|
Qwen3-LiveTranslate Flash Realtime
alibaba/qwen3-livetranslate-flash-realtime
Input
text
image
audio
video
Output
text
audio
|
Alibaba
|
qwen3-livetranslate-flash-realtime |
53,248 |
|
Reasoning
Tools
|
|
Qwen3 Omni 30B A3B Instruct
novita_ai/qwen/qwen3-omni-30b-a3b-instruct
Input
text
video
audio
image
Output
text
audio
|
NovitaAI
|
qwen3-omni-30b-a3b-instruct |
65,536 |
In: $0.25/1M
Out: $0.97/1M
|
Reasoning
Tools
|
|
Qwen3 Omni 30B A3B Thinking
novita-ai/qwen/qwen3-omni-30b-a3b-thinking
Input
text
image
video
audio
Output
text
|
Novita AI
|
qwen |
65,536 |
In: $0.25/1M
Out: $0.97/1M
|
Reasoning
Tools
|
|
Qwen3 Omni 30B A3B Thinking
novita_ai/qwen/qwen3-omni-30b-a3b-thinking
Input
text
audio
video
image
Output
text
|
NovitaAI
|
qwen3-omni-30b-a3b-thinking |
65,536 |
In: $0.25/1M
Out: $0.97/1M
|
Reasoning
Tools
|
|
Qwen3-Omni Flash
alibaba-cn/qwen3-omni-flash
Input
text
image
audio
video
Output
text
audio
|
Alibaba (China)
|
qwen |
65,536 |
In: $0.058/1M
Out: $0.23/1M
|
Reasoning
Tools
|
|
Qwen3-Omni Flash
alibaba_cn/qwen3-omni-flash
Input
text
image
audio
video
Output
text
audio
|
Alibaba (China)
|
qwen3-omni-flash |
65,536 |
In: $0.058/1M
Out: $0.23/1M
|
Reasoning
Tools
|
|
Qwen3-Omni Flash
alibaba/qwen3-omni-flash
Input
text
image
audio
video
Output
text
audio
|
Alibaba
|
qwen3-omni-flash |
65,536 |
In: $0.43/1M
Out: $1.66/1M
|
Reasoning
Tools
|
|
Qwen3-Omni Flash Realtime
alibaba-cn/qwen3-omni-flash-realtime
Input
text
image
audio
Output
text
audio
|
Alibaba (China)
|
qwen |
65,536 |
In: $0.23/1M
Out: $0.918/1M
|
Reasoning
Tools
|
|
Qwen3-Omni Flash Realtime
alibaba_cn/qwen3-omni-flash-realtime
Input
text
image
audio
Output
text
audio
|
Alibaba (China)
|
qwen3-omni-flash-realtime |
65,536 |
In: $0.23/1M
Out: $0.918/1M
|
Reasoning
Tools
|
|
Qwen3-Omni Flash Realtime
alibaba/qwen3-omni-flash-realtime
Input
text
image
audio
video
Output
text
audio
|
Alibaba
|
qwen3-omni-flash-realtime |
65,536 |
In: $0.52/1M
Out: $1.99/1M
|
Reasoning
Tools
|
|
Qwen3 TTS VoiceDesign
digitalocean/qwen3-tts-voicedesign
Input
text
Output
audio
|
DigitalOcean
|
qwen |
32,768 |
|
Reasoning
Tools
|
|
Qwen-Omni Turbo
alibaba-cn/qwen-omni-turbo
Input
text
image
audio
video
Output
text
audio
|
Alibaba (China)
|
qwen |
32,768 |
In: $0.058/1M
Out: $0.23/1M
|
Reasoning
Tools
|
|
Qwen-Omni Turbo
alibaba_cn/qwen-omni-turbo
Input
text
image
audio
video
Output
text
audio
|
Alibaba (China)
|
qwen-omni-turbo |
32,768 |
In: $0.058/1M
Out: $0.23/1M
|
Reasoning
Tools
|
|
Qwen-Omni Turbo
alibaba/qwen-omni-turbo
Input
text
image
audio
video
Output
text
audio
|
Alibaba
|
qwen-omni-turbo |
32,768 |
In: $0.07/1M
Out: $0.27/1M
|
Reasoning
Tools
|
|
Qwen-Omni Turbo Realtime
alibaba-cn/qwen-omni-turbo-realtime
Input
text
image
audio
Output
