Back to home
Cost
Compare input and output pricing across all AI models. Sorted by lowest input cost per million tokens.
RankModelScore
1
Gemma 4 E4Bgoogle/gemma-4-e4b-non-reasoning
$0.02
2Llama 3.1 Instruct 8Bmeta/llama-3-1-instruct-8b
$0.02
3S
Sarvam 30Bsarvam/sarvam-30b
$0.03
4I
Granite 4.2 3Bibm/granite-4-2-3b
$0.03
5Qwen3.5 4Balibaba/qwen3-5-4b
$0.03
6I
Granite 3.3 8Bibm/granite-3-3-8b-instruct
$0.03
7Nova Microaws/nova-micro
$0.04
8NVIDIA Nemotron Nano 9B V2nvidia/nvidia-nemotron-nano-9b-v2-reasoning
$0.04
9M
HyperNova 60B 2605multiversecomputing/hypernova-60b
$0.04
10S
Sarvam 105Bsarvam/sarvam-105b
$0.04
11Llama 3 Instruct 8Bmeta/llama-3-instruct-8b
$0.04
12S
Agnes 3.0 Flashagnes-ai/agnes-3-0-flash
$0.05
13NVIDIA Nemotron 3 Nano 30B A3Bnvidia/nvidia-nemotron-3-nano-30b-a3b-reasoning
$0.05
14I
Granite 4.1 8Bibm/granite-4-1-8b
$0.05
15GPT-5openai/gpt-5-nano-minimal
$0.05
16Llama 2 Chat 7Bmeta/llama-2-chat-7b
$0.05
17Qwen2.5alibaba/qwen-turbo
$0.05
18gpt oss 20bopenai/gpt-oss-20b
$0.06
19Nemotron 3.5 Lightningnvidia/nemotron-3-5-lightning
$0.06
20I
Granite 4.0 H Smallibm/granite-4-0-h-small
$0.06
21I
Granite 4.2 8Bibm/granite-4-2-8b
$0.06
22Nova Liteaws/nova-lite
$0.06
23T
Hy3tencent/hy3-preview
$0.06
24Z
GLM 4.7 Flashzai/glm-4-7-flash
$0.07
25I
Ling 3.0 Flashinclusionai/ling-3-0-flash
$0.07
26Nemotron 3 Nano Omni 30B A3B Rnvidia/nemotron-3-nano-omni-30b-a3b
$0.09
27DeepSeek V4 Flashdeepseek/deepseek-v4-flash-0420-non-reasoning
$0.09
28Gemma 4 12Bgoogle/gemma-4-12b
$0.10
29Ministral 3 3Bmistral/ministral-3-3b
$0.10
30A
Olmo 3 7B Instructai2/olmo-3-7b-instruct
$0.10
255 models tested