Skip to content

62 listings across 30 models

Data policies

from the provider's published policies

Headquarters: USPrivacy policyTerms of serviceStatus page

On training
We don't have their wording on this. Their policy: Phala privacy policy
On keeping your data

IP logs for anti-spam purposes: Retained for six months.

Source: Phala privacy policy

More from Phala on keeping your data (2)

Cookies and tracking data: Retained based on third-party policies.

Source: Phala privacy policy

TEE-stored business information: Permanently deleted upon user request.

Source: Phala privacy policy

We take these statements from Phala'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.

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

Sold by Phala

19 listings on this page sold by Phala.

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
$2.00$10.001M
$0.75cache read $0.15$1.601M
Kimi K3
$3.00cache read $0.30$15.001M
GLM 5.3
$1.40cache read $0.26$4.401M
GLM 5.2
$1.26cache read $0.22$3.001M
GLM 5.3 Flashfp8
$0.15cache read $0.03$0.501M
Kimi K2.6
$1.09cache read $0.37$4.60262K
DeepSeek V4 Flash 0731
$0.44cache read $0.028$1.321M
GLM 5.1
$1.21cache read $0.60$4.20203K
$0.55cache read $0.225$3.50262K
Qwen 3.8 27B
$0.20cache read $0.05$2.501MNot measured
$0.15cache read $0.075$0.46262K
Qwen3.5 27B
$0.30cache read $0.03$2.40262KNot measured
DeepSeek V3.2
$1.00cache read $0.50$1.00164KNot measured
Qwen3.6 27B
$0.32cache read $0.03$3.25262KNot measured
$0.20cache read $0.056$1.27262KNot measured
GPT OSS 120B
$0.15$0.60131K
qwen3-vl-30bqwen/qwen3-vl-30b-a3b-instruct
Not enough data yet$0.20cache read $0.03$0.70128KNot measuredNot measured
$2.00$2.00131KNot measured

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

How this data works