.5B v5 NovaSearch	0.583	Not timed	Run in your cloud	1.5B
Linq Embed Mistral Linq-AI-Research	0.576	Not timed	Run in your cloud	7.1B
gte Qwen2 1.5B instruct Alibaba-NLP	0.561	Not timed	Run in your cloud	1.8B
stella en 400M v5 NovaSearch	0.561	Not timed	Run in your cloud	435M
embeddinggemma 300m google	0.551	Not timed	Run in your cloud	303M

Show 10 more models Show fewer models

Search: 10 more models
Model	8 retrieval sets, mean nDCG@10	Time per request	Serverless price	Size
snowflake arctic embed l v2.0 Snowflake	0.532	Not timed	$0.0377 per 1M tokens	568M
Qwen3 VL Embedding 2B Qwen	0.524	Not timed	Run in your cloud	2.1B
mxbai embed large v1 mixedbread-ai	0.523	Not timed	Run in your cloud	335M
gte multilingual base Alibaba-NLP	0.520	Not timed	Run in your cloud	305M
snowflake arctic embed s Snowflake	0.499	Not timed	Run in your cloud	33M
nomic embed text v2 moe nomic-ai	0.486	Not timed	Run in your cloud	475M
all MiniLM L6 v2 sentence-transformers	0.481	Not timed	Run in your cloud	23M
bge m3 BAAI	0.470	Not timed	$0.0377 per 1M tokens	568M
multilingual e5 small intfloat	0.452	Not timed	Run in your cloud	118M
R3 embedding 0.6b tencent	Not measured	Not timed	$0.0531 per 1M tokens	596M

16 more models served

Search: 16 more models served
Model	8 retrieval sets, mean nDCG@10	Time per request	Serverless price	Size
e5 base v2 intfloat	Not measured	Not timed	Run in your cloud	109M
e5 large v2 intfloat	Not measured	Not timed	Run in your cloud	335M
e5 mistral 7b instruct intfloat	Not measured	Not timed	Run in your cloud	7.1B
e5 small v2 intfloat	Not measured	Not timed	Run in your cloud	33M
granite embedding 97m multilingual r2 ibm-granite	Not measured	Not timed	Run in your cloud	97M
granite embedding english r2 ibm-granite	Not measured	Not timed	Run in your cloud	149M
granite embedding small english r2 ibm-granite	Not measured	Not timed	Run in your cloud	48M
GritLM 7B GritLM	Not measured	Not timed	Run in your cloud	7.2B
gte modernbert base Alibaba-NLP	Not measured	Not timed	Run in your cloud	149M
gte Qwen2 7B instruct Alibaba-NLP	Not measured	Not timed	Run in your cloud	7.6B
modernbert embed base nomic-ai	Not measured	Not timed	Run in your cloud	149M
multilingual e5 large intfloat	Not measured	Not timed	Run in your cloud	560M
multilingual e5 large instruct intfloat	Not measured	Not timed	Run in your cloud	560M
Qwen3 Embedding 0.6B Qwen	Not measured	Not timed	Run in your cloud	596M
SFR Embedding Mistral Salesforce	Not measured	Not timed	Run in your cloud	7.1B
snowflake arctic embed m v2.0 Snowflake	Not measured	Not timed	Run in your cloud	305M

Rerank and request routing 22 models

Rerank Request routing

Qwen3 Reranker 4B

Qwen/Qwen3-Reranker-4B

91.2%

Right document first · 499 questions

55 ms

Time per query

$15

Cost per 100,000 queries

See the comparison on Rerank

Rerank and request routing
Model	AskUbuntu, nDCG@10	Time per request	Serverless price	Size
Qwen3 Reranker 4B Qwen	0.697	55 ms per query	$0.0425 per 1M tokens	4.0B
mxbai rerank large v2 mixedbread-ai	0.691	Not timed	Run in your cloud	1.5B
bge reranker v2 m3 BAAI	0.676	Not timed	Run in your cloud	568M
gte reranker modernbert base Alibaba-NLP	0.670	Not timed	Run in your cloud	150M
bge m3 BAAI	0.666	Not timed	$0.0743 per 1M tokens $3.72 per 1M pairs	568M
Qwen3 VL Reranker 2B Qwen	0.666	Not timed	$0.149 per 1,000 images $222.80 per 1M pairs	2.1B
mxbai rerank base v2 mixedbread-ai	0.664	Not timed	Run in your cloud	494M
mLateOn lightonai	0.663	Not timed	Run in your cloud	307M

