Prime Inference
67 models available
Models
Browse all models from Prime Inference
DeepSeek V4 Flash 0423
prime
ReasoningTool UseOpen Weights
Input
$0.44/1M
Output
$1.32/1M
Context
1.0M
Max Output
944K
Llama 3.3 70B Instruct
prime
Tool UseOpen Weights
Input
$1.04/1M
Output
$2.25/1M
Context
131K
Max Output
16K
GLM 5.3 Flash
prime
ReasoningTool UseOpen WeightsVision
Input
$0.15/1M
Output
$0.50/1M
Context
1.0M
Max Output
944K
GLM 5.2
prime
ReasoningTool UseOpen Weights
Input
$1.54/1M
Output
$4.84/1M
Context
1.0M
Max Output
944K
GLM 5.3
prime
ReasoningTool UseOpen Weights
Input
$1.40/1M
Output
$4.40/1M
Context
1.0M
Max Output
131K
Grok 4.7
prime
ReasoningTool UseVision
Input
$1.60/1M
Output
$4.80/1M
Context
500K
Max Output
450K
Grok 4.6
prime
ReasoningTool UseVision
Input
$2.00/1M
Output
$6.00/1M
Context
500K
Max Output
450K
Gemma 3 27B
prime
Tool UseOpen WeightsVision
Input
$0.12/1M
Output
$0.30/1M
Context
131K
Max Output
118K
Gemini 3.6 Flash
prime
ReasoningTool UseVision
Input
$1.50/1M
Output
$7.50/1M
Context
1.0M
Max Output
66K
Gemini 3.1 Pro Preview
prime
ReasoningTool UseVision
Input
$2.00/1M
Output
$12.00/1M
Context
1.0M
Max Output
66K
Gemini 3.5 Flash
prime
ReasoningTool UseVision
Input
$1.50/1M
Output
$9.00/1M
Context
1.0M
Max Output
66K
Gemini 3.7 Flash
prime
ReasoningTool UseVision
Input
$1.35/1M
Output
$6.75/1M
Context
1.0M
Max Output
66K
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
PRIME_API_KEY
API Base URL
https://api.pinference.ai/api/v1