The Cheapest LLM API in 2026 (Ranked)

Looking for the cheapest LLM API? Below are the 15 lowest-cost models available today, sorted by blended price per million tokens (70% input + 30% output — the typical real-world mix). Pricing is sourced from official provider pages and refreshed weekly. For your own workload, plug your traffic into the cost calculator.
ModelInput / 1MOutput / 1MContext
gpt-oss 120B
OpenAI
$0.039$0.10131K
Mistral Small 24B
Mistral
$0.05$0.0833K
gpt-oss 20B
OpenAI
$0.03$0.14131K
MiMo V2.5
Xiaomi
$0.015$0.181000K
Gemma 4 31B
Google
$0.05$0.15256K
Hunyuan HY3 Preview
Tencent
$0.03$0.30256K
DeepSeek V4 Flash
DeepSeek
$0.07$0.271000K
NVIDIA Nemotron 3 Super
NVIDIA
$0.07$0.281000K
GPT-5.4 nano (xhigh)
OpenAI
$0.05$0.40400K
Llama 4 Scout 17B
Meta
$0.11$0.3410000K
Qwen3.6 35B A3B
Alibaba
$0.10$0.37262K
MiMo V2.5 Pro
Xiaomi
$0.04$0.581000K
Qwen3.6 Plus
Alibaba
$0.12$0.481000K
MiniMax M2.7
MiniMax
$0.05$0.70205K
Llama 3.3 70B Instruct
Meta
$0.23$0.40131K

How we rank "cheapest"

Raw input price alone is misleading — most real workloads generate 20–40% as many output tokens as input. We use a 70/30 input/output blend, which closely matches what production chat, RAG and agent workloads actually consume. If your workload is output-heavy (long-form generation, code), sort by output price separately on the comparison tool.

Cheap doesn't always mean cheap

A model that costs $0.05/1M tokens but needs 3x more tokens to solve the same task isn't cheaper. For reasoning, coding, and tool-use, look at cost per successful task, not cost per token. DeepSeek V4 Flash and Gemini 3.5 Flash currently offer the best intelligence-per-dollar in the <$1/1M tier.

When the cheapest tier is enough

Use a sub-$0.10/1M model when the task is: bulk classification, embedding-style retrieval rewrites, simple extraction, autocomplete, or first-pass routing. Escalate to a $1–$5/1M model only when the cheap tier fails — and log every escalation so you can measure the real cost of "smart enough".

Related: LLM Price Comparison 2026 — Frontier Models Ranked by Cost per Quality.

Frequently asked questions