Show 13 more models Show fewer models

Rerank and request routing: 13 more models
Model	AskUbuntu, nDCG@10	Time per request	Serverless price	Size
jina reranker v2 base multilingual jinaai	0.655	Not timed	Run in your cloud	278M
Qwen3 Reranker 0.6B Qwen	0.652	Not timed	$0.017 per 1M tokens	596M
bge reranker large BAAI	0.640	Not timed	Run in your cloud	560M
jina colbert v2 jinaai	0.639	Not timed	Run in your cloud	559M
Reason ModernColBERT lightonai	0.634	Not timed	Run in your cloud	149M
mxbai colbert large v1 mixedbread-ai	0.630	Not timed	Run in your cloud	335M
answerai colbert small v1 answerdotai	0.626	Not timed	Run in your cloud	33M
ms marco MiniLM L 12 v2 cross-encoder	0.614	Not timed	Run in your cloud	33M
ms marco MiniLM L 6 v2 cross-encoder	0.603	Not timed	Run in your cloud	23M
bge reranker base BAAI	0.593	Not timed	Run in your cloud	278M
colbertv2.0 colbert-ir	0.591	Not timed	Run in your cloud	110M
GTE ModernColBERT lightonai	Not measured	Not timed	$0.149 per 1M tokens $7.43 per 1M pairs	149M
R3 rerank 0.6b tencent	Not measured	Not timed	$0.017 per 1M tokens	596M

1 more model served

Rerank and request routing: 1 more model served
Model	AskUbuntu, nDCG@10	Time per request	Serverless price	Size
mxbai edge colbert v0 32m mixedbread-ai	Not measured	Not timed	Run in your cloud	32M

Multi-vector 9 models

Multi-vector

GTE ModernColBERT

lightonai/GTE-ModernColBERT-v1

269

Right article first · of 437 questions

$2.11

Index 11,802 articles

See the comparison on Multi-vector

Multi-vector
Model	8 retrieval sets, mean nDCG@10	Time per request	Serverless price	Size
GTE ModernColBERT lightonai	Not measured	Not timed	$0.0332 per 1M tokens	149M
mLateOn lightonai	0.561	Not timed	Run in your cloud	307M
Reason ModernColBERT lightonai	0.519	Not timed	Run in your cloud	149M
answerai colbert small v1 answerdotai	0.466	Not timed	Run in your cloud	33M
jina colbert v2 jinaai	0.462	Not timed	Run in your cloud	559M
bge m3 BAAI	Not measured	Not timed	$0.0499 per 1M tokens	568M

3 more models served

Multi-vector: 3 more models served
Model	8 retrieval sets, mean nDCG@10	Time per request	Serverless price	Size
colbertv2.0 colbert-ir	Not measured	Not timed	Run in your cloud	110M
mxbai colbert large v1 mixedbread-ai	Not measured	Not timed	Run in your cloud	335M
mxbai edge colbert v0 32m mixedbread-ai	Not measured	Not timed	Run in your cloud	32M

Sparse embeddings 12 models

Sparse embeddings

OpenSearch doc-v3-gte

opensearch-project/opensearch-neural-sparse-encoding-doc-v3-gte

119

Product ranking quality · BM25 = 100

$3.38

Model API cost to index · 482,105 products

See the comparison on Sparse embeddings

Sparse embeddings
Model	8 retrieval sets, mean nDCG@10	Time per request	Serverless price	Size
OpenSearch doc-v3-gte opensearch-project	Not measured	Not timed	$0.0292 per 1M tokens	137M
splade v3 naver	0.456	Not timed	Run in your cloud	110M
opensearch neural sparse encoding v1 opensearch-project	0.448	Not timed	Run in your cloud	133M
bge m3 BAAI	Not measured	Not timed	$0.0408 per 1M tokens	568M
Splade PP en v2 prithivida	Not measured	Not timed	$0.0256 per 1M tokens	110M

7 more models served

Sparse embeddings: 7 more models served
Model	8 retrieval sets, mean nDCG@10	Time per request	Serverless price	Size
granite embedding 30m sparse ibm-granite	Not measured	Not timed	Run in your cloud	30M
opensearch neural sparse encoding doc v2 distill opensearch-project	Not measured	Not timed	Run in your cloud	67M
opensearch neural sparse encoding doc v2 mini opensearch-project	Not measured	Not timed	Run in your cloud	23M
opensearch neural sparse encoding doc v3 distill opensearch-project	Not measured	Not timed	Run in your cloud	67M
opensearch neural sparse encoding v2 distill opensearch-project	Not measured	Not timed	Run in your cloud	67M
splade cocondenser selfdistil naver	Not measured	Not timed	Run in your cloud	110M
splade mini rasyosef	Not measured	Not timed	Run in your cloud	11M

