← Models

Meta · current

Llama 3.2 3B

Llama 3.2 3B is attributed to Meta in the catalog. It accepts text input and produces text output. Reported capabilities include tool calling.

Compare model

Modalities

Hosted provider token rates

$0.15 / $0.60

USD per 1M input / output tokens · Venice AI

Context

128K

Released

2024-09-25

Knowledge cutoff

Dec 2023

No recent lab-operated provider rate is available. Showing the third-party host with the lowest input rate + ¼ output rate. This is one offering, not an average; other providers, modalities, tiers, and fees may differ.

Where to use it

2 observed offerings · token prices in USD per million where available

Estimate your workload cost
Venice AI

llama-3.2-3b

current

Input

$0.15

Output

$0.60

Cache

—

Context

128K

Max output

4K
Reasoning
No
Tool calling
Yes
Structured output
Unknown
Temperature
Yes

Recent price

Pioneer

meta-llama/Llama-3.2-3B

deprecated

Input

$0.10

Output

$0.10

Cache

$0.10

Context

131K

Max output

131K
Reasoning
No
Tool calling
No
Structured output
Unknown
Temperature
Yes

Historical price

Limits and capabilities reflect each provider’s listed offering. Unknown means support was not reported.

Capabilities and limits

Input
text
Output
text
Max output
4K
Weights
Open (source-reported)
Release
2024-09-25
Knowledge cutoff
Dec 2023
Family
llama

Tool calling

Provider-specific limits and support can differ.

Plan a model evaluation

Evaluate quality and latency on examples from your intended use before choosing a model.

Explore available evidence

Models to compare

Candidates match reported specifications; they are not tested replacements.

Model and price history

Latest recorded change: source refresh · 2026-10-23

Model changes (3)
  • source refresh · 2026-10-23
    {
      "before": {
        "status": "deprecated",
        "canonical_name": "Llama-3.2-3B",
        "context_tokens": 131072,
        "supports_tools": false,
        "max_output_tokens": 131072
      },
      "after": {
        "status": "current",
        "canonical_name": "Llama 3.2 3B",
        "context_tokens": 128000,
        "supports_tools": true,
        "max_output_tokens": 4096
      }
    }
  • source refresh · 2026-10-21
    {
      "before": {
        "status": "current"
      },
      "after": {
        "status": "deprecated"
      }
    }
  • source refresh · 2026-10-12
    {
      "before": {
        "knowledge_cutoff_reported": null
      },
      "after": {
        "knowledge_cutoff_reported": "2023-12"
      }
    }
Price history (42 observations)
DateProviderInput / output
2026-11-02Venice AI$0.15 / $0.60
2026-11-01Venice AI$0.15 / $0.60
2026-10-31Venice AI$0.15 / $0.60
2026-10-30Venice AI$0.15 / $0.60
2026-10-29Venice AI$0.15 / $0.60
2026-10-28Venice AI$0.15 / $0.60
2026-10-27Venice AI$0.15 / $0.60
2026-10-27Venice AI$0.15 / $0.60
2026-10-27Venice AI$0.15 / $0.60
2026-10-27Venice AI$0.15 / $0.60
2026-10-26Venice AI$0.15 / $0.60
2026-10-25Venice AI$0.15 / $0.60
2026-10-24Venice AI$0.15 / $0.60
2026-10-24Venice AI$0.15 / $0.60
2026-10-24Venice AI$0.15 / $0.60
2026-10-23Venice AI$0.15 / $0.60
2026-10-23Venice AI$0.15 / $0.60
2026-10-23Venice AI$0.15 / $0.60
2026-10-23Venice AI$0.15 / $0.60
2026-10-23Venice AI$0.15 / $0.60
2026-10-22Venice AI$0.15 / $0.60
2026-10-22Pioneer$0.10 / $0.10
2026-10-21Venice AI$0.15 / $0.60
2026-10-21Pioneer$0.10 / $0.10
2026-10-20Pioneer$0.10 / $0.10
2026-10-19Pioneer$0.10 / $0.10
2026-10-18Pioneer$0.10 / $0.10
2026-10-17Pioneer$0.10 / $0.10
2026-10-12Pioneer$0.10 / $0.10
2026-10-12Pioneer$0.10 / $0.10
2026-10-11Pioneer$0.10 / $0.10
2026-10-10Pioneer$0.10 / $0.10
2026-10-09Pioneer$0.10 / $0.10
2026-10-09Pioneer$0.10 / $0.10
2026-10-08Pioneer$0.10 / $0.10
2026-10-07Pioneer$0.10 / $0.10
2026-09-22Pioneer$0.10 / $0.10
2026-09-21Pioneer$0.10 / $0.10
2026-09-20Pioneer$0.10 / $0.10
2026-09-19Pioneer$0.10 / $0.10
2026-09-18Pioneer$0.10 / $0.10
2026-09-17Pioneer$0.10 / $0.10