Directories / Models / Cheapest Audio

Cheapest models for audio

Ranked by input $/Mtoken, then output. Speech and audio models.

1
Phi-4-multimodal-instruct
Microsoft · 128,000 context

Input

$0/M

Output

$0/M
2
Llama-3.2-11B-Vision-Instruct
Meta · 128,000 context

Input

$0/M

Output

$0/M
3
Llama-3.2-90B-Vision-Instruct
Meta · 128,000 context

Input

$0/M

Output

$0/M
4
magpie-tts-zeroshot
NVIDIA · 1 context

Input

$0/M

Output

$0/M
5
Nemotron 3 Nano Omni (free)
NVIDIA · 256,000 context

Input

$0/M

Output

$0/M
6
nemotron-voicechat
NVIDIA · 128,000 context

Input

$0/M

Output

$0/M
7
Whisper
OpenAI · 1 context

Input

$0/M

Output

$0/M
8
Whisper Large v3
OpenAI · 1 context

Input

$0/M

Output

$0/M
9
Auto Router (Beta)
Openrouter · 2,000,000 context

Input

$0/M

Output

$0/M
10
Auto Router
Openrouter · 2,000,000 context

Input

$0/M

Output

$0/M
11
Qwen3.5 122B A10B NVFP4
Qwen · 256,144 context

Input

$0/M

Output

$0/M
12
Qwen3.6 27B FP8
Qwen · 262,144 context

Input

$0/M

Output

$0/M
13
X-Ai/Grok 4.1 Fast Reasoning
xAI · 20,000,000 context

Input

$0/M

Output

$0/M
14
X-Ai/Grok-4-Fast-Non-Reasoning
xAI · 2,000,000 context

Input

$0/M

Output

$0/M
15
X-Ai/Grok-4-Fast-Reasoning
xAI · 2,000,000 context

Input

$0/M

Output

$0/M
16
Grok STT
xAI · 1 context

Input

$0/M

Output

$0/M
17
Grok Voice Think Fast 1.0
xAI · 1 context

Input

$0/M

Output

$0/M
18
KB Whisper
Kblab · 448 context

Input

$0.0023/M

Output

$0.0023/M
19
Whisper Large v3 Turbo
OpenAI · 448 context

Input

$0.0023/M

Output

$0.0023/M
20
Gemini-2.0-Flash-Lite
Google · 990,000 context

Input

$0.052/M

Output

$0.210/M
21
Google: Gemini 2.0 Flash Lite
Google · 1,048,576 context

Input

$0.075/M

Output

$0.300/M
22
Gemma 4 E2B IT
Google · 32,768 context

Input

$0.100/M

Output

$0.100/M
23
Voxtral Small 24B 2507
Mistral · 32,000 context

Input

$0.100/M

Output

$0.300/M
24
Gemini 2.5 Flash-Lite
Gemini · 1,048,576 context

Input

$0.100/M

Output

$0.400/M
25
Google: Gemini 2.0 Flash
Google · 1,048,576 context

Input

$0.100/M

Output

$0.400/M
26
Google: Gemini 2.5 Flash Lite Preview 09-2025
Google · 1,048,576 context

Input

$0.100/M

Output

$0.400/M
27
Gemini Flash-Lite Latest
Google · 1,048,576 context

Input

$0.100/M

Output

$0.400/M
28
Gemini-2.0-Flash
Google · 990,000 context

Input

$0.100/M

Output

$0.420/M
29
MiMo-V2.5
Xiaomi · 1,048,576 context

Input

$0.140/M

Output

$0.280/M
30
Gemma 4 E4B IT
Google · 32,768 context

Input

$0.200/M

Output

$0.200/M
31
Nemotron 3 Nano Omni 30B A3B Reasoning
NVIDIA · 262,144 context

Input

$0.200/M

Output

$0.800/M
32
Qwen3 Omni 30B A3B Instruct
Qwen · 65,536 context

Input

$0.250/M

Output

$0.970/M
33
Qwen3 Omni 30B A3B Thinking
Qwen · 65,536 context

Input

$0.250/M

Output

$0.970/M
34
Gemini 3.1 Flash Lite Preview
Google · 1,048,576 context

Input

$0.250/M

Output

$1.50/M
35
Gemini 3.1 Flash Lite
Google · 1,048,576 context

Input

$0.250/M

Output

$1.50/M
36
Gemini 2.5 Flash
Gemini · 1,048,576 context

Input

$0.300/M

Output

$2.50/M
37
MiMo-V2.5
Xiaomimimo · 262,144 context

Input

$0.400/M

Output

$2.00/M
38
MiMo V2 Omni
Xiaomi · 265,000 context

Input

$0.400/M

Output

$2.00/M
39
Gemini 3 Flash Preview
Google · 1,048,576 context

Input

$0.500/M

Output

$3.00/M
40
Gemini 3 Flash Preview
Gemini · 1,048,576 context

Input

$0.500/M

Output

$3.00/M

Full audio leaderboard → All models