Skip to content

Sference

Pricing page

16 listings across 8 models

Data policies

from the provider's published policies

Headquarters: GBPrivacy policyTerms of service

On training

Sference shall not use Customer Content (including Customer Personal Data) to train, retrain, or improve any machine learning model of Sference or of any third party, except: (a) where and to the extent expressly instructed or agreed by Customer in writing (for example, a fine-tuning job submitted by Customer for Customer's own model, or a training arrangement specifically agreed in respect of paid Services); or (b) in respect of Services expressly designated by Sference as free of charge, where and to the extent the applicable service terms disclose such use and Customer elects to use those Services.

Possible sources (2)
On keeping your data

Inference inputs and outputs are not retained longer than operationally necessary as described in Annex 1.

Possible sources (2)
On where data is processed

Sference Processes Customer Content on inference and storage infrastructure located within the EEA, as described in Annex 2.

Source: Sference data-processing addendum

More from Sference on where data is processed (1)

Inference and storage of customer content run on infrastructure located within the EEA; ancillary vendors (analytics, monitoring, email, payments, status notifications, productivity tools) never receive inference content.

Possible sources (2)
Other statements

Operating entity: Neural Compute Ltd (trading as Sference), company number 17195150, registered office 167-169 Great Portland Street, 5th Floor, London, England, W1W 5PF.

Possible sources (2)

We take these statements from Sference's own published policies each time we refresh the data, so they can change or disappear when those pages do. Check with the provider before you rely on any of this.

Sold by Sference

8 listings sold by Sference.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
$0.35cache read $0.03$1.321M
GLM 5.3
$1.20cache read $0.26$4.201M
$0.35cache read $0.03$1.321M
GLM 5.2
$1.20cache read $0.26$4.201M
$0.20cache read $0.07$0.601M
DeepSeek V4 Flash 0731
$0.28cache read $0.07$0.561M
DeepSeek V4 Flash
$0.28cache read $0.07$0.561M
Clef 27BCloudflare/clef
Doesn’t apply to this modelDoesn’t apply to this model$0.24Doesn’t apply to this model66KDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model

Run by Sference

8 listings where Sference runs the model. Another provider sells these listings.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
 Cortecs AI——1M
GLM 5.3
 Cortecs AI——1M
GLM 5.2
 Requesty$1.20cache read $0.26$4.201M
 Cortecs AI——1M
DeepSeek V4 Flash 0731
 Cortecs AI——1M
Show all 8 listings

Showing 5 of 8: one listing for each model.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

Around the web

  • Activity | sference
    sference API Reference ## Path Parameters request\_id\string Format`uuid` ## Response Body `application/json` `application/json` ``` curl …sference API Reference ## Path Parameters request\_id\string Format`uuid` ## Response Body `application/json` `application/json` ``` curl -X GET " ``` [...] ``` {{ "status_code": 400, "status_code": …

    sference.com

    Docs
  • GitHub - s-ference/sference: Inference SDK & CLI for efficient ai pipelines and background agents · GitHub
    ## Repository files navigation # sference Python SDK and CLI for the sference batch inference …## Repository files navigation # sference Python SDK and CLI for the sference batch inference API. ## Coding agents (Cursor, Claude Code, …) 1. Paste PROMPT.txt into your project rules or `CLAUDE.md`…

    github.com

    Repository
  • sference

    AI inference for async pipelines. sference has 4 repositories available. Follow their code on GitHub.

    github.com

    Repository
  • sference
    # sference ID: 0mPXCeFUL35A Website: www.sference.com Headquarters: London, United Kingdom LinkedIn: www.linkedin.com/company/sference · 482 followers …# sference ID: 0mPXCeFUL35A Website: www.sference.com Headquarters: London, United Kingdom LinkedIn: www.linkedin.com/company/sference · 482 followers Industry: Technology, Information and Internet C…

    tavily.com

  • sference - Products, Competitors, Financials, Employees, Headquarters Locations
    ## About sference Sference is a managed inference platform that focuses on open-weight models, fine-tunes, …## About sference Sference is a managed inference platform that focuses on open-weight models, fine-tunes, and distilled models within the artificial intelligence domain. The company's offerings incl…

    cbinsights.com

  • Sference AI search visibility, competitors, reviews, and pricing | DevTune
    Sference is a managed inference platform for open-weight models, fine-tunes and distilled models, run on …Sference is a managed inference platform for open-weight models, fine-tunes and distilled models, run on European GPUs and offered through one OpenAI-compatible API. It supports several scheduling la…

    devtune.ai

  • sference API: Open Models on European Compute | Eden AI
    ## What is sference? sference is a managed inference platform for open models, running on …## What is sference? sference is a managed inference platform for open models, running on European compute. It serves frontier open-weight models through an OpenAI-compatible API, with zero data rete…

    edenai.co

  • Sference (company) - Nordic9.com
    # Sference (private company) United Kingdom sference.com See something wrong or missing? Let us know …# Sference (private company) United Kingdom sference.com See something wrong or missing? Let us know Offices:London Industry: AI Software Services Business model: B2B SAAS Sference is a British softw…

    nordic9.com

  • Sference | Enterprise Software | F4
    Sference · Enterprise Software · F4 Company OverviewBacked BySimilar CompaniesStartup DNA # Sference Sference is …Sference · Enterprise Software · F4 Company OverviewBacked BySimilar CompaniesStartup DNA # Sference Sference is a managed inference platform for open models that allows users to run open-weight mode…

    f4.fund

  • sference
    # sference Description: AI inference for async pipelines. LinkedIn: · 440 followers Industry: Technology, Information …# sference Description: AI inference for async pipelines. LinkedIn: · 440 followers Industry: Technology, Information and Internet Type: Privately Held Headquarters: London, United Kingdom ## Employe…

    uk.linkedin.com

How this data works