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

510 models · click headers to sort

Model

Throughput ↓

TTFT

$/1M

$/Speed

Price×TTFT

Mercury 2

Inception

736 t/s

3.75s

$0.38

$0.001

1408.1

Granite 3.3 8B (Non-reasoning)

IBM

380 t/s

20.30s

$0.09

$0.000

1725.5

Nova Micro

Amazon

341 t/s

640ms

$0.06

$0.000

39.0

Qwen3.5 2B (Non-reasoning)

Alibaba

333 t/s

229ms

$0.04

$0.000

9.2

Nemotron 3 Nano Omni 30B A3B Reasoning

NVIDIA

308 t/s

580ms

$0.13

$0.000

76.0

Llama 3.1 Nemotron Instruct 70B

NVIDIA

284 t/s

260ms

$1.2

$0.004

312.0

Ministral 3 3B

Mistral

283 t/s

345ms

$0.10

$0.000

34.5

Gemini 3.1 Flash-Lite Preview

Google

277 t/s

5.00s

$0.56

$0.002

2813.9

Granite 4.0 H Small

IBM

267 t/s

8.77s

$0.11

$0.000

938.0

gpt-oss-20B (low)

OpenAI

266 t/s

420ms

$0.10

$0.000

39.9

gpt-oss-20B (high)

OpenAI

256 t/s

342ms

$0.09

$0.000

30.1

Qwen3.5 Omni Flash

Alibaba

249 t/s

1.05s

$0.28

$0.001

290.1

Sarvam 30B (high)

Sarvam

247 t/s

1.21s

$0.00

—

NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)

NVIDIA

234 t/s

714ms

$0.30

$0.001

214.2

gpt-oss-120B (low)

OpenAI

232 t/s

549ms

$0.26

$0.001

143.8

Gemini 2.5 Flash-Lite (Reasoning)

Google

230 t/s

19.07s

$0.17

$0.001

3336.5

LFM2 24B A2B

Liquid AI

227 t/s

292ms

$0.05

$0.000

15.2

Nova 2.0 Lite (Non-reasoning)

Amazon

227 t/s

865ms

$0.85

$0.004

735.3

Qwen3 0.6B (Reasoning)

Alibaba

226 t/s

911ms

$0.40

$0.002

362.6

Gemini 2.5 Flash-Lite (Non-reasoning)

Google

226 t/s

1.36s

$0.17

$0.001

238.7

Qwen3 0.6B (Non-reasoning)

Alibaba

224 t/s

877ms

$0.19

$0.001

164.9

Llama 3.1 Instruct 8B

Meta

223 t/s

478ms

$0.10

$0.000

47.8

Devstral Small (Jul '25)

Mistral

217 t/s

397ms

$0.15

$0.001

59.5

Nova Lite

Amazon

214 t/s

662ms

$0.10

$0.000

69.5

Gemini 2.5 Flash (Reasoning)

Google

212 t/s

10.54s

$0.85

$0.004

8955.6

Qwen3.5 0.8B (Non-reasoning)

Alibaba

210 t/s

282ms

$0.02

$0.000

5.6

gpt-oss-120B (high)

OpenAI

208 t/s

545ms

$0.26

$0.001

142.8

Qwen3.5 4B (Reasoning)

Alibaba

202 t/s

227ms

$0.06

$0.000

13.6

Gemini 2.5 Flash (Non-reasoning)

Google

199 t/s

524ms

$0.85

$0.004

445.4

Gemini 3 Flash Preview (Reasoning)

Google

197 t/s

5.65s

$1.1

$0.006

6358.5

Gemini 3 Flash Preview (Non-reasoning)

Google

194 t/s

780ms

$1.1

$0.006

877.5

Qwen3.5 4B (Non-reasoning)

Alibaba

191 t/s

231ms

$0.06

$0.000

13.9

Qwen3.6 35B A3B (Reasoning)

Alibaba

183 t/s

1.41s

$0.56

$0.003

787.6

GPT-5.1 Codex (high)

OpenAI

183 t/s

3.80s

$3.4

$0.019

13067.8

Jamba 1.6 Mini

AI21 Labs

182 t/s

798ms

$0.25

$0.001

199.5

Qwen3.6 35B A3B (Non-reasoning)

Alibaba

182 t/s

1.39s

$0.84

$0.005

1171.5

GPT-5.4 mini (xhigh)

OpenAI

178 t/s

3.93s

$1.7

$0.009

6640.6

GPT-5.1 Codex mini (high)

OpenAI

176 t/s

5.30s

$0.69

$0.004

3645.7

Grok 3 mini Reasoning (high)

xAI

173 t/s

467ms

$0.35

$0.002

163.5

GPT-5.4 mini (medium)

OpenAI

172 t/s

3.48s

$1.7

$0.010

5865.8

Qwen3 Next 80B A3B (Reasoning)

Alibaba

171 t/s

1.07s

$1.9

$0.011

1998.8

Qwen3 Next 80B A3B Instruct

Alibaba

171 t/s

1.06s

$0.88

$0.005

931.9

GPT-5 Codex (high)

