Home / Models / Meta / Llama 3.2 1B Instruct

Llama 3.2 1B Instruct pricing and routing profile

Llama 3.2 1B Instruct from Meta lists at $0.027 per million input tokens and $0.201 per million output tokens, with a 60,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.027
Output, per 1M tokens$0.201
Context window60K
Confidence signalNot exposed

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.0182
Chat reply (2,000 in, 400 out)$0.134
Retrieval-augmented answer (8,000 in, 500 out)$0.317

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for Llama 3.2 1B Instruct. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Cheaper models that can answer first

Models priced below Llama 3.2 1B Instruct that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
Granite 4.0 Micro$0.017 / $0.11241%
gpt-oss-20b$0.018 / $0.0946%
Ling 3.0 Flash$0.021 / $0.06350%
Ling 3.0 Flash VL$0.021 / $0.061650%
Mistral Nemo$0.019 / $0.0363%

Questions

How much does Llama 3.2 1B Instruct cost?

Llama 3.2 1B Instruct lists at $0.027 per million input tokens and $0.201 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.134 per 1,000 requests.

What is the context window of Llama 3.2 1B Instruct?

60,000 tokens.

Can a cheaper model replace Llama 3.2 1B Instruct?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Llama 3.2 1B Instruct on one half of your requests and make at most three answers worse on the other.