Skip to content

30 listings across 20 models

Data policies

from the provider's published policies

Headquarters: USPrivacy policy

On training

We do not retain prompt or response content after the response is returned, and we do not use API content to train models.

Source: Tinfoil privacy policy

On keeping your data

We do not retain prompt or response content after the response is returned, and we do not use API content to train models.

Source: Tinfoil privacy policy

More from Tinfoil on keeping your data (1)

Account data: for the life of your account and up to 30 days after deletion to complete deletion across backups. Billing records: as required by tax and accounting laws, typically up to 7 years.

Source: Tinfoil privacy policy

On where data is processed

Tinfoil is based in the United States, and personal data may be processed in the United States and other locations where our providers operate.

Source: Tinfoil privacy policy

Other statements

Headquarters street address (trust portal): 135 Pierce St, San Francisco, CA 94117, USA.

Source: Tinfoil privacy policy

We take these statements from Tinfoil'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 Tinfoil

18 listings sold by Tinfoil.

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
Kimi K3.1 Pro
$4.00cache read $0.40$20.00262K
GLM 5.3
$1.80cache read $0.45$5.751M
DeepSeek V4.1 Flash
$0.60cache read $0.01$1.451M
Inkling 2 Small
$0.30cache read $0.03$1.00524KNot measuredNot measured
Gemma 4 31B ITgemma4-31b
$0.40$1.00262K
GPT OSS 120B
$0.15$0.60131K
Llama 3.3 70B Instructllama3-3-70b
$1.75$2.75131KNot measured
Nomic Embed Text
Not enough data yetNot enough data yet$0.016—8KNot enough data yetNot measuredNot measured
Doesn’t apply to this modelDoesn’t apply to this model$0.02Doesn’t apply to this model33KDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model
Doesn’t apply to this modelDoesn’t apply to this model$0.06Doesn’t apply to this model33KDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model
GPT OSS Safeguard 120B
Not enough data yetNot enough data yet$0.15$0.60131KNot enough data yetNot measuredNot measured
Voxtral Small 24B
Not enough data yetNot enough data yet$0.20$0.6033KNot measuredNot measured
Doesn’t apply to this modelDoesn’t apply to this model$0.40Doesn’t apply to this model33KDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model
Qwen3 TTS
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Voxtral Mini 4B Realtime
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Voxtral TTS
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Whisper Large V3 Turbo
Not enough data yetNot enough data yet——Not published by the providerNot measuredNot measured

Run by Tinfoil

10 listings where Tinfoil 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
Kimi K3.1 Protee · 🇺🇸 US
 NanoGPT$4.20cache read $0.42$21.00Not published by the provider
GLM 5.3tee · 🇺🇸 US
 NanoGPT$1.89cache read $0.4725$6.0375Not published by the provider
DeepSeek V4.1 Flashtee · 🇺🇸 US
 NanoGPT$0.63cache read $0.0105$1.5225Not published by the provider
Inkling 2 Smalltee · 🇺🇸 US
 NanoGPT$0.315cache read $0.0315$1.05Not published by the providerNot measuredNot measured
Gemma 4 31B IT🇺🇸 US
 NanoGPT$0.42$1.05Not published by the provider
GPT OSS 120B🇺🇸 US
 NanoGPT$0.1575$0.63Not published by the provider
Llama 3.3 70B Instruct🇺🇸 US
 NanoGPT$1.8375$2.8875Not published by the providerNot measured
Show all 10 listings

Showing 7 of 10: one listing for each model.

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

How this data works