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

446 models · click headers to sort

Model

Throughput ↓

TTFT

$/1M

$/Speed

Price×TTFT

Mercury 2

Inception

907 t/s

3.76s

$0.38

$0.000

1409.3

Granite 4.0 H Small

IBM

524 t/s

8.68s

$0.11

$0.000

928.7

Granite 3.3 8B (Non-reasoning)

IBM

386 t/s

7.20s

$0.09

$0.000

612.3

Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)

Google

365 t/s

3.39s

$0.17

$0.000

592.6

NVIDIA Nemotron 3 Super 120B A12B (Reasoning)

NVIDIA

363 t/s

549ms

$0.41

$0.001

226.2

Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

Google

344 t/s

363ms

$0.17

$0.001

63.5

Gemini 2.5 Flash-Lite (Non-reasoning)

Google

328 t/s

250ms

$0.17

$0.001

43.8

gpt-oss-20B (low)

OpenAI

320 t/s

451ms

$0.09

$0.000

42.4

Gemini 2.5 Flash-Lite (Reasoning)

Google

318 t/s

18.42s

$0.17

$0.001

3223.3

gpt-oss-20B (high)

OpenAI

316 t/s

433ms

$0.09

$0.000

40.7

Nova Micro

Amazon

305 t/s

351ms

$0.06

$0.000

21.4

Devstral Small (Jul '25)

Mistral

301 t/s

345ms

$0.15

$0.000

51.8

Ministral 3 3B

Mistral

299 t/s

258ms

$0.10

$0.000

25.8

gpt-oss-120B (low)

OpenAI

253 t/s

503ms

$0.26

$0.001

132.3

gpt-oss-120B (high)

OpenAI

252 t/s

486ms

$0.26

$0.001

127.8

Grok 4.20 Beta 0309 (Reasoning)

xAI

238 t/s

10.94s

$3.0

$0.013

32811.0

Nova 2.0 Omni (Non-reasoning)

Amazon

229 t/s

670ms

$0.85

$0.004

569.5

Gemini 2.5 Flash (Reasoning)

Google

226 t/s

12.02s

$0.85

$0.004

10217.9

Nova 2.0 Lite (low)

Amazon

224 t/s

3.55s

$0.85

$0.004

3014.1

GPT-5.4 mini (xhigh)

OpenAI

219 t/s

3.82s

$1.7

$0.008

6443.1

GPT-5 Codex (high)

OpenAI

216 t/s

12.05s

$3.4

$0.016

41421.0

Gemini 3.1 Flash-Lite Preview

Google

216 t/s

7.25s

$0.56

$0.003

4080.6

LFM2 24B A2B

Liquid AI

213 t/s

224ms

$0.05

$0.000

11.6

Gemini 2.5 Flash (Non-reasoning)

Google

212 t/s

404ms

$0.85

$0.004

343.4

Qwen3 0.6B (Non-reasoning)

Alibaba

211 t/s

848ms

$0.19

$0.001

159.4

Nova 2.0 Lite (medium)

Amazon

206 t/s

10.32s

$0.85

$0.004

8776.3

Qwen3 0.6B (Reasoning)

Alibaba

205 t/s

872ms

$0.40

$0.002

347.1

GPT-5.4 mini (Non-Reasoning)

OpenAI

202 t/s

476ms

$1.7

$0.008

803.5

GPT-5.4 mini (medium)

OpenAI

200 t/s

3.77s

$1.7

$0.008

6372.2

Nova Lite

Amazon

200 t/s

399ms

$0.10

$0.001

41.9

Mistral Small 3.2

Mistral

196 t/s

313ms

$0.15

$0.001

46.9

Grok 3 mini Reasoning (high)

xAI

196 t/s

390ms

$0.35

$0.002

136.5

Devstral Small 2

Mistral

195 t/s

343ms

$0.00

—

Llama 3.1 Instruct 8B

Meta

193 t/s

474ms

$0.10

$0.001

47.4

Ministral 3 8B

Mistral

192 t/s

279ms

$0.15

$0.001

41.9

Gemini 3 Flash Preview (Non-reasoning)

