Cheapest LLM APIs

The lowest-cost large language model APIs we track, ranked by combined input and output price per million tokens. Most of the cheapest options are open-weight models (DeepSeek, Qwen, GLM, MiniMax) served by competing providers — which is exactly why prices keep falling.

Ranking 50 options · updated October 4, 2026

# Model Provider Input /1M Output /1M
1 Llama 3.2 1B Instruct open Novita AI $0.020 $0.020
2 Llama 3.1 8B Instruct open Novita AI $0.020 $0.050
3 gpt-oss-20b open OpenRouter $0.018 $0.090
4 Llama 3.1 8B Instruct open OpenRouter $0.050 $0.080
5 Llama 3.1 8B Instruct open WaveSpeed AI $0.050 $0.080
6 Gemma 3 4B open OpenRouter $0.050 $0.100
7 Gemma 3 4B open DeepInfra $0.050 $0.100
8 Gemma 3 12B open Novita AI $0.050 $0.100
9 Qwen3.7 Flash OpenRouter $0.030 $0.130
10 Qwen3.7 Flash Alibaba Cloud $0.030 $0.130
11 Qwen3.7 Flash WaveSpeed AI $0.030 $0.130
12 gpt-oss-20b open DeepInfra $0.030 $0.140
13 gpt-oss-20b open Parasail $0.030 $0.150
14 Laguna XS 2.1 open OpenRouter $0.060 $0.120
15 GPT-6 Luna KIE AI $0.030 $0.150
16 DeepSeek V4 Flash open WaveSpeed AI $0.060 $0.120
17 Mercury 2.5 OpenRouter $0.040 $0.150
18 gpt-oss-20b open Novita AI $0.040 $0.150
19 Gemma 3 12B open OpenRouter $0.050 $0.150
20 Gemma 3 12B open DeepInfra $0.050 $0.150
21 GPT OSS 120B open DeepInfra $0.037 $0.170
22 GPT OSS 120B open OpenRouter $0.037 $0.170
23 GPT OSS 120B open WaveSpeed AI $0.037 $0.170
24 Llama 3.2 1B Instruct open Cloudflare Workers AI $0.027 $0.201
25 Llama 3.2 1B Instruct open OpenRouter $0.027 $0.201
26 Nemotron 3.5 Lightning open OpenRouter $0.059 $0.170
27 Gemma 3 27B open DeepInfra $0.080 $0.160
28 DeepSeek V4 Flash open DeepInfra $0.060 $0.180
29 Qwen 3.5 9B open DeepInfra $0.100 $0.150
30 Qwen 3.5 9B open OpenRouter $0.100 $0.150
31 Solar Mini 4 OpenRouter $0.050 $0.200
32 Qwen 3.5 9B open Venice AI $0.100 $0.150
33 DeepSeek V4 Flash open DeepInfra $0.090 $0.180
34 Laguna S 2.1 open OpenRouter $0.090 $0.180
35 Gemma 4 26B A4B open OpenRouter $0.068 $0.225
36 Ministral 3 8B open OpenRouter $0.150 $0.150
37 Nova Lite OpenRouter $0.060 $0.240
38 Ministral 3 8B open Mistral AI $0.150 $0.150
39 Nemotron 3.5 Lightning open Nebius $0.060 $0.240
40 GPT OSS 120B open Novita AI $0.050 $0.250
41 Granite 4.2 8B open OpenRouter $0.060 $0.250
42 Granite 4.2 8B open DeepInfra $0.060 $0.250
43 Gemma 3 27B open Novita AI $0.119 $0.200
44 Gemma 3 27B open Venice AI $0.120 $0.200
45 Qwen3 Coder 30B A3B Instruct open Novita AI $0.070 $0.270
46 Mistral Small 4 open Venice AI $0.094 $0.250
47 Mistral Small 3.2 24B open OpenRouter $0.094 $0.250
48 Qwen 3.5 9B open Parasail $0.100 $0.250
49 Qwen3 Coder 30B A3B Instruct open OpenRouter $0.070 $0.280
50 Qwen3 14B open OpenRouter $0.120 $0.240