text
audio
|
Alibaba (China)
|
qwen |
32,768 |
In: $0.23/1M
Out: $0.918/1M
|
Reasoning
Tools
|
|
Qwen-Omni Turbo Realtime
alibaba_cn/qwen-omni-turbo-realtime
Input
text
image
audio
Output
text
audio
|
Alibaba (China)
|
qwen-omni-turbo-realtime |
32,768 |
In: $0.23/1M
Out: $0.918/1M
|
Reasoning
Tools
|
|
Qwen-Omni Turbo Realtime
alibaba/qwen-omni-turbo-realtime
Input
text
image
audio
Output
text
audio
|
Alibaba
|
qwen-omni-turbo-realtime |
32,768 |
In: $0.27/1M
Out: $1.07/1M
|
Reasoning
Tools
|
|
Qwen/Qwen3-Omni-30B-A3B-Captioner
siliconflow_cn/Qwen/Qwen3-Omni-30B-A3B-Captioner
Input
audio
Output
text
|
SiliconFlow (China)
|
qwen3-omni-30b-a3b-captioner |
66,000 |
|
Reasoning
Tools
|
|
Qwen/Qwen3-Omni-30B-A3B-Captioner
siliconflow/Qwen/Qwen3-Omni-30B-A3B-Captioner
Input
audio
Output
text
|
SiliconFlow
|
qwen3-omni-30b-a3b-captioner |
66,000 |
|
Reasoning
Tools
|
|
Qwen/Qwen3-Omni-30B-A3B-Instruct
siliconflow_cn/Qwen/Qwen3-Omni-30B-A3B-Instruct
Input
text
image
audio
Output
text
|
SiliconFlow (China)
|
qwen3-omni-30b-a3b-instruct |
66,000 |
|
Reasoning
Tools
|
|
Qwen/Qwen3-Omni-30B-A3B-Instruct
siliconflow/Qwen/Qwen3-Omni-30B-A3B-Instruct
Input
text
image
audio
Output
text
|
SiliconFlow
|
qwen3-omni-30b-a3b-instruct |
66,000 |
|
Reasoning
Tools
|
|
Qwen/Qwen3-Omni-30B-A3B-Thinking
siliconflow_cn/Qwen/Qwen3-Omni-30B-A3B-Thinking
Input
text
image
audio
Output
text
|
SiliconFlow (China)
|
qwen3-omni-30b-a3b-thinking |
66,000 |
|
Reasoning
Tools
|
|
Qwen/Qwen3-Omni-30B-A3B-Thinking
siliconflow/Qwen/Qwen3-Omni-30B-A3B-Thinking
Input
text
image
audio
Output
text
|
SiliconFlow
|
qwen3-omni-30b-a3b-thinking |
66,000 |
|
Reasoning
Tools
|
|
Qwen VL-MAX-2025-01-25
qiniu-ai/qwen-vl-max-2025-01-25
Input
text
image
audio
video
Output
text
|
Qiniu
|
qwen-vl-max |
128,000 |
|
Reasoning
Tools
|
|
Qwen VL-MAX-2025-01-25
qiniu_ai/qwen-vl-max-2025-01-25
Input
text
image
audio
video
Output
text
|
Qiniu
|
qwen-vl-max |
128,000 |
|
Reasoning
Tools
|
|
S1
vercel/fish-audio/s1
Input
text
Output
audio
|
Vercel AI Gateway
|
— |
0 |
|
Reasoning
Tools
|
|
S2.1 Pro
vercel/fish-audio/s2.1-pro
Input
text
Output
audio
|
Vercel AI Gateway
|
s2.1-pro |
0 |
|
Reasoning
Tools
|
|
S2 Pro
vercel/fish-audio/s2-pro
Input
text
Output
audio
|
Vercel AI Gateway
|
s2-pro |
0 |
|
Reasoning
Tools
|
|
Stable Audio 2.5 (Text-to-Audio)
digitalocean/fal-ai/stable-audio-25/text-to-audio
Input
text
Output
audio
|
DigitalOcean
|
text-to-audio |
0 |
|
Reasoning
Tools
|
|
StepAudio 2.5 ASR
stepfun-ai/stepaudio-2.5-asr
Input
audio
Output
text
|
StepFun (Global)
|
step |
0 |
|
Reasoning
Tools
|
|
StepAudio 2.5 ASR
stepfun/stepaudio-2.5-asr
Input
audio
Output
text
|
StepFun
|
step |
0 |
|
Reasoning
Tools
|
|
StepAudio 2.5 TTS
stepfun-ai/stepaudio-2.5-tts
Input