Google

190 t/s

1.23s

$1.1

$0.006

1378.1

Grok 4.20 Beta 0309 (Non-reasoning)

xAI

189 t/s

309ms

$3.0

$0.016

927.0

GPT-5.1 Codex mini (high)

OpenAI

188 t/s

5.81s

$0.69

$0.004

3998.0

Mistral 7B Instruct

Mistral

187 t/s

274ms

$0.25

$0.001

68.5

Grok Code Fast 1

xAI

186 t/s

2.79s

$0.53

$0.003

1466.8

Jamba 1.6 Mini

AI21 Labs

184 t/s

607ms

$0.25

$0.001

151.8

Magistral Small 1.2

Mistral

184 t/s

327ms

$0.75

$0.004

245.3

Mistral Small (Sep '24)

Mistral

184 t/s

417ms

$0.30

$0.002

125.1

Mistral Small 3.1

Mistral

182 t/s

414ms

$0.15

$0.001

62.1

Gemini 3 Flash Preview (Reasoning)

Google

180 t/s

6.08s

$1.1

$0.006

6841.1

GPT-5.4 nano (xhigh)

OpenAI

178 t/s

2.94s

$0.46

$0.003

1363.5

Sarvam 30B (high)

Sarvam

178 t/s

1.21s

$0.00

—

GPT-5.4 nano (Non-Reasoning)

OpenAI

177 t/s

466ms

$0.46

$0.003

215.8

Nova 2.0 Lite (Non-reasoning)

Amazon

175 t/s

564ms

$0.85

$0.005

479.4

Mistral Small (Feb '24)

Mistral

174 t/s

411ms

$1.5

$0.009

616.5

GPT-5.4 nano (medium)

OpenAI

169 t/s

2.65s

$0.46

$0.003

1227.9

Qwen3 Coder Next

Alibaba

165 t/s

983ms

$0.60

$0.004

589.8

GPT-5 nano (medium)

OpenAI

164 t/s

41.55s

$0.14

$0.001

5733.6

Mistral Small 3

Mistral

163 t/s

414ms

$0.15

$0.001

62.1

Mistral Small 4 (Non-reasoning)

Mistral

163 t/s

408ms

$0.26

$0.002

107.3

Nova 2.0 Pro Preview (Non-reasoning)

Amazon

163 t/s

473ms

$3.4

$0.021

1626.2

GPT-4.1 nano

OpenAI

159 t/s

446ms

$0.17

$0.001

78.0

GPT-5 nano (minimal)

OpenAI

158 t/s

775ms

$0.14

$0.001

107.0

NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

NVIDIA

154 t/s

570ms

$0.09

$0.001

49.0

Nova 2.0 Pro Preview (medium)

Amazon

154 t/s

14.17s

$3.4

$0.022

48713.0

Qwen3 Next 80B A3B Instruct

Alibaba

154 t/s

972ms

$0.88

$0.006

850.5

o3-mini

OpenAI

153 t/s

7.38s

$1.9

$0.013

14212.3

GPT-5 nano (high)

OpenAI

151 t/s

80.65s

$0.14

$0.001

11129.1

Qwen3 Next 80B A3B (Reasoning)

Alibaba

151 t/s

1.01s

$1.9

$0.012

1903.1

Nova 2.0 Pro Preview (low)

Amazon

149 t/s

5.32s

$3.4

$0.023

18273.0

Qwen3.5 122B A10B (Non-reasoning)

Alibaba

148 t/s

997ms

$1.1

$0.007

1096.7

GPT-5 (ChatGPT)

OpenAI

148 t/s

657ms

$3.4

$0.023

2258.8

o3-mini (high)

