Confronto prezzi live

Ogni modello. Prezzi reali, zero ricarico.

Confronta prezzi pay-as-you-go trasparenti su 9 provider · 79 modelli, USD per 1M di token. In tempo reale da /api/pricing.

Ottieni la tua chiave API, gratis Calcolatore di costi LLM

OpenAI

21 modelli

Famiglia GPT · ragionamento di frontiera

Modello · Capacità

Contesto

Input/1M

Output/1M

Cache/1M

gpt-4o-mini-transcribe

16K

$1.25

$5.00

—

gpt-4o-transcribe

16K

$2.50

$10.00

—

gpt-4o-transcribe-diarize

16K

$2.50

—

gpt-5.2

400K

$1.75

$14.00

$0.875

gpt-5.2-codex

400K

$1.75

$14.00

$0.875

gpt-5.3-codex

400K

$1.75

$14.00

$0.875

gpt-5.4

922K

$2.50

$15.00

$1.25

gpt-5.4-mini

400K

$0.750

$4.50

$0.375

gpt-5.4-nano

400K

$0.200

$1.25

$0.100

gpt-5.4-pro

922K

$30.00

$180.00

$15.00

gpt-5.5

922K

$5.00

$30.00

$0.500

gpt-5.5-pro

1.1M

$30.00

$180.00

—

gpt-5.6

1.1M

$5.00

$30.00

$0.500

gpt-5.6-luna

1.1M

$1.00

$6.00

$0.100

gpt-5.6-sol

1.1M

$5.00

$30.00

$0.500

gpt-5.6-terra

1.1M

$2.50

$15.00

$0.250

gpt-image-1

—

$5.00

$40.00

—

gpt-image-1-mini

—

$2.00

$8.00

—

gpt-image-1.5

—

$5.00

$32.00

—

gpt-image-2

—

$5.00

$30.00

—

whisper-1

—

$0.006/min

—

Anthropic

9 modelli

Claude · contesto lungo, tool affidabili

Modello · Capacità

Contesto

Input/1M

Output/1M

Cache/1M

claude-fable-5

200K

$10.00

$50.00

$1.00

claude-haiku-4-5

200K

$1.00

$5.00

$0.100

claude-opus-4-5

200K

$5.00

$25.00

$0.500

claude-opus-4-6

$5.00

$25.00

$0.500

claude-opus-4-7

$5.00

$25.00

$0.500

claude-opus-4-8

$5.00

$25.00

$0.500

claude-sonnet-4-5

200K

$3.00

$15.00

$0.300

claude-sonnet-4-6

$3.00

$15.00

$0.300

claude-sonnet-5

$2.00

$10.00

$0.200

Google

13 modelli

Gemini · multimodale, contesto ampio

Modello · Capacità

Contesto

Input/1M

Output/1M

Cache/1M

chirp-2

—

$0.016/min

—

chirp-3

—

$0.016/min

—

gemini-2.5-flash

1.0M

$0.300

$2.50

$0.030

gemini-2.5-flash-image

—

$0.300

$30.00

—

gemini-2.5-flash-lite

1.0M

$0.100

$0.400

$0.010

gemini-2.5-pro

1.0M

$1.25

$10.00

$0.125

gemini-3-flash-preview

1.0M

$0.500

$3.00

$0.050

gemini-3-pro-image-preview

—

$2.00

$120.00

—

gemini-3.1-flash-image-preview

—

$0.500

$60.00

—

gemini-3.1-flash-lite-image

—

$0.250

$30.00

—

gemini-3.1-flash-lite-preview

1.0M

$0.250

$1.50

—

gemini-3.1-pro-preview

1.0M

$2.00

$12.00

$0.200

gemini-3.5-flash

1.0M

$1.50

$9.00

$0.150

Alibaba

19 modelli

Qwen · conveniente, open weights

Modello · Capacità

Contesto

Input/1M

Output/1M

Cache/1M

fun-asr

—

$0.002/min

—

fun-asr-flash

—

$0.002/min

—

fun-asr-mtl

—

$0.002/min

—

fun-asr-realtime

