Skip to content

573 listings across 344 models

Page 4 of 14. The lists below split this page's listings into those sold by Venice, run by Venice, or sent to Venice by a marketplace.

Sold by Venice

26 listings on this page sold by Venice.

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
$1.00cache read $0.20$2.00256KNot measuredNot measured
Doubao Seed 2.1 Turboseed-2-1-turbo
Not enough data yet$0.625cache read $0.125$3.125256KNot enough data yetNot measuredNot measured
Gemma 4 31B ITgoogle-gemma-4-31b-it · fp4
$0.12cache read $0.09$0.36256K
GPT-5.4 miniopenai-gpt-54-mini
$0.75cache read $0.075$4.50400K
$0.375cache read $0.0375$3.1251M
GLM 4.7zai-org-glm-4.7 · fp4
$0.55cache read $0.11$2.65198K
MiMo V2.5xiaomi-mimo-v2-5 · fp8
$0.40cache read $0.08$2.001MNot measured
Kimi K2.7 Codeint4
$0.75cache read $0.16$3.50256K
GLM 5 Turboz-ai-glm-5-turbo
$1.20cache read $0.24$4.00200KNot measuredNot measured
GLM 5V Turboz-ai-glm-5v-turbo
$1.50cache read $0.30$5.00200KNot measuredNot measured
MiniMax M3minimax-m3-preview · fp8
$0.30cache read $0.06$1.20524K
Gemini Omni 1.1 Flashgemini-omni-flash-1-1-image-to-video · image-to-video
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
DeepSeek V3.2
$0.33cache read $0.16$0.48160KNot measured
NVIDIA Nemotron 3.5 Super VL 120Bnvidia-nemotron-3-5-super-vl-120b-a12b · fp4
$0.20cache read $0.04$0.50262KNot measuredNot measured
Gemma 4 26B A4Bgoogle-gemma-4-26b-a4b-it · bf16
$0.13cache read $0.05$0.40256K
$0.45$3.50128KNot measuredNot measured
Grok 4.3
$1.42cache read $0.23$2.831MNot measured
Nemotron 3 Ultranvidia-nemotron-3-ultra-550b-a55b · fp8
$0.625cache read $0.1875$3.125256K
Qwen3.6 27Bfp8
$0.325$3.25256KNot measured
GLM 4.6zai-org-glm-4.6 · fp4
$0.43cache read $0.08$1.75198KNot measured
MiniMax M2.5
$0.27cache read $0.03$0.95198KNot measured
Gemini Embedding 2gemini-embedding-2-preview
Not enough data yet$0.25—2KNot enough data yetNot measuredNot measured
Qwen3.5 35B A3B
$0.15cache read $0.05$1.00256K
Show all 26 listings

Showing 23 of 26: one listing for each model.

Run by Venice

38 listings on this page where Venice 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$0.12$0.36256K
GLM 4.7
 Hugging Face$0.4004$1.9292198K
MiMo V2.5
 Hugging Face$0.40$2.001MNot measured
 Hugging Face$0.75$3.50256K
MiniMax M3
 Hugging Face$0.30$1.20524K
Nemotron 3.5 Super VLfp4
 OpenRouterNot enough data yet$0.20cache read $0.04$0.50262KNot measured
NVIDIA Nemotron 3.5 Super VL 120Bnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 · bf16
 Hugging Face$0.20$0.50262KNot measuredNot measured
Gemma 4 26B A4Bgoogle/gemma-4-26B-A4B-it
 Hugging Face$0.13$0.40256K
 Hugging Face$0.45$3.50128KNot measuredNot measured
Nemotron 3 Ultranvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · bf16
 Hugging Face$0.625$3.125256K
Qwen3.6 27B
 Hugging Face$0.325$3.25256KNot measured
GLM 4.6
 Hugging Face$0.43$1.75198KNot measured
MiniMax M2.5
 Hugging Face$0.27$0.95198KNot measured
Qwen3.5 35B A3B
 Hugging Face$0.15$1.00256K
Show all 38 listings

Showing 14 of 38: one listing for each model.

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

How this data works