Cheapest AI Models for Chat

Ranked from provider-published pricing · Prices checked November 17, 2026

Conversational workloads sit between the input-heavy and output-heavy extremes: a growing transcript goes in, a moderate reply comes out. This list ranks on an even 50/50 weighting for that balance.

The ranking

top 20 of 270

Ranked bya Balanced 50/50 Blend. Prices checked November 17, 2026.

Gemma 2 2B from Google leads this ranking at $0.0200/M. That is 98% below the $0.8000/M median across the 270 models that qualify for this list.

#ModelProvidera Balanced 50/50 BlendInput /1MOutput /1MContext
1Gemma 2 2BGoogle$0.0200/M$0.0200$0.02008,000
2Mistral NemoMistral$0.0295/M$0.0290$0.0300128,000
3Qwen2.5-1.5B-InstructQwen$0.0300/M$0.0300$0.030032,000
4Llama 3.2 1BMeta$0.0400/M$0.0400$0.0400128,000
5Phi-3-Mini-4K (NIM)Nvidia$0.0400/M$0.0400$0.04004,000
6Qwen2.5-3B-InstructQwen$0.0500/M$0.0500$0.050032,000
7ABAB 5.5cMiniMax$0.0500/M$0.0500$0.050016,000
8Llama 3.2 3BMeta$0.0600/M$0.0600$0.0600128,000
9Llama 3.2 3B (Groq)Groq$0.0600/M$0.0600$0.0600128,000
10Gemma 2 9B (DI)DeepInfra$0.0600/M$0.0600$0.06008,000
11Llama 3.1 8B (Groq)Groq$0.0650/M$0.0500$0.0800128,000
12Granite 3.1 2B InstructIBM$0.0650/M$0.0300$0.1000128,000
13Doubao-Lite-128kByteDance$0.0650/M$0.0400$0.0900128,000
14Doubao-Lite-32kByteDance$0.0650/M$0.0400$0.090032,000
15Mistral 7B (DI)DeepInfra$0.0700/M$0.0700$0.070032,000
16Mistral 7B (Lepton)Lepton AI$0.0700/M$0.0700$0.070032,000
17Mistral 7B v0.3Mistral$0.0800/M$0.0800$0.080032,000
18Nova MicroAmazon$0.0875/M$0.0350$0.1400128,000
19Gemma 2 9BGoogle$0.0900/M$0.0900$0.09008,000
20Gemini 1.5 Flash-8BGoogle$0.0938/M$0.0375$0.15001,000,000

How this list is built

  • Ranked cheapest first by a blended rate weighting input and output at 50/50. Symmetrical blend. Useful for back-and-forth chat workloads.
  • Excludes embed models.
  • Includes models marked available or preview; retired and deprecated SKUs are excluded.
  • Prices are the rates each provider publishes, not estimates. How the blended rate is calculated.

Frequently asked questions

What is the cheapest model for a chatbot?

On an even weighting of input and output token prices, the models at the top of this table are the cheapest we track. Remember that a chat transcript grows with every turn, so the input side of a long conversation costs more than it does on the first message, a large context window and cached-input pricing both help.

Related rankings

Price it for your workload

Rankings are recomputed on every deploy from the catalogue. Prices checked November 17, 2026.