← Back to Calculator

Cheapest LLM APIs in 2026

A data-driven ranking of all 19 AI models by estimated monthly cost. Based on 5M input + 2M output tokens — a typical monthly volume for a solo developer or small team. Updated 2026-06-29.

Full Ranking — Cheapest to Most Expensive

#ModelInput $/MOutput $/MEst. Monthly
1DeepSeek V4 Flash$0.14$0.28$1.26
2Gemini Flash Lite$0.10$0.40$1.30
3MiniMax M3$0.30$1.20$3.90
4DeepSeek V4 Pro$0.43$0.87$3.92
5Gemini 3.5 Flash$0.25$1.50$4.25
6Qwen 3 Coder$0.30$1.50$4.50
7Llama 4 Maverick$0.80$2.00$8.00
8Kimi K2.6$0.95$4.00$12.75
9Claude Haiku 4.5$1.00$5.00$15.00
10GPT-5.6 Luna$1.00$6.00$17.00
11Mistral Large 3$2.00$8.00$26.00
12Gemini 3.1 Pro$2.00$12.00$34.00
13GPT-5.6 Terra$2.50$15.00$42.50
14GPT-5.4$2.50$15.00$42.50
15GPT-5.3 Codex$2.50$15.00$42.50
16Claude Sonnet 4.6$3.00$15.00$45.00
17Claude Opus 4.8$5.00$25.00$75.00
18GPT-5.6 Sol$5.00$30.00$85.00
19Claude Fable 5$10.00$50.00$150.00

Estimated cost: 5,000,000 input + 2,000,000 output tokens/month, no caching, no batch. Your actual cost depends on your exact usage. Use the calculator for custom estimates →

Key Insights

115×

Price gap between cheapest (Gemini Flash Lite at $1.30/mo) and most expensive (Claude Fable 5 at $150/mo) for the same token volume.

$0.10/M

Gemini Flash Lite has the lowest input price of any model. At 10M input tokens/month, that's just $1.00.

Top 5

The top 5 cheapest models all come from Google (2), DeepSeek (2), and Alibaba (1). No Western provider cracks the top 5.

80.5

MiniMax M3's SWE-bench score at $0.30/M input — matching or beating models that cost 10× more.

Top 3 Cheapest Models — Detailed

#1DeepSeek V4 Flash

DeepSeek

$1.26/mo
Input: $0.14/M
Output: $0.28/M
Context: 1M
Max Output: 64K
SWE-bench: 79
Caching:
cheapestfastcoding

#2Gemini Flash Lite

Google

$1.30/mo
Input: $0.10/M
Output: $0.40/M
Context: 1M
Max Output: 64K
SWE-bench: 45
Caching:
cheapestfastsimple

#3MiniMax M3

MiniMax

$3.90/mo
Input: $0.30/M
Output: $1.20/M
Context: 1M
Max Output: 64K
SWE-bench: 80.5
Caching:
codingcheapopen-weight

Compare the Cheapest Models

📊 Find the cheapest model for your exact usage

Token volumes, caching, and input/output ratios change the ranking. Enter your numbers to see which model is truly cheapest for you.

Try the Calculator →