Nebius Token Factory
49 models available
Models
Browse all models from Nebius Token Factory
Hermes-4-70B
nebius
ReasoningTool UseOpen Weights
Input
$0.13/1M
Output
$0.40/1M
Context
128K
Max Output
8K
Hermes-4-405B
nebius
ReasoningTool UseOpen Weights
Input
$1.00/1M
Output
$3.00/1M
Context
128K
Max Output
8K
Kimi-K2-Instruct
nebius
Tool UseVision
Input
$0.50/1M
Output
$2.40/1M
Context
200K
Max Output
8K
Llama-3.1-Nemotron-Ultra-253B-v1
nebius
Tool UseOpen Weights
Input
$0.60/1M
Output
$1.80/1M
Context
128K
Max Output
4K
gpt-oss-20b
nebius
Tool UseOpen Weights
Input
$0.05/1M
Output
$0.20/1M
Context
128K
Max Output
4K
gpt-oss-120b
nebius
ReasoningTool UseOpen Weights
Input
$0.15/1M
Output
$0.60/1M
Context
128K
Max Output
8K
Qwen3 235B A22B Instruct 2507
nebius
ReasoningTool Use
Input
$0.20/1M
Output
$0.60/1M
Context
262K
Max Output
8K
Qwen3 235B A22B Thinking 2507
nebius
ReasoningTool Use
Input
$0.20/1M
Output
$0.80/1M
Context
262K
Max Output
8K
Qwen3 Coder 480B A35B Instruct
nebius
Tool Use
Input
$0.40/1M
Output
$1.80/1M
Context
262K
Max Output
67K
Llama-3.1-405B-Instruct
nebius
Tool UseOpen Weights
Input
$1.00/1M
Output
$3.00/1M
Context
131K
Max Output
8K
Llama-3.3-70B-Instruct (Fast)
nebius
Tool UseOpen Weights
Input
$0.25/1M
Output
$0.75/1M
Context
128K
Max Output
8K
Llama-3.3-70B-Instruct
nebius
Tool UseOpen Weights
Input
$0.13/1M
Output
$0.40/1M
Context
128K
Max Output
8K
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
NEBIUS_API_KEY
API Base URL
https://api.tokenfactory.nebius.com/v1