Skip to content

47 listings across 32 models

Page 1 of 2. The lists below split this page's listings into those sold by Flexai, run by Flexai, or sent to Flexai by a marketplace.

Sold by Flexai

33 listings on this page sold by Flexai.

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
DeepSeek V4.1 Flash 1017🇪🇺 eu
$0.08cache read $0.0055$0.6051M
Qwen 3.8 Flash Next🇪🇺 eu
$0.15cache read $0.0225$0.47262KNot enough data yetNot measuredNot measured
MiniMax M3.1 Flash🇪🇺 eu
$0.15cache read $0.015$0.601MNot measuredNot measured
MiMo V2.6 FlashMiMo-V2.6-Flash-RL · 🇪🇺 eu
$0.14cache read $0.0037$0.281MNot measured
GLM 5.2🇪🇺 eu
$0.60cache read $0.09$2.001M
GLM 5.3 Flash🇪🇺 eu
$0.088cache read $0.0132$0.251M
DeepSeek V4 Flash 0731🇪🇺 eu
$0.13cache read $0.0195$0.261M
Qwen 3.8 27B🇪🇺 eu
$0.20cache read $0.03$2.50262KNot measured
Gemma 4 31B IT🇪🇺 eu
$0.14cache read $0.021$0.40262K
Muse Glimmer 30B🇪🇺 eu
Not enough data yet$0.35cache read $0.04$1.50131KNot measuredNot measured
Gemma 4 26B A4Bgemma-4-26B-A4B-it · 🇪🇺 eu
$0.067cache read $0.01$0.29262K
Qwen3.6 27BQwen3.6-27B-FP8 · fp8 · 🇪🇺 eu
$0.25$2.00262KNot measured
Qwen3.6 35B A3BQwen3.6-35B-A3B-FP8 · fp8 · 🇪🇺 eu
$0.10$0.95262KNot measured
GPT OSS 120B🇪🇺 eu
$0.03cache read $0.0045$0.15131K
GLM 4.5 AirGLM-4.5-Air-FP8 · fp8 · 🇪🇺 eu
$0.14$0.86131KNot measuredNot measured
Qwen3 Coder 30B A3B InstructQwen3-Coder-30B-A3B-Instruct-FP8 · fp8 · 🇪🇺 eu
Not enough data yet$0.07$0.28262KNot measuredNot measured
Nemotron 3.5 Lightning 30B A3BNVIDIA-Nemotron-3.5-Lightning-30B-A3B · 🇪🇺 eu
$0.06cache read $0.009$0.161MNot measuredNot measured
Qwen3 30B A3BQwen3-30B-A3B-Thinking-2507-FP8 · thinking+fp8+2507 · fp8 · 🇪🇺 eu
$0.20$2.40262KNot measured
Qwen3.5 9B🇪🇺 eu
$0.10cache read $0.015$0.15262KNot measured
GPT OSS 20b🇪🇺 eu
$0.018cache read $0.0027$0.09131K
Llama 3.3 70B InstructLlama-3.3-70B-Instruct-FP8 · fp8 · 🇪🇺 eu
$0.22$0.50131KNot measured
BGE M3🇪🇺 eu
Not enough data yet$0.01—8KNot enough data yetNot measuredNot measured
Mistral NemoMistral-Nemo-Instruct-2407-FP8 · fp8 · 🇪🇺 eu
Not enough data yet$0.023$0.03131KNot measured
Llama 3.1 8B InstructMeta-Llama-3.1-8B-Instruct-FP8 · fp8 · 🇪🇺 eu
$0.05$0.08131KNot measuredNot measured
Qwen3 Reranker 8B🇪🇺 eu
Not enough data yetNot enough data yet$0.05—41KNot enough data yetNot measuredNot measured
Show all 33 listings

Showing 25 of 33: one listing for each model.

Run by Flexai

7 listings on this page where Flexai 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
 Eden AI$0.08cache read $0.0055$0.6051M
DeepSeek V4 Flash 0731
 Eden AI$0.13cache read $0.0195$0.261M
DeepSeek V4 Flash 0731flexai/DeepSeek-V4-Flash-0731@eu · 🇪🇺 eu
 Eden AI$0.13cache read $0.0195$0.261M
 Eden AINot enough data yet$0.35cache read $0.04$1.50131KNot measuredNot measured
GPT OSS 120B
 Eden AI$0.03cache read $0.0045$0.15131K
GPT OSS 20b
 Eden AI$0.018cache read $0.0027$0.09131K
GPT OSS 20bflexai/gpt-oss-20b@eu · 🇪🇺 eu
 Eden AI$0.018cache read $0.0027$0.09131K

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

Around the web

  • FlexAI
    FlexAI is building the next generation of AI cloud infrastructure, one that is software defined …FlexAI is building the next generation of AI cloud infrastructure, one that is software defined and optimized for modern AI workloads.Read more

    linkedin.com

  • FlexAI - Crunchbase Company Profile & Funding
    FlexAI is a NeoCloud for AI startups and enterprises. It sells tokens with an Agent …FlexAI is a NeoCloud for AI startups and enterprises. It sells tokens with an Agent SDK for startups, and offers private cloud deployments for enterprises.Read more

    crunchbase.com

  • Ex-Nvidia, Apple And Intel Engineers Launched AI Startup ...
    FlexAI aims to unlock access to more compute capabilities and increased efficiency, with less complexity …FlexAI aims to unlock access to more compute capabilities and increased efficiency, with less complexity for developers. Delivered as an on- ...Read more

    crn.com

  • FlexAI: Funding, Team & Investors
    FlexAI: AI compute infrastructure orchestrating diverse hardware and clouds for developers, reducing AI model training …FlexAI: AI compute infrastructure orchestrating diverse hardware and clouds for developers, reducing AI model training costs and complexity.

    startupintros.com

  • FlexAI PaaS: AI training + inference right-sizing, OpenAI- ...
    We're building a platform as a service that enables AI engineers to train and deploy …We're building a platform as a service that enables AI engineers to train and deploy models in record time and at only 30% of their typical costs.

    youtube.com

How this data works