Skip to content

105 listings across 40 models

Data policies

from the provider's published policies

Headquarters: USPrivacy policyTerms of serviceStatus page

We haven't found any data policy statements on Baseten's pages yet.

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

Sold by Baseten

23 listings on this page sold by Baseten.

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
$2.00cache read $0.20$10.001M
$0.30cache read $0.007$1.201M
Kimi K3fp8
$3.00cache read $0.30$15.001M
GLM 5.3fp4
$1.40cache read $0.14$4.401M
$0.30cache read $0.007$1.201M
DeepSeek V4 Pro 0813fp4
$1.32cache read $0.132$3.961M
Muse Spark Openfp4
$1.25cache read $0.15$4.251MNot measured
GLM 5.2fp8
$1.40cache read $0.14$4.401M
GLM 5.3 Flashfp8
$0.15cache read $0.03$0.501M
Kimi K2.6
$0.95cache read $0.16$4.00262K
DeepSeek V4 Flash 0731fp8
$0.13cache read $0.028$0.261M
$1.74cache read $0.145$3.481M
GLM 5
$0.95$3.15Not published by the provider
Kimi K2.5
$0.60$3.00Not published by the provider
$0.50cache read $0.10$1.201M
GLM 4.7
$0.60cache read $0.12$2.20200K
Inkling FP4baseten/thinkingmachines/inkling
$1.00cache read $0.17$4.051M
$0.95cache read $0.16$4.00262K
NVIDIA Nemotron 3.5 Super VL 120Bnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B
$0.20cache read $0.04$0.501MNot measuredNot measured
Show all 23 listings

Showing 19 of 23: one listing for each model.

Run by Baseten

49 listings on this page where Baseten 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
 Hugging Face$0.30$1.201M
Kimi K3
 Hugging Face$3.00$15.001M
GLM 5.3
 Hugging Face$1.40$4.401M
 Hugging Face$0.30$1.201M
 Hugging Face$1.32$3.961M
Muse Spark Openfp4 · 🇺🇸 US
 NanoGPT$1.3125cache read $0.1575$4.4625Not published by the providerNot measured
 Hugging Face$1.25$4.251MNot measured
GLM 5.2
 Hugging Face$1.40$4.401M
 Hugging Face$0.15$0.501M
DeepSeek V4 Flash 0731
 Hugging Face$0.13$0.261M
DeepSeek V4.1 Flash 0910deepseek/deepseek-v4.1-flash
 OpenRouterNot enough data yet$0.30cache read $0.007$1.201MNot enough data yetNot measuredNot measured
 Hugging Face$0.40$1.201MNot enough data yetNot measuredNot measured
DeepSeek V4 Flashdeepseek/deepseek-v4-flash-latest · latest · 🇺🇸 US
 NanoGPT$0.315cache read $0.0074$1.26Not published by the provider
Nemotron 3.5 Super VLfp4 · 🇺🇸 US
 NanoGPTNot enough data yet$0.21cache read $0.042$0.525Not published by the providerNot measured
NVIDIA Nemotron 3.5 Super VL 120Bnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 · bf16
 Hugging Face$0.20$0.501MNot measuredNot measured
Show all 49 listings

Showing 15 of 49: one listing for each model.

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

How this data works