LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Llama 3.2 3B Instruct

meta·meta/llama-3.2-3b-instruct·GA·Open weights·llama series
Small instruction-tuned Llama model for multilingual dialogue and agentic retrieval

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·Eden AIGateway
$0.02 / $0.02
Blended $0.02 · 7.5× spread
Context
131,072
Output limit
131,072
Knowledge cutoff
2023-12
Released / updated
2024-09-25 / 2024-09-25
Capabilities
Reasoning✓ Tool useStructured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
License
Llama 3.2 Community License
Weights
Hugging Face

Llama 3.2 3B Instruct by meta is offered by 9 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Eden AI at $0.02 / $0.02 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 7.5× across the providers that host it.

The context window is 131,072 tokens at the reference host, but hosts report different limits, from 16,000 to 131,072, so the usable window depends on the provider you pick. It supports tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2023-12.

Available at 9 providers9 with public prices

  • ProviderInput / Output
  • Eden AIGateway
    deepinfra/meta-llama/Llama-3.2-3B-Instruct
    $0.02 / $0.02
    Context 131,072Output limit 131,072
  • InferenceGateway
    $0.02 / $0.02
    Context 16,000 ⚠Output limit 4,096
  • NanoGPTGateway
    $0.05 / $0.33
    Cache read $0.025Context 131,072Output limit 8,192
  • OpenRouterGateway
    $0.05 / $0.33
    Context 131,072Output limit 117,964
  • Kilo GatewayGateway
    $0.05 / $0.33
    Context 131,072Output limit 117,964
  • Eden AIGateway
    $0.051 / $0.34
    Context 80,000 ⚠Output limit 80,000
  • Hugging FaceCloud
    meta-llama/Llama-3.2-3B-Instruct
    $0.051 / $0.34
    Context 80,000 ⚠Output limit 80,000
  • Venice AIGateway
    llama-3.2-3b
    $0.15 / $0.60
    Context 128,000 ⚠Output limit 4,096
  • AutarchoGateway
    llama-32-3b-uncensored
    $0 / $3.00
    Context 131,072Output limit 131,072
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Eden AI
deepinfra/meta-llama/Llama-3.2-3B-Instruct
Gateway$0.02$0.02——131,072131,072
InferenceGateway$0.02$0.02——16,000 ⚠4,096
NanoGPTGateway$0.05$0.33$0.025—131,0728,192
OpenRouterGateway$0.05$0.33——131,072117,964
Kilo GatewayGateway$0.05$0.33——131,072117,964
Eden AIGateway$0.051$0.34——80,000 ⚠80,000
Hugging Face
meta-llama/Llama-3.2-3B-Instruct
Cloud$0.051$0.34——80,000 ⚠80,000
Venice AI
llama-3.2-3b
Gateway$0.15$0.60——128,000 ⚠4,096
Autarcho
llama-32-3b-uncensored
Gateway$0$3.00——131,072131,072

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1Eden AI$5.00
2Inference$5.00
3NanoGPT$23.50
4OpenRouter$26.50
5Kilo Gateway$26.50
6Eden AI$26.93
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.02

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-05). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

Omega Directive 24B Unslop v2.0same series—EVA-LLaMA-3.33-70B-v0.1same series—Llama 3.3 70B Instruct abliteratedsame series—Llama 3.2 1B Instructsame lab—Llama-3.3-70B-Instructsame lab—
Data partly from models.dev (MIT)