Back to home
Cost
Compare input and output pricing across all AI models. Sorted by lowest input cost per million tokens.
RankModelScore
1
Gemma 3n E4B Instructgoogle/gemma-3n-e4b
$0.02
2S
Sarvam 30Bsarvam/sarvam-30b
$0.03
3Qwen3.5 4Balibaba/qwen3-5-4b-non-reasoning
$0.03
4I
Granite 3.3 8Bibm/granite-3-3-8b-instruct
$0.03
5Nova Microaws/nova-micro
$0.04
6NVIDIA Nemotron Nano 9B V2nvidia/nvidia-nemotron-nano-9b-v2-reasoning
$0.04
7M
HyperNova 60B 2605multiversecomputing/hypernova-60b
$0.04
8S
Sarvam 105Bsarvam/sarvam-105b
$0.04
9Llama 3 Instruct 8Bmeta/llama-3-instruct-8b
$0.04
10gpt oss 20bopenai/gpt-oss-20b
$0.05
11NVIDIA Nemotron 3 Nano 30B A3Bnvidia/nvidia-nemotron-3-nano-30b-a3b
$0.05
12I
Granite 4.1 8Bibm/granite-4-1-8b
$0.05
13GPT-5openai/gpt-5-nano
$0.05
14Llama 2 Chat 7Bmeta/llama-2-chat-7b
$0.05
15Qwen2.5alibaba/qwen-turbo
$0.05
16I
Granite 4.0 H Smallibm/granite-4-0-h-small
$0.06
17Nova Liteaws/nova-lite
$0.06
18Z
GLM 4.7 Flashzai/glm-4-7-flash-non-reasoning
$0.07
19Nemotron 3 Nano Omni 30B A3B Rnvidia/nemotron-3-nano-omni-30b-a3b
$0.07
20Gemma 4 12Bgoogle/gemma-4-12b
$0.10
21Ministral 3 3Bmistral/ministral-3-3b
$0.10
22S
Step 3.5 Flash 2603stepfun/step-3-5-flash
$0.10
23A
Olmo 3 7B Instructai2/olmo-3-7b-instruct
$0.10
24S
Apertus 8B Instructswiss-ai-initiative/apertus-8b-instruct
$0.10
25Qwen3.5 9Balibaba/qwen3-5-9b
$0.10
26Qwen3.5 Omni Flashalibaba/qwen3-5-omni-flash
$0.10
27I
Ling 2.6 Flashinclusionai/ling-2-6-flash
$0.10
28GPT 4.1 nanoopenai/gpt-4-1-nano
$0.10
29Llama 3.1 Instruct 8Bmeta/llama-3-1-instruct-8b
$0.10
30Llama 3.2 Instruct 1Bmeta/llama-3-2-instruct-1b
$0.10
238 models tested