Compare · AI Inference · cost

Pricing reference rows.

Review provider-published pricing references for AI Inference. Rows stay unsorted by price when billing units do not match.

Mixed units

Starting prices are shown as references, not a cheapest ranking.

Providers publish these rows in different billing units, so losclouds keeps the original labels and falls back to alphabetical order.

Pricing comparison

50 offerings on this page, listed alphabetically because starting-price units are mixed.

Service

Qwen

Offering

Qwen3 30B A3B

pay-as-you-go$0.080 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 30B A3B Instruct 2507

pay-as-you-go$0.090 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 30B A3B Thinking 2507

pay-as-you-go$0.080 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 32B

pay-as-you-go$0.140 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 8B

pay-as-you-go$0.050 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 Coder 30B A3B Instruct

pay-as-you-go$0.070 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 Coder 480B A35B

pay-as-you-go$0.220 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 Coder 480B A35B

freePrice pending

Pricing

Service

Qwen

Offering

Qwen3 Coder Flash

pay-as-you-go$0.195 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 Coder Next

pay-as-you-go$0.120 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 Coder Plus

pay-as-you-go$0.650 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 Max

pay-as-you-go$0.780 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 Max Thinking

pay-as-you-go$0.780 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 Next 80B A3B Instruct

pay-as-you-go$0.090 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 Next 80B A3B Instruct

freePrice pending

Pricing

Service

Qwen

Offering

Qwen3 Next 80B A3B Thinking

pay-as-you-go$0.0975 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 VL 235B A22B Instruct

pay-as-you-go$0.200 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 VL 235B A22B Thinking

pay-as-you-go$0.260 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 VL 30B A3B Instruct

pay-as-you-go$0.130 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 VL 30B A3B Thinking

pay-as-you-go$0.130 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 VL 32B Instruct

pay-as-you-go$0.104 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 VL 8B Instruct

pay-as-you-go$0.080 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3 VL 8B Thinking

pay-as-you-go$0.117 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3.5 397B A17B

pay-as-you-go$0.390 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3.5 Plus 2026-02-15

pay-as-you-go$0.260 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3.5-122B-A10B

pay-as-you-go$0.260 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3.5-27B

pay-as-you-go$0.195 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3.5-35B-A3B

pay-as-you-go$0.1625 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3.5-9B

pay-as-you-go$0.050 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3.5-Flash

pay-as-you-go$0.065 1M input tokens

Pricing

Service

Qwen

Offering

Qwen3.6 Plus

freePrice pending

Pricing

Service

Qwen

Offering

QwQ-32B

pay-as-you-go$0.120 1M input tokens

Pricing

Service

Recursion

Offering

Recursion AI Models (Phenomics)

subscriptionFree

Pricing

Service

Reka AI

Offering

Reka AI Multimodal Models

usage-based$0.0004 per 1K tokens (Reka Edge)

Pricing

Service

Reka AI

Offering

Reka Edge

pay-as-you-go$0.100 1M input tokens

Pricing

Service

Reka AI

Offering

Reka Flash 3

pay-as-you-go$0.100 1M input tokens

Pricing

Service

Replicate

Offering

Replicate Open-Source AI Model API

usage-based$0.0002 per second CPU (varies by model)

Pricing

Service

Resemble AI

Offering

Resemble AI Voice API

usage-based$0.006 per second of audio

Pricing

Service

RunPod

Offering

RunPod Serverless AI Inference

usage-based$0.0002 per second (RTX 3090)

Pricing

Service

Runway Research

Offering

Runway Research API

usage-based$0.050 per generation credit

Pricing

Service

Salesforce

Offering

Salesforce Einstein AI

subscription$50 per user/month (Einstein for Sales)

Pricing

Service

SambaNova Systems

Offering

SambaNova Cloud AI Inference

usage-based$0.0005 per 1K tokens

Pricing

Service

SAP Business Technology Platform

Offering

SAP AI Core

usage-based$0.020 per capability unit hour

Pricing

Service

Scale AI

Offering

Scale Generative AI Platform

usage-basedFree

Pricing

Service

Snorkel AI

Offering

Snorkel Flow Model Training

subscriptionFree

Pricing

Service

Snowflake

Offering

Snowflake Cortex AI

usage-based$0.040 per 1M tokens (Llama 3 8B)

Pricing

Service

Stability AI

Offering

Stability AI Inference API

usage-based$0.065 per image (SD3.5)