OpenAI

171 t/s

6.50s

$3.4

$0.020

22329.8

GPT-5 (ChatGPT)

OpenAI

166 t/s

655ms

$3.4

$0.021

2251.9

Mistral Small 4 (Reasoning)

Mistral

165 t/s

573ms

$0.26

$0.002

150.1

GPT-5.4 nano (Non-Reasoning)

OpenAI

164 t/s

503ms

$0.46

$0.003

232.9

Step 3.5 Flash 2603

StepFun

164 t/s

793ms

$0.00

—

NVIDIA Nemotron 3 Super 120B A12B (Reasoning)

NVIDIA

161 t/s

968ms

$0.41

$0.003

398.8

Mistral Small 4 (Non-reasoning)

Mistral

161 t/s

506ms

$0.26

$0.002

132.6

Hy3-preview (Reasoning)

Tencent

159 t/s

2.26s

$0.00

—

Qwen3.5 122B A10B (Reasoning)

Alibaba

158 t/s

1.04s

$1.1

$0.007

1147.3

Nova 2.0 Lite (medium)

Amazon

158 t/s

10.59s

$0.85

$0.005

9002.4

Mistral Small (Sep '24)

Mistral

158 t/s

551ms

$0.30

$0.002

165.3

Mistral Small (Feb '24)

Mistral

157 t/s

511ms

$1.5

$0.010

766.5

GPT-5 nano (medium)

OpenAI

157 t/s

34.56s

$0.14

$0.001

4769.1

GPT-5.4 nano (medium)

OpenAI

156 t/s

3.90s

$0.46

$0.003

1805.7

GPT-5.4 mini (Non-Reasoning)

OpenAI

155 t/s

597ms

$1.7

$0.011

1007.7

Qwen3 Coder Next

Alibaba

155 t/s

863ms

$0.56

$0.004

485.9

Step 3.5 Flash

StepFun

154 t/s

881ms

$0.15

$0.001

132.1

Mistral Small 3

Mistral

154 t/s

493ms

$0.10

$0.001

51.3

Mistral Small 3.1

Mistral

153 t/s

506ms

$0.14

$0.001

69.8

Mistral Medium 3.5

Mistral

153 t/s

818ms

$3.0

$0.020

2454.0

Qwen3.5 122B A10B (Non-reasoning)

Alibaba

153 t/s

1.11s

$1.1

$0.007

1221.0

o4-mini (high)

OpenAI

152 t/s

19.29s

$1.9

$0.013

37129.4

Hy3-preview (Non-reasoning)

Tencent

152 t/s

2.31s

$0.00

—

Nova 2.0 Lite (low)

Amazon

152 t/s

5.62s

$0.85

$0.006

4780.4

Qwen3 30B A3B 2507 (Reasoning)

Alibaba

149 t/s

1.01s

$0.67

$0.005

683.1

Nova 2.0 Lite (high)

Amazon

149 t/s

20.02s

$0.85

$0.006

17017.8

GPT-5 nano (minimal)

OpenAI

149 t/s

794ms

$0.14

$0.001

109.6

Nova 2.0 Pro Preview (low)

Amazon

148 t/s

5.24s

$3.4

$0.023

18025.4

Nova 2.0 Pro Preview (Non-reasoning)

Amazon

148 t/s

743ms

$3.4

$0.023

2554.4

Sarvam 105B (high)

Sarvam

148 t/s

1.26s

$0.00

—

GPT-5.4 nano (xhigh)

OpenAI

147 t/s

3.04s

$0.46

$0.003

1405.2

GPT-5 nano (high)

OpenAI

147 t/s

72.61s

$0.14

$0.001

10019.9

o3-mini

OpenAI

143 t/s

9.20s

$1.9

$0.013

17715.8

Qwen3 VL 8B Instruct

Alibaba

142 t/s

1.08s

$0.31

$0.002

333.6

MiMo-V2-Flash (Reasoning)

Xiaomi

142 t/s

1.60s

$0.15

$0.001

240.1

MiMo-V2-Flash (Non-reasoning)

Xiaomi

141 t/s

1.43s

$0.15

$0.001

214.4

Qwen3 1.7B (Non-reasoning)

Alibaba

141 t/s

1.05s

$0.19

$0.001

196.8

Claude 4.5 Haiku (Reasoning)

Anthropic

139 t/s

8.33s

$2.2

$0.016

18217.3

Qwen3 1.7B (Reasoning)

Alibaba

139 t/s

977ms

$0.40

$0.003

388.8

NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

NVIDIA

139 t/s

700ms

$0.09

$0.001

60.2

Sarvam M (Reasoning)

Sarvam

139 t/s

1.19s

$0.00

—

o3-mini (high)

OpenAI

138 t/s

24.49s

$1.9

$0.014

47145.2

MiMo-V2-Flash (Feb 2026)

Xiaomi

137 t/s

1.56s

$0.15

$0.001

234.6

Qwen3 VL 8B (Reasoning)

Alibaba

134 t/s

1.14s

$0.66

$0.005

749.1

Trinity Large Thinking

Arcee AI

134 t/s

635ms

$0.40

$0.003

250.8

Llama 4 Scout

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