OpenAI: GPT-5.4 Nano
openai/gpt-5-4-nanoGPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.
Modalities
In / out per 1M$0.20 / $1.25
Context391K
ReleasedMar 17, 2026
Providers
4 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 OpenAI | $0.10 | $0.63 | $0.01 | 1.10s | 116 tps | 100% |
| OpenAI | $0.20 | $1.25 | $0.02 | 0.98s | 102 tps | 100% |
 Azureeastus2 | $0.22 | $1.38 | $0.02 | 8.16s | 50 tps | 100% |
| Azure | $0.20 | $1.25 | $0.02 | 4.52s | 45 tps | 99.87% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves GPT-5.4 Nano in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what GPT-5.4 Nano costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.20
per 1M tokens
Output
$1.25
per 1M tokens
Cache read
$0.02
per 1M cached tokens
Included in every pass
GPT-5.4 Nano is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s2.0s4.0s6.0s8.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Azure OpenAI OpenAI
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Azure OpenAI OpenAI
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.41%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.25%
100% 97% 93% 90%
Oct 13, 2:40 PMNow
Apps
Tools that most often run GPT-5.4 Nano, by tokens this week.
Activity
467.6B tokens processed market-wide in the last month.
05.0B10.0B15.0B20.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for GPT-5.4 Nano?
openai/gpt-5.4-nano. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does GPT-5.4 Nano hold?
400,000 tokens per request, of which up to 128,000 can be the response.
What can it accept and return?
Input: file, image, text. Output: text.
What does GPT-5.4 Nano cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.20 per 1M input tokens and $1.25 per 1M output tokens.
How current is its knowledge?
Training data runs to Aug 2025. Anything later has to come from your prompt or a tool call.
Who built GPT-5.4 Nano?
OpenAI, in the GPT family.
Explore
Other models your pass can call.
