Skip to content

20 listings across 12 models

Data policies

from the provider's published policies

Privacy policy

On training

Content submitted to the Services is not used to train, fine-tune, evaluate, or improve models, and is not used for advertising, profiling, or analytics.

Source: Ambient privacy policy

On keeping your data

Ambient does not log, store, or retain inference request or response content from API traffic, including prompts/inputs, files/attachments, tool payloads, or model outputs.

Source: Ambient privacy policy

More from Ambient on keeping your data (1)

Chat Data is not stored unless you choose to save it

Source: Ambient privacy policy

We take these statements from Ambient'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 Ambient

11 listings sold by Ambient.

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 1017fp4
$0.045cache read $0.0025$0.251M
GLM 5.2fp8
$0.60cache read $0.15$2.00203K
GLM 5.2zai-org/GLM-5.2-FP8 Β· fp8
$1.20cache read $0.26$4.20203K
Qwen 3.8 27B
$0.32cache read $0.16$3.2033KNot measured
MiniMax M3
$0.23cache read $0.05$0.96131K
Qwen3.6 27B
$0.32cache read $0.16$3.2033KNot measured
Qwen3.6 35B A3B
$0.15$1.00262KNot measured
Qwen3 30B A3B Instructqwen/qwen3-30b-a3b-instruct-2507
$0.09$0.30131KNot measured
Ambient Smallambient/small
Not enough data yetNot enough data yet$0.001$0.001101KNot enough data yetNot measuredNot measured
Ambient Largeambient/large
Not enough data yetNot enough data yet$0.60cache read $0.15$2.00203KNot enough data yetNot measuredNot measured
Not enough data yetNot enough data yet$0.001$0.001101KNot enough data yetNot measuredNot measured

Run by Ambient

7 listings where Ambient 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
DeepSeek V4.1 Flash 1017fp4
Β NanoGPT$0.1029cache read $0.003$0.3087Not published by the provider
GLM 5.2fp8
Β NanoGPT$0.63cache read $0.1575$2.10Not published by the provider
DeepSeek V4 Flashdeepseek/deepseek-v4-flash-latest Β· latest Β· fp4
Β NanoGPT$0.1029cache read $0.003$0.3087Not published by the provider
Show all 7 listings

Showing 3 of 7: one listing for each model.

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

How this data works