OpenAI

147 t/s

23.74s

$1.9

$0.013

45705.3

Apriel-v1.5-15B-Thinker

ServiceNow

146 t/s

186ms

$0.00

—

o4-mini (high)

OpenAI

143 t/s

26.75s

$1.9

$0.013

51491.8

Qwen3 30B A3B 2507 (Reasoning)

Alibaba

142 t/s

972ms

$0.75

$0.005

729.0

Qwen3 VL 8B Instruct

Alibaba

141 t/s

1.05s

$0.31

$0.002

327.0

Qwen3 1.7B (Reasoning)

Alibaba

140 t/s

879ms

$0.40

$0.003

349.8

Sarvam 105B (high)

Sarvam

140 t/s

1.31s

$0.00

—

Qwen3 1.7B (Non-reasoning)

Alibaba

139 t/s

993ms

$0.19

$0.001

186.7

Apriel-v1.6-15B-Thinker

ServiceNow

139 t/s

203ms

$0.00

—

Devstral Medium

Mistral

139 t/s

406ms

$0.80

$0.006

324.8

Claude 4.5 Haiku (Reasoning)

Anthropic

139 t/s

9.86s

$2.0

$0.014

19718.0

GPT-5.1 Codex (high)

OpenAI

139 t/s

7.13s

$3.4

$0.025

24509.5

Grok 4.1 Fast (Reasoning)

xAI

139 t/s

8.22s

$0.28

$0.002

2259.4

Grok 4.1 Fast (Non-reasoning)

xAI

138 t/s

316ms

$0.28

$0.002

86.9

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)

NVIDIA

138 t/s

1.00s

$0.10

$0.001

105.1

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

NVIDIA

138 t/s

526ms

$0.30

$0.002

157.8

Qwen3 VL 8B (Reasoning)

Alibaba

135 t/s

1.01s

$0.66

$0.005

666.6

Qwen3.5 122B A10B (Reasoning)

Alibaba

134 t/s

1.02s

$1.1

$0.008

1127.5

Claude 3 Haiku

Anthropic

133 t/s

459ms

$0.50

$0.004

229.5

Apertus 8B Instruct

Swiss AI Initiative

133 t/s

1.84s

$0.13

$0.001

230.6

NVIDIA Nemotron Nano 12B v2 VL (Reasoning)

NVIDIA

132 t/s

229ms

$0.30

$0.002

68.7

MiMo-V2-Flash (Feb 2026)

Xiaomi

131 t/s

1.60s

$0.15

$0.001

240.8

Gemini 2.5 Pro

Google

131 t/s

21.11s

$3.4

$0.026

72562.4

MiMo-V2-Flash (Non-reasoning)

Xiaomi

130 t/s

1.31s

$0.15

$0.001

196.6

Qwen3 VL 30B A3B (Reasoning)

Alibaba

130 t/s

992ms

$0.75

$0.006

744.0

LongCat Flash Lite

LongCat

129 t/s

3.24s

$0.00

—

Qwen3 VL 30B A3B Instruct

Alibaba

129 t/s

965ms

$0.35

$0.003

337.8

Llama 4 Scout

Meta

129 t/s

451ms

$0.29

$0.002

131.7

Llama 4 Maverick

Meta

127 t/s

475ms

$0.49

$0.004

231.3

NVIDIA Nemotron Nano 9B V2 (Reasoning)

NVIDIA

127 t/s

246ms

$0.07

$0.001

17.2

MiMo-V2-Flash (Reasoning)

Xiaomi

125 t/s

1.49s

$0.15

$0.001

223.8

GPT-5.2 Codex (xhigh)

OpenAI

123 t/s

9.13s

$4.8

$0.039

43918.6

100

Llama 2 Chat 7B

Meta

123 t/s

846ms

$0.10

$0.001

84.6

Showing top 100 of 446 models. Use search/filter to narrow down.

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