openai/gpt-5.4-nano-2026-03-17

openai/gpt-5.4-nano-2026-03-17
VisionToolsJSONReasoning
by openai
Endpoints:/v1/chat/completions/v1/responses
Max output128K
Inputfile + image + text
p50 TTFT682 ms
INPUT$0.20/ 1M tokens
OUTPUT$1.25/ 1M tokens
p50 TTFT682 ms7d
p95 TTFT1.00 s7d
TRAFFIC3.3Ktokens / 7d
Get the openai/gpt-5.4-nano-2026-03-17 API →▶ Try in playground</> Use via API

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="openai/gpt-5.4-nano-2026-03-17",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • response_format
  • seed
  • stream
  • structured_outputs
  • tool_choice
  • tools

Pricing

Pricing
Input / 1M tokens$0.200
Output / 1M tokens$1.25
Cache read / 1M$0.020
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $5.15 · With prompt caching $4.52

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000629

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

last 7 days
p50 TTFT
682 ms
Output speed
30.2 tok/s
p95 TTFT
1.00 s
Error rate
1.8%

Public benchmarks

Last evaluated 2026-03-17
56.1
AA Coding
Better than 63% of models compared
#48 of 138
20.7
AA Intelligence
Better than 32% of models compared
#100 of 149
GPQA Diamond
81.7
Humanity's Last Exam
28.3
IFBench
75.9
Long-Context Recall
76.7
SciCode
47.2
tau_banking
27.4
TerminalBench Hard
42.4
terminalbench_v2_1
60.7
terminalbench_v4_0
0.5
τ²-Bench
76.0
Source: artificialanalysis.ai

Community buzz

What developers are saying this week

Hacker News0 mentions · 7d

How it compares

openai/gpt-5.4-nano-2026-03-17GPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$0.20$21.00$60.00$5.00
Output $/M$1.25$168.00$270.00$30.00
Context—400K1.1M—
Quality5/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

Browse AI model comparisons →

More from openai

See all models from openai →
GPT-5.5 ProFlagship
openai/gpt-5.5-pro
$30.00 in · $180.00 out / 1M
· quality 10/10
 Compare side-by-side
GPT-5.2Cheapest
openai/gpt-5.2
$1.75 in · $14.00 out / 1M
400K ctx· quality 9/10
 Compare side-by-side
openai/gpt-5.2-chat-latest
openai/gpt-5.2-chat-latest
$1.75 in · $14.00 out / 1M
· quality 9/10
 Compare side-by-side

FAQ

How much does openai/gpt-5.4-nano-2026-03-17 cost on OrcaRouter?
openai/gpt-5.4-nano-2026-03-17 is priced at $0.20 per 1M input tokens and $1.25 per 1M output tokens via OrcaRouter. Pricing is pulled live from the routing layer.
How do I call openai/gpt-5.4-nano-2026-03-17 via the OpenAI SDK?
Set OpenAI base_url to https://api.orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="openai/gpt-5.4-nano-2026-03-17" in the chat.completions.create call.
Does OrcaRouter rate-limit openai/gpt-5.4-nano-2026-03-17?
Per-model rate limits follow your OrcaRouter plan. Free tiers ship with conservative caps; paid tiers lift them. Check /pricing for current quotas.

Embed this badge

Paste into your blog post
openai/gpt-5.4-nano-2026-03-17•$0.20/M in•682ms p50•via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-5.4-nano-2026-03-17" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-5.4-nano-2026-03-17.svg" alt="openai/gpt-5.4-nano-2026-03-17 on OrcaRouter" /> </a>
Markdown [![openai/gpt-5.4-nano-2026-03-17](https://www.orcarouter.ai/embed/openai/gpt-5.4-nano-2026-03-17.svg)](https://www.orcarouter.ai/models/openai/gpt-5.4-nano-2026-03-17)

Model card as data

GET /api/public/models/openai/gpt-5.4-nano-2026-03-17Open
Machine-readable:/llms.txt/llms-full.txt