aiagent.club
中文

Model pricing

The cost of tokens across models on OpenRouter, ranked cheapest-first by input price — the falling cost of intelligence, measured daily. Real daily usage is shown where the model appears in usage data.

Cheapest models by input price

USD per million tokens, cheapest first. Priced models only — free tiers and unpriced variants excluded. Tokens/day shown where available. Trend is input price over time.

# Name $/Mtok in$/Mtok outContextTokens/day Price trend
1 inclusionAI: Ling-2.6-flash 0.010.03262.1k
2 IBM: Granite 4.0 Micro 0.0170.112131.0k
3 mistralai/mistral-nemo 0.0190.03131.1k40.8B
4 inclusionAI: Ling 3.0 Flash 0.0210.063262.1k
5 nex-agi/nex-n2-mini 0.0250.1262.1k29.6B
6 OpenAI: GPT-5 Nano (batch) 0.0250.2400.0k
7 Meta: Llama 3.2 1B Instruct 0.0270.20160.0k
8 openai/gpt-oss-20b 0.030.13131.1k36.3B
9 Qwen: Qwen3.7 Flash 0.030.131.0M
10 Inference.net: Schematron V2 Turbo 0.030.15128.0k
11 Amazon: Nova Micro 1.0 0.0350.14128.0k
12 openai/gpt-oss-120b 0.0370.17131.1k83.9B
13 Cohere: Command R7B (12-2024) 0.03750.15128.0k
14 Sao10K: Llama 3 8B Lunaris 0.040.058.2k
15 DeepSeek: DeepSeek V4 Flash Latest 0.040.11.3M
16 Inception: Mercury 2.5 Preview 0.040.15260.0k
17 Inception: Mercury 2.5 0.040.15260.0k
18 Tencent: Hy-MT2-1.8B 0.0440.1778.2k
19 Qwen: Qwen3 30B A3B Instruct 2507 0.048150.19305262.1k
20 IBM: Granite 4.1 8B 0.050.1131.1k
21 NVIDIA: Nemotron 3 Nano 30B A3B 0.050.2262.1k
22 OpenAI: GPT-5 Nano 0.050.4400.0k
23 Google: Gemma 3 4B 0.050.1131.1k
24 Google: Gemma 3 12B 0.050.15131.1k
25 Mistral: Mistral Small 3 0.050.0832.8k
26 Meta: Llama 3.2 3B Instruct 0.050.33131.1k
27 Meta: Llama 3.1 8B Instruct 0.050.08131.1k11.3B
28 Google: Gemini 2.5 Flash Lite (batch) 0.050.21.0M
29 OpenAI: GPT-4.1 Nano (batch) 0.050.21.0M
30 OpenAI: gpt-oss-20b (batch) 0.050.2131.1k
31 Inference.net: Schematron V2 Small 0.050.23128.0k
32 DeepSeek: DeepSeek V4 Flash 0731 0.0550.111.3M
33 Poolside: Laguna XS 2.1 0.060.12262.1k
34 Google: Gemma 3n 4B 0.060.1232.8k
35 Amazon: Nova Lite 1.0 0.060.24300.0k
36 MythoMax 13B 0.060.068.2k
37 IBM: Granite 4.2 8B 0.060.25131.1k
38 inclusionAI: Ling 3.0 Flash Fin 0.060.18262.1k
39 inclusionAI: Ling 3.0 Flash VL 0.060.18131.1k
40 Z.ai: GLM 4.7 Flash 0.06050.4200.0k

← All rankings