Back to home
Cost
Compare input and output pricing across all AI models. Sorted by lowest input cost per million tokens.
RankModelScore
1
I
inclusionAI: Ling 2.6 flashinclusionai/ling-2.6-flash
$0.01
2I
IBM: Granite 4.0 Microibm-granite/granite-4.0-h-micro
$0.02
3Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct
$0.02
4Mistral Nemomistralai/mistral-nemo
$0.02
5Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct
$0.03
6gpt oss 20bopenai/gpt-oss-20b
$0.03
7L
LiquidAI: LFM2 24B A2Bliquid/lfm-2-24b-a2b
$0.03
8Amazon: Nova Micro 1.0amazon/nova-micro-v1
$0.04
9Command Rcohere/command-r7b-12-2024
$0.04
10gpt oss 120bopenai/gpt-oss-120b
$0.04
11Qwen: Qwen3.5 9Bqwen/qwen3.5-9b
$0.04
12NVIDIA: Nemotron Nano 9B V2nvidia/nemotron-nano-9b-v2
$0.04
13Gemma 3 4Bgoogle/gemma-3-4b-it
$0.04
14Gemma 3 12Bgoogle/gemma-3-12b-it
$0.04
15Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct
$0.04
16S
Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8b
$0.04
17Llama 3 8B Instructmeta-llama/llama-3-8b-instruct
$0.04
18Qwen: Qwen3 30B A3B Instruct 2qwen/qwen3-30b-a3b-instruct-2507
$0.04
19A
Arcee AI: Trinity Miniarcee-ai/trinity-mini
$0.04
20I
IBM: Granite 4.1 8Bibm-granite/granite-4.1-8b
$0.05
21NVIDIA: Nemotron 3 Nano 30B A3nvidia/nemotron-3-nano-30b-a3b
$0.05
22GPT-5openai/gpt-5-nano
$0.05
23Qwen: Qwen3 8Bqwen/qwen3-8b
$0.05
24Mistral Small 3mistralai/mistral-small-24b-instruct-2501
$0.05
25Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct
$0.05
26Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-it
$0.06
27Z
Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flash
$0.06
28Gemma 3n 4Bgoogle/gemma-3n-e4b-it
$0.06
29Amazon: Nova Lite 1.0amazon/nova-lite-v1
$0.06
30G
MythoMax 13Bgryphe/mythomax-l2-13b
$0.06
314 models tested