Skip to content

Vercel AI Gateway

Pricing page

99 listings across 97 models

Page 3 of 4. The lists below split this page's listings into those sold by Vercel AI Gateway, run by Vercel AI Gateway, or sent to Vercel AI Gateway by a marketplace.

Sold by Vercel AI Gateway

25 listings on this page sold by Vercel AI Gateway.

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
Ministral 8B
Not enough data yet$0.10$0.10128KNot measuredNot measured
Mixtral 8x22B Instruct
Not enough data yet$1.20$1.2066KNot enough data yetNot measuredNot measured
Nova Pro
Not enough data yet$0.80$3.20300KNot measuredNot measured
Llama 4 Scout
$0.10$0.30131KNot measured
Meta Llama 3 70bvercel_ai_gateway/meta/llama-3-70b
Not enough data yet$0.59$0.798KNot measured
Text Embedding 005
Not enough data yet$0.025β€”Not published by the providerNot enough data yetNot measuredNot measured
GPT-4.1 nano
$0.10cache read $0.025$0.401MNot measured
Nova Lite
$0.06$0.24300KNot measured
Nova Micro
Not enough data yet$0.035$0.14128KNot measuredNot measured
Claude 3 Haiku
$0.25cache read $0.03$1.25cache write $0.30200KNot measured
Llama 3.1 70B
Not enough data yet$0.72$0.72128KNot enough data yetNot measured
Text Embedding 3 Small
Not enough data yet$0.02β€”Not published by the providerNot enough data yetNot measuredNot measured
Text Embedding Ada 002
Not enough data yet$0.10β€”Not published by the providerNot enough data yetNot measuredNot measured
Ministral 3B
Not enough data yet$0.04$0.04128KNot measuredNot measured
gemma-2-9b
Not enough data yet$0.20$0.208KNot measured
GPT-3.5 Turbo
$0.50$1.5016KNot measured
Not enough data yet$0.75$0.99131KNot enough data yetNot measuredNot measured
Command R+
$0.15$0.60128KNot enough data yetNot measuredNot measured
Command R Plus
Not enough data yet$2.50$10.00128KNot measuredNot measured
Pixtral 12B
Not enough data yet$0.15$0.15128KNot measuredNot measured
Grok 2 Vision 1212vercel_ai_gateway/xai/grok-2-vision
Not enough data yet$2.00$10.0033KNot measuredNot measured
Meta Llama 3 8bvercel_ai_gateway/meta/llama-3-8b
Not enough data yet$0.05$0.088KNot enough data yetNot measured
Llama 3.1 8B
Not enough data yet$0.05$0.08131KNot enough data yetNot measured
Llama 3.2 3B
$0.15$0.15128KNot measuredNot measured
Llama 3.2 1B
Not enough data yet$0.10$0.10128KNot enough data yetNot measuredNot measured

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

How this data works