—

$0.002/min

—

paraformer-realtime-v2

—

$0.002/min

—

qwen-image-2.0

—

$0.04/call

—

qwen-image-2.0-pro

—

$0.07/call

—

qwen3-asr-flash

—

$0.002/min

—

qwen3-asr-flash-realtime

—

$0.002/min

—

qwen3-max

256K

$1.20+

$6.00

$0.359

qwen3-vl-flash

256K

$0.050+

$0.400

$0.022

qwen3-vl-plus

256K

$0.200+

$1.60

$0.143

qwen3.5-flash

1.0M

$0.100

$0.400

$0.029

qwen3.5-plus

1.0M

$0.400+

$2.40

$0.115

qwen3.6-flash

256K

$0.250

$1.50

$0.050

qwen3.7-max

$2.50

$7.50

$0.500

qwen3.7-plus

$0.400

$1.60

$0.080

wan2.7-image

—

$0.03/call

—

wan2.7-image-pro

—

$0.07/call

—

DeepSeek

2 modelli

DeepSeek · ragionamento solido, open weights

Modello · Capacità

Contesto

Input/1M

Output/1M

Cache/1M

deepseek-v4-flash

$0.138

$0.275

$0.003

deepseek-v4-pro

131K

$1.61

$3.22

$0.013

Moonshot

2 modelli

Kimi · contesto lungo

Modello · Capacità

Contesto

Input/1M

Output/1M

Cache/1M

kimi-k2.5

262K

$0.574

$3.01

$0.115

kimi-k2.7-code

256K

$0.950

$4.00

$0.190

MiniMax

1 modello

MiniMax · multimodale, agentico

Modello · Capacità

Contesto

Input/1M

Output/1M

Cache/1M

minimax-m3

$0.300

$1.20

$0.060

Z.ai

4 modelli

GLM · bilingue, tool use

Modello · Capacità

Contesto

Input/1M

Output/1M

Cache/1M

glm-5

200K

$1.00

$3.20

$0.200

glm-5-turbo

205K

$1.20

$4.00

$0.240

glm-5.1

200K

$1.40

$4.40

$0.260

glm-5.2

1.0M

$1.40

$4.40

$0.260

ByteDance

8 modelli

Doubao · inferenza ad alto throughput

Modello · Capacità

Contesto

Input/1M

Output/1M

Cache/1M

ByteDance-Seed-1.8

262K

$0.250+

$2.00

$0.050

Dola-Seed-2.0-lite

262K

$0.250+

$2.00

$0.050

Dola-Seed-2.0-mini

262K

$0.100+

$0.400

$0.020

Dola-Seed-2.0-pro

262K

$0.500+

$3.00

$0.100

seed-asr-bigmodel

—

$0.002/min

—

seedream-4-0-250828

—

$0.03/call

—

seedream-4-5-251128

—

$0.04/call

—

seedream-5-0-260128

—

$0.04/call

—

Note sui prezzi

Tutti i prezzi sono in USD. La fatturazione si basa sull'utilizzo effettivo di token.
Token di input = il tuo prompt. Token di output = la risposta del modello.
Prezzi a scaglioni: l'intero conteggio di token di una richiesta viene addebitato alla tariffa dello scaglione in cui rientra l'input. Input più grandi passano allo scaglione superiore.
Cache hit: quando lo stesso prefisso di prompt viene riutilizzato (context caching), i token di input sono fatturati alla tariffa scontata Cache/1M indicata sopra.
I modelli di generazione di immagini e audio sono fatturati per chiamata API.
Sconti sui volumi disponibili per i clienti enterprise. Contattaci.

Hai trovato il tuo modello? Inizia a chiamarlo in 60 secondi.

Ottieni la tua chiave API, gratis