Llama 3.2 3B Instruct
by MetaChat
Open Llama instruction model for multilingual chat, reasoning, and coding
- Context
- 131K tokens
- Max output
- 32,768 tokens
- Parameters
- 3.2B total
- Released
- 2024-09-25
- Weights
- Open
- Licence
- llama3.2
meta/llama-3-2-3b-instruct · also seen as @cf/meta/llama-3.2-3b-instruct, meta-llama/Llama-3.2-3B-Instruct, novita/llama-3.2-3b-instruct, eu.meta.llama3-2-3b-instruct-v1:0, +3 more
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2024-09-25
- Weights
- Opengated
- License
- llama3.2
- Input
- Text
- Output
- Text
- Context window
- 131,072 max across endpoints
- Max output
- 32,768
- Providers
- 11 + 6 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.02–$0.15 in · $0.02–$0.33 out per 1M tokens · 6 of 11 providers have a comparable price
More details
- Last updated
- 2025-01-01
- Knowledge cutoff
- 2023-12
- Weights link
- Hugging Face · meta-llama/Llama-3.2-3B-Instruct
- Parameters
- 3.2B total
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel tools
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt cachingunknown
- Web searchunknown
- Computer useunknown
- System messages
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.02 in / $0.02 out per 1M tokens at Deep Infra on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Llama 3.2 3B Instruct |
|---|---|---|---|---|---|
| Sarvam-30BSarvam AI | $0.0333 | $0.02 | $0.10 | 65.5K | +0% |
| Granite 4.0 H MicroIBM | $0.0328 | $0.017 | $0.112 | 131K | −2% cheaper |
| GPT OSS 20BOpenAI | $0.03 | $0.018 | $0.09 | 131K | −10% cheaper |
| Mistral NemoMistral AI | $0.0292 | $0.029 | $0.03 | 131K | −12% cheaper |
| Nex-N2.5-MiniNex AGI | $0.0375 | $0.025 | $0.10 | 262K | +13% |
| Ling 3.0 FlashinclusionAI | $0.028 | $0.021 | $0.063 | 262K | −16% cheaper |
| Ministral 3BMistral AI | $0.04 | $0.04 | $0.04 | 131K | +20% |
| Voxtral Mini 3B 2507Mistral AI | $0.04 | $0.04 | $0.04 | — | +20% |
More from Meta
Newest Meta models in the catalogue. All Meta models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Muse Spark Open | 2026-10-15 | 1.05M | from $1.25 |
| Muse Wonder | 2026-10-12 | 1.05M | from $4.00 |
| Muse Wonder | 2026-10-12 | 1.05M | from $4.00 |
| Muse Voice Transcribe 1.0 | 2026-09-11 | — | unpriced |
| Muse Spark 1.3 | 2026-09-02 | 1.05M | from $1.25 |
| Muse Spark 1.3 Contributor | 2026-09-02 | 1.05M | from $0.10 |
| Muse Image 1.0 | 2026-08-26 | — | unpriced |
| Muse Image | 2026-08-26 | 65.5K | unpriced |