GPT-5 Nano
OpenAI · moe · 8B parameters · 400,000 context
Parameters
8B
Context Window
391K tokens
Architecture
MoE
Best GPU
A10G
Cheapest API
$0.40/M
Intelligence Brief
GPT-5 Nano is a 8B parameter Mixture-of-Experts (16 experts, 2 active) model from OpenAI, featuring Grouped Query Attention (GQA) with 80 layers and 10,240 hidden dimensions. With a 400,000 token context window, it supports tools, vision, structured output, code, math, multilingual, reasoning. The most cost-effective API deployment is via openai at $0.40/M output tokens. For self-hosted inference, A10G delivers optimal throughput at $285/month.
Provider pricing
1 provider · canonical: openai| Provider | Input $/M | Output $/M ▲ | Notes |
|---|---|---|---|
| openaicanonical | $0.050 | $0.400 | cheapest input · cheapest output |
Prices update via the nightly pricing cron + admin approvals at /admin/ingest-queue. The leaderboard's Input/Output cells show the canonical rate above; this table shows the full spread.
Recent changes
Loading…
Related models
5 suggestions- GPT-4.5 PreviewGPT · 300B$150.00/M out
- GPT-5.5GPT · 110B$30.00/M out
- GPT-5 MiniGPT · 25B$2.00/M out
- GPT-5GPT · 90B$10.00/M out
- DALL-E 3DALL-E · 3.5B$40.00/M out
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
16.0 GB
FP8 Weights
8.0 GB
INT4 Weights
4.0 GB
GPU Compatibility Matrix
GPT-5 Nano is compatible with 90% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
405.0 tok/s
Latency (ITL)
2.5ms
Est. TTFT
0ms
Cost/Month
$285
Cost/M Tokens
$0.27
BF16 · 1 GPU · vllm
100/100
score
Throughput
629.7 tok/s
Latency (ITL)
1.6ms
Est. TTFT
0ms
Cost/Month
$332
Cost/M Tokens
$0.20
BF16 · 1 GPU · vllm
100/100
score
Throughput
680.4 tok/s
Latency (ITL)
1.5ms
Est. TTFT
0ms
Cost/Month
$370
Cost/M Tokens
$0.21
Deployment Options
API Deployment
openai
$0.40/M
output tokens
Single GPU
A10G
$285/mo
Min VRAM: 8 GB
Multi-GPU
A4000 x2
434.9 tok/s
TP· $323/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| openai | $0.05 | $0.40 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| openaiBest Value | $0.05 | $0.40 | $2 |
Cost per 1,000 Requests
Short (500 tok)
$0.11
via openai
Medium (2K tok)
$0.42
via openai
Long (8K tok)
$1.20
via openai
Performance Estimates
Throughput by GPU
VRAM Breakdown (A10G, BF16)
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy GPT-5 Nano
Self-Hosted Infrastructure
Similar Models
Aya 23 8B
8B params · dense
Quality: 50
from $0.60/M
DeepSeek R1 Distill 8B
8B params · dense
Quality: 88
from $0.20/M
InternLM3 8B
8B params · dense
Quality: 50
Llama 3 8B
8B params · dense
Quality: 63
from $0.04/M
Llama 3.3 8B
8B params · dense
Quality: 50
from $0.18/M
Frequently Asked Questions
How much VRAM does GPT-5 Nano need for inference?
GPT-5 Nano requires approximately 16.0 GB of VRAM at BF16 precision, 8.0 GB at FP8, or 4.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (204800 bytes per token) and activations (~4.00 GB).
What is the best GPU for GPT-5 Nano?
The top recommended GPU for GPT-5 Nano is the A10G using BF16 precision. It achieves approximately 405.0 tokens/sec at an estimated cost of $285/month ($0.27/M tokens). Score: 100/100.
How much does GPT-5 Nano inference cost?
GPT-5 Nano API inference starts from $0.05/M input tokens and $0.40/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.