How much does the OpenAI GPT-5.4 API cost?

GPT-5.4 API pricing is $2.50 per million input tokens and $15.00 per million output tokens. Use our calculator at aiapicost.com for exact cost estimates based on your usage.

Which AI model is cheapest for API usage?

The cheapest AI API models change frequently. Use aiapicost.com to compare real-time pricing across 400+ models from OpenAI, Anthropic, Google, DeepSeek, and more. DeepSeek and open-source models typically offer the lowest per-token costs.

How do AI API token costs work?

AI APIs charge per token (roughly 0.75 words). Costs are split into input tokens (what you send) and output tokens (what the model generates). Output tokens are typically 2-5x more expensive. Prices are quoted per 1 million tokens.

Claude vs ChatGPT: which is better?

Both are top-tier models. Claude excels at coding and instruction-following, while GPT-5.4 offers broader multimodal capabilities. Compare them head-to-head at aiapicost.com/compare with real benchmark data.

Live speed data from Artificial Analysis API

AI Model Speed Rankings

Compare 454+ AI models by response speed, latency, and throughput. Find the fastest models for your use case.

454 models · click headers to sort

Model

Throughput ↓

TTFT

$/1M

$/Speed

Price×TTFT

Mercury 2

Inception

770 t/s

3.46s

$0.38

$0.000

1298.3

Granite 3.3 8B (Non-reasoning)

IBM

661 t/s

18.28s

$0.09

$0.000

1553.7

Granite 4.0 H Small

IBM

526 t/s

8.69s

$0.11

$0.000

929.9

Qwen3.5 0.8B (Reasoning)

Alibaba

450 t/s

233ms

$0.02

$0.000

4.7

Qwen3.5 2B (Reasoning)

Alibaba

361 t/s

538ms

$0.04

$0.000

21.5

Gemini 2.5 Flash-Lite (Reasoning)

Google

322 t/s

19.76s

$0.17

$0.001

3458.3

Qwen3.5 0.8B (Non-reasoning)

Alibaba

309 t/s

237ms

$0.02

$0.000

4.7

Nova Micro

Amazon

284 t/s

359ms

$0.06

$0.000

21.9

Ministral 3 3B

Mistral

279 t/s

297ms

$0.10

$0.000

29.7

Gemini 2.5 Flash-Lite (Non-reasoning)

Google

274 t/s

280ms

$0.17

$0.001

49.0

Qwen3.5 2B (Non-reasoning)

Alibaba

272 t/s

535ms

$0.04

$0.000

21.4

gpt-oss-20B (high)

OpenAI

262 t/s

429ms

$0.09

$0.000

40.3

Grok 4.20 Beta 0309 (Reasoning)

xAI

248 t/s

10.20s

$3.0

$0.012

30585.0

gpt-oss-20B (low)

OpenAI

248 t/s

459ms

$0.09

$0.000

43.1

gpt-oss-120B (high)

OpenAI

234 t/s

498ms

$0.26

$0.001

131.0

Qwen3.5 4B (Reasoning)

Alibaba

227 t/s

275ms

$0.06

$0.000

16.5

Grok 4.20 Beta 0309 (Non-reasoning)

xAI

226 t/s

308ms

$3.0

$0.013

924.0

gpt-oss-120B (low)

OpenAI

225 t/s

513ms

$0.26

$0.001

134.9

Qwen3.5 4B (Non-reasoning)

Alibaba

220 t/s

246ms

$0.06

$0.000

14.8

LFM2 24B A2B

Liquid AI

216 t/s

219ms

$0.05

$0.000

11.4

Gemini 2.5 Flash (Reasoning)

Google

213 t/s

13.44s

$0.85

$0.004

11425.7

Nova 2.0 Omni (Non-reasoning)

Amazon

213 t/s

678ms

$0.85

$0.004

576.3

Nova 2.0 Lite (medium)

Amazon

210 t/s

10.13s

$0.85

$0.004

8607.1

Gemini 2.5 Flash (Non-reasoning)

Google

210 t/s

437ms

$0.85

$0.004

371.4

Devstral Small (Jul '25)

Mistral

207 t/s

337ms

$0.15

$0.001

50.6

GPT-5.4 nano (xhigh)

OpenAI

206 t/s

2.58s

$0.46

$0.002

1195.5

Nova 2.0 Lite (low)

Amazon

206 t/s

4.34s

$0.85

$0.004

3692.4

Gemini 3.1 Flash-Lite Preview

Google

205 t/s

7.12s

$0.56

$0.003

4010.8

Nova 2.0 Lite (Non-reasoning)

Amazon

201 t/s

543ms

$0.85

$0.004

461.6

Grok 3 mini Reasoning (high)

xAI

197 t/s

344ms

$0.35

$0.002

120.4

GPT-5.4 nano (medium)

OpenAI

196 t/s

1.36s

$0.46

$0.002

631.1

Qwen3 0.6B (Reasoning)

Alibaba

196 t/s

847ms

$0.40

$0.002

337.1

Gemini 3 Flash Preview (Reasoning)

Google

194 t/s

5.49s

$1.1

$0.006

6177.4

GPT-5.4 nano (Non-Reasoning)

OpenAI

190 t/s

480ms

$0.46

$0.002

222.2

GPT-5.4 mini (xhigh)

OpenAI

188 t/s

5.07s

$1.7

$0.009

8558.2

Nova Lite

Amazon

188 t/s

386ms

$0.10

$0.001

40.5

Qwen3 0.6B (Non-reasoning)

Alibaba

187 t/s

848ms

$0.19

$0.001

159.4

GPT-5.4 mini (medium)

OpenAI

183 t/s

6.98s

$1.7

$0.009

11789.0

Jamba 1.6 Mini

AI21 Labs

182 t/s

726ms

$0.25

$0.001

181.5

Llama 3.1 Instruct 8B

Speed Metrics Guide

Throughput (tokens/s)

Output generation speed in tokens per second. Higher is better.

Good: >50 t/s · Excellent: >100 t/s

Time to First Token (TTFT)

Delay before the first token appears. Lower is better.

Good: <500ms · Excellent: <200ms

Price/Performance

Cost efficiency ratios. Lower values indicate better value.

$/Speed: price per t/s · Price×TTFT: latency penalty

Compare pricing for all models side by side

Open AI API Cost Calculator →

AI Model Speed Rankings

Speed Metrics Guide

Tools

Guides

Comparisons