Visual document search 6 models

Visual document search

Tomoro ColQwen3 4B

TomoroAI/tomoro-colqwen3-embed-4b

64.0

Answer-page ranking · of 100

$0.20

Cost per 1,000 pages

See the comparison on Visual document search

Visual document search
Model	3 ViDoRe v3 sets, mean nDCG@10	Time per request	Serverless price	Size
Tomoro ColQwen3 4B TomoroAI	Not measured	Not timed	$2.00 per 1M tokens $0.20 per 1,000 images	4.4B
nemotron colembed vl 4b v2 nvidia	0.720	Not timed	Run in your cloud	4.8B
v splade quality naver	0.527	Not timed	Run in your cloud	330M

3 more models served

Visual document search: 3 more models served
Model	3 ViDoRe v3 sets, mean nDCG@10	Time per request	Serverless price	Size
colpali v1.3 hf vidore	Not measured	Not timed	Run in your cloud	2.9B
colqwen2.5 v0.2 vidore	Not measured	Not timed	Run in your cloud	7.0B
llama nemoretriever colembed 3b v1 nvidia	Not measured	Not timed	Run in your cloud	4.4B

Named entities 16 models

Named entities

NuNER Zero-span

numind/NuNER_Zero-span

63.0%

Exact spans and types (F1) · 652 sentences

$1.38

Cost per 1M sentences

See the comparison on Named entities

Named entities
Model	CoNLL-2003, F1	Time per request	Serverless price	Size
NuNER Zero-span numind	0.645	Not timed	$0.05 per 1M tokens	449M
gliner small v2.5 gliner-community	0.669	Not timed	Run in your cloud	166M
modern gliner bi base v1.0 knowledgator	0.664	Not timed	Run in your cloud	Not listed
gliner medium v2.5 gliner-community	0.664	Not timed	Run in your cloud	209M
gliner large v2.5 gliner-community	0.655	Not timed	Run in your cloud	459M
gliner biomed large v1.0 Ihor	0.644	Not timed	$0.15 per 1M tokens	478M
gliner bi base v2.0 knowledgator	0.640	Not timed	Run in your cloud	Not listed
gliner medium v2.1 urchade	0.611	Not timed	Run in your cloud	195M

Show 8 more models Show fewer models

Named entities: 8 more models
Model	CoNLL-2003, F1	Time per request	Serverless price	Size
NuNER Zero numind	0.607	Not timed	$0.05 per 1M tokens	449M
gliner multi v2.1 urchade	0.602	Not timed	$0.0907 per 1M tokens	289M
gliner small v2.1 urchade	0.596	Not timed	Run in your cloud	153M
gliner large news v2.1 EmergentMethods	0.553	Not timed	Run in your cloud	445M
gliner large v2.1 urchade	0.548	Not timed	Run in your cloud	445M
gliner2 large v1 fastino	0.540	Not timed	$0.186 per 1M tokens	486M
gliner multi pii v1 urchade	0.538	Not timed	$0.04 per 1M tokens	289M
gliner2 base v1 fastino	0.519	Not timed	$0.0929 per 1M tokens	208M

Evaluation

Accuracy: Each model run on SIE against the public dataset named in its column
8 retrieval sets: The mean over NFCorpus, FiQA2018, SciFact, SCIDOCS, CQADupstackPhysicsRetrieval, CosQA, StackOverflowQA and LegalBenchConsumerContractsQA
3 ViDoRe v3 sets: The mean over Vidore3ComputerScienceRetrieval, Vidore3FinanceEnRetrieval and Vidore3PharmaceuticalsRetrieval
Time: SIE timed on a GPU server with the client alongside, one request at a time
Prices: Serverless list prices
Sources: Task page runs and their inputs

Run these models on Serverless or in your own cloud

SIE Serverless

We host the models; you call one API.

No idle GPUs, pay for what you use
Fits your stack: SDK, API, CLI, MCP
Self-host the same open-source engine
SOC 2 Type 2, US or EU data residency
Create an account to try Serverless

Get started

SIE Cluster

Kubernetes in your own cloud, backed by our engineers.

Terraform modules for your cloud
Apache-2.0, same engine as Serverless
GPU workers scale to zero between jobs
Separate worker pools for each tenant

Agent prompt Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deployment.

Deploy SIE to our Google Cloud project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deployment.

Deploy SIE to our Azure subscription with the superlinked/sie/azure Terraform module. Docs: superlinked.com/docs/deployment.

Deploy SIE to our Alibaba Cloud account with the superlinked/sie/alicloud Terraform module. Docs: superlinked.com/docs/deployment.

Talk to us Deploy guide

SIE Local

The open-source server on your own machine.

Runs on your NVIDIA GPU
One container, no cluster
Process your data fully offline
Same SDK and model IDs as Serverless

docker run --gpus all -p 8080:8080 ghcr.io/superlinked/sie-server:latest-cuda12-default

Quickstart