Pricing

Service

StepFun

Offering

Step 3.5 Flash

pay-as-you-go$0.100 1M input tokens

Pricing

Service

StepFun

Offering

Step 3.5 Flash

freePrice pending

Pricing

Service

Tabnine

Offering

Tabnine AI Code Inference

freemiumFree

Pricing

Pricing comparison for AI Inference
Service	Offering	Model	Starting Price	Details
Qwen	Qwen3 30B A3B	pay-as-you-go	$0.080 1M input tokens	Pricing
Qwen	Qwen3 30B A3B Instruct 2507	pay-as-you-go	$0.090 1M input tokens	Pricing
Qwen	Qwen3 30B A3B Thinking 2507	pay-as-you-go	$0.080 1M input tokens	Pricing
Qwen	Qwen3 32B	pay-as-you-go	$0.140 1M input tokens	Pricing
Qwen	Qwen3 8B	pay-as-you-go	$0.050 1M input tokens	Pricing
Qwen	Qwen3 Coder 30B A3B Instruct	pay-as-you-go	$0.070 1M input tokens	Pricing
Qwen	Qwen3 Coder 480B A35B	pay-as-you-go	$0.220 1M input tokens	Pricing
Qwen	Qwen3 Coder 480B A35B	free	—	Pricing
Qwen	Qwen3 Coder Flash	pay-as-you-go	$0.195 1M input tokens	Pricing
Qwen	Qwen3 Coder Next	pay-as-you-go	$0.120 1M input tokens	Pricing
Qwen	Qwen3 Coder Plus	pay-as-you-go	$0.650 1M input tokens	Pricing
Qwen	Qwen3 Max	pay-as-you-go	$0.780 1M input tokens	Pricing
Qwen	Qwen3 Max Thinking	pay-as-you-go	$0.780 1M input tokens	Pricing
Qwen	Qwen3 Next 80B A3B Instruct	pay-as-you-go	$0.090 1M input tokens	Pricing
Qwen	Qwen3 Next 80B A3B Instruct	free	—	Pricing
Qwen	Qwen3 Next 80B A3B Thinking	pay-as-you-go	$0.0975 1M input tokens	Pricing
Qwen	Qwen3 VL 235B A22B Instruct	pay-as-you-go	$0.200 1M input tokens	Pricing
Qwen	Qwen3 VL 235B A22B Thinking	pay-as-you-go	$0.260 1M input tokens	Pricing
Qwen	Qwen3 VL 30B A3B Instruct	pay-as-you-go	$0.130 1M input tokens	Pricing
Qwen	Qwen3 VL 30B A3B Thinking	pay-as-you-go	$0.130 1M input tokens	Pricing
Qwen	Qwen3 VL 32B Instruct	pay-as-you-go	$0.104 1M input tokens	Pricing
Qwen	Qwen3 VL 8B Instruct	pay-as-you-go	$0.080 1M input tokens	Pricing
Qwen	Qwen3 VL 8B Thinking	pay-as-you-go	$0.117 1M input tokens	Pricing
Qwen	Qwen3.5 397B A17B	pay-as-you-go	$0.390 1M input tokens	Pricing
Qwen	Qwen3.5 Plus 2026-02-15	pay-as-you-go	$0.260 1M input tokens	Pricing
Qwen	Qwen3.5-122B-A10B	pay-as-you-go	$0.260 1M input tokens	Pricing
Qwen	Qwen3.5-27B	pay-as-you-go	$0.195 1M input tokens	Pricing
Qwen	Qwen3.5-35B-A3B	pay-as-you-go	$0.1625 1M input tokens	Pricing
Qwen	Qwen3.5-9B	pay-as-you-go	$0.050 1M input tokens	Pricing
Qwen	Qwen3.5-Flash	pay-as-you-go	$0.065 1M input tokens	Pricing
Qwen	Qwen3.6 Plus	free	—	Pricing
Qwen	QwQ-32B	pay-as-you-go	$0.120 1M input tokens	Pricing
Recursion	Recursion AI Models (Phenomics)	subscription	Free	Pricing
Reka AI	Reka AI Multimodal Models	usage-based	$0.0004 per 1K tokens (Reka Edge)	Pricing
Reka AI	Reka Edge	pay-as-you-go	$0.100 1M input tokens	Pricing
Reka AI	Reka Flash 3	pay-as-you-go	$0.100 1M input tokens	Pricing
Replicate	Replicate Open-Source AI Model API	usage-based	$0.0002 per second CPU (varies by model)	Pricing
Resemble AI	Resemble AI Voice API	usage-based	$0.006 per second of audio	Pricing
RunPod	RunPod Serverless AI Inference	usage-based	$0.0002 per second (RTX 3090)	Pricing
Runway Research	Runway Research API	usage-based	$0.050 per generation credit	Pricing
Salesforce	Salesforce Einstein AI	subscription	$50 per user/month (Einstein for Sales)	Pricing
SambaNova Systems	SambaNova Cloud AI Inference	usage-based	$0.0005 per 1K tokens	Pricing
SAP Business Technology Platform	SAP AI Core	usage-based	$0.020 per capability unit hour	Pricing
Scale AI	Scale Generative AI Platform	usage-based	Free	Pricing
Snorkel AI	Snorkel Flow Model Training	subscription	Free	Pricing
Snowflake	Snowflake Cortex AI	usage-based	$0.040 per 1M tokens (Llama 3 8B)	Pricing
Stability AI	Stability AI Inference API	usage-based	$0.065 per image (SD3.5)	Pricing
StepFun	Step 3.5 Flash	pay-as-you-go	$0.100 1M input tokens	Pricing
StepFun	Step 3.5 Flash	free	—	Pricing
Tabnine	Tabnine AI Code Inference	freemium	Free	Pricing

Showing 401–450 of 495 offerings