text
Output
audio
|
StepFun (Global)
|
step |
0 |
|
Reasoning
Tools
|
|
StepAudio 2.5 TTS
stepfun/stepaudio-2.5-tts
Input
text
Output
audio
|
StepFun
|
step |
0 |
|
Reasoning
Tools
|
|
Step TTS 2
stepfun-ai/step-tts-2
Input
text
Output
audio
|
StepFun (Global)
|
step |
0 |
|
Reasoning
Tools
|
|
Step TTS 2
stepfun/step-tts-2
Input
text
Output
audio
|
StepFun
|
step |
0 |
|
Reasoning
Tools
|
|
Thinking Machines: Inkling Small (free)
kilo/thinkingmachines/inkling-small:free
Input
text
image
audio
Output
text
|
Kilo Gateway
|
ling |
1,048,576 |
|
Reasoning
Tools
|
|
Transcribe-1
vercel/fish-audio/transcribe-1
Input
audio
Output
text
|
Vercel AI Gateway
|
transcribe-1 |
0 |
|
Reasoning
Tools
|
|
TTS-1
vercel/openai/tts-1
Input
text
Output
audio
|
Vercel AI Gateway
|
tts-1 |
0 |
|
Reasoning
Tools
|
|
TTS-1 HD
vercel/openai/tts-1-hd
Input
text
Output
audio
|
Vercel AI Gateway
|
tts-1-hd |
0 |
|
Reasoning
Tools
|
|
Vision Large
vispark/vispark/vision-large
Input
text
image
audio
video
pdf
Output
text
|
Vispark
|
vision-large |
1,000,000 |
In: $7.37/1M
Out: $22.11/1M
|
Reasoning
Tools
|
|
Vision Medium
vispark/vispark/vision-medium
Input
text
image
audio
video
pdf
Output
text
|
Vispark
|
vision-medium |
1,000,000 |
In: $4.21/1M
Out: $12.63/1M
|
Reasoning
Tools
|
|
Vision Small
vispark/vispark/vision-small
Input
text
image
audio
video
pdf
Output
text
|
Vispark
|
vision-small |
1,000,000 |
In: $1.05/1M
Out: $3.16/1M
|
Reasoning
Tools
|
|
Voxtral Mini 3B
privatemode-ai/voxtral-mini-3b
Input
audio
Output
text
|
Privatemode AI
|
voxtral |
32,000 |
In: $0.00462/1M
Out: $0/1M
|
Reasoning
Tools
|
|
Voxtral Mini 3B 2507
amazon-bedrock/mistral.voxtral-mini-3b-2507
Input
text
audio
Output
text
|
Amazon Bedrock
|
voxtral |
32,768 |
In: $0.04/1M
Out: $0.04/1M
|
Reasoning
Tools
|
|
Voxtral Mini 3B 2507
amazon_bedrock/mistral.voxtral-mini-3b-2507
Input
audio
text
Output
text
|
Amazon Bedrock
|
mistral.voxtral-mini-3b |
128,000 |
In: $0.04/1M
Out: $0.04/1M
|
Reasoning
Tools
|
|
Voxtral Mini 3B 2507 (Amazon Bedrock)
edenai/amazon/mistral.voxtral-mini-3b-2507
Input
text
audio
Output
text
|
Eden AI
|
voxtral |
32,768 |
In: $0.04/1M
Out: $0.04/1M
|
Reasoning
Tools
|
|
Voxtral Mini 3B 2507 (Amazon Bedrock, US)
edenai/amazon/mistral.voxtral-mini-3b-2507@us
Input
text
audio
Output
text
|
Eden AI
|
voxtral |
32,768 |
In: $0.04/1M
Out: $0.04/1M
|
Reasoning
Tools
|
|
Voxtral Mini (latest)
mistral/voxtral-mini-latest
Input
audio
Output
text
|
Mistral
|
voxtral |
0 |
|
Reasoning
Tools
|
|
Voxtral Mini TTS (latest)
mistral/voxtral-mini-tts-latest
Input
text
Output
audio
|
Mistral
|
voxtral |
0 |
|
Reasoning
Tools
|
|
Voxtral Small
mistral/voxtral-small-2507
Input
text
audio
Output
text
|
Mistral
|
voxtral |
32,768 |
|
Reasoning
Tools
|