Llama 3.2 3B Instruct API pricing
Meta · Budget price tier · Llama 3.x · released 2024-09. Prices in USD per 1 million tokens. Data snapshot: 2026-10-22.
The price we quote for Llama 3.2 3B Instruct has changed once since 2026-10-18, most recently by +1.5% on 2026-10-19; it is now the 60th cheapest of 164 models in the Budget price tier. Buying from Parasail rather than at the price we quote lowers the token price by about 2%. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.0509 per 1M tokens
- Output: $0.335 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: Not published
- Context window: 131K tokens
- Arena ELO: 1167 as of 2026-10-08
Available on
AWS Bedrock regions: eu-central-1, eu-west-1, eu-west-3, us-east-1, us-east-2, us-west-2
Market position
On blended price ($0.2498 per 1M tokens at 30% input, 70% output) it is cheaper than 64% of models in the Budget price tier: 60th cheapest of 164. Across every price tier it is cheaper than 81% of priced text models in the catalogue: 60th cheapest of 308. Its Arena ELO of 1167 ranks 155th of the 156 models that carry one, above 1% of them. With an Arena score of 1167, Llama 3.2 3B Instruct sits below OptimNow's lowest working quality threshold, Standard (Arena 1415+), so the quality-bar method would not shortlist it for any of the 8 use cases the table prices. Each threshold is a distance below the best ranked model, which scores 1525 on Arena scores as of 8 Oct 2026.
Licence, size and capabilities
Llama 3.2 3B Instruct is open weights, which is not the same as open source: the weights are published, but under Llama 3.x, a licence that restricts some uses. Read it before self-hosting commercially. Its published size is 3B parameters. Listed capabilities: Text. Filling its 131K context window once costs $0.00667 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 2 different hosts. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
Cheapest host: Parasail at $0.05 input / $0.33 output per 1M tokens, 2% below the price we quote on the blended price (30% input, 70% output). All of them charge within 10% of one another.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| Parasail (price we quote) | $0.05 | $0.33 | bf16 |
| Cloudflare (price we quote) | $0.0509 | $0.335 | not declared |
List prices as published on 2026-10-22, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where Meta publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $24 |
| Knowledge Q&A | 2,000 / 800 | $37 |
| Meeting Summary | 10,000 / 1,200 | $91 |
| Marketing Content | 2,500 / 1,800 | $73 |
| Coding Task | 3,000 / 2,000 | $82 |
| Invoice Processing | 1,500 / 600 | $28 |
| Call Summary | 2,000 / 700 | $34 |
| Agent Workflow | 6,000 / 3,000 | $131 |
Price history
Llama 3.2 3B Instruct entered our daily price archive on 2026-10-18; tracking began on 2026-08-15. It listed at $0.05 input / $0.33 output per 1M tokens that day. The price we quote has changed once since then. The latest change, on 2026-10-19, was +1.5% on the blended price (30% input, 70% output), to $0.0509 input / $0.335 output.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-10-19 | $0.05 / $0.33 | $0.0509 / $0.335 | +1.5% |
Alternatives to Llama 3.2 3B Instruct
- Next cheaper model in the Budget price tier: Llama 4 Scout (Meta) at $0.24 blended, 4% less.
- Next more expensive: Llama 3.3 70B Instruct (Meta) at $0.254 blended, 2% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against Llama 3.2 3B Instruct.
- Llama 3.1 8B Instruct (Meta): $0.05 in / $0.08 out per 1M, Arena ELO 1211 (72% cheaper, 44 ELO points higher)
- Llama 3.2 1B Instruct (Meta): $0.027 in / $0.201 out per 1M, Arena ELO 1111 (40% cheaper, 56 ELO points lower)
- Command R (08-2024) (Cohere): $0.15 in / $0.60 out per 1M, Arena ELO 1250 (86% more expensive, 83 ELO points higher)
- Phi 4 (Microsoft): $0.07 in / $0.14 out per 1M, Arena ELO 1256 (52% cheaper, 89 ELO points higher)
- Highest Arena ELO within 20% of this price: MiMo-V2.6-Flash (Xiaomi), 5% cheaper, 284 ELO points higher, out of 13 models in that price band.
Other models from Meta
The 8 nearest to Llama 3.2 3B Instruct in price, of 15 other Meta models in the catalogue. Prices per 1M tokens, input then output.
- Muse Spark 1.2 Contributor: $0.10 / $0.20
- Muse Spark 1.3 Contributor: $0.10 / $0.20
- Llama Guard 4 12B: $0.18 / $0.18
- Llama 4 Scout: $0.10 / $0.30
- Llama 3.3 70B Instruct: $0.10 / $0.32
- Llama 3.1 70B Instruct: $0.40 / $0.40
- Llama 4 Maverick: $0.1875 / $0.6525
- Muse Glimmer 30B: $0.30 / $1.20
Common questions about Llama 3.2 3B Instruct pricing
- How much does Llama 3.2 3B Instruct cost?
- Llama 3.2 3B Instruct costs $0.0509 per 1M input tokens and $0.335 per 1M output tokens at Parasail, the host whose rate we quote. Prices as listed on 2026-10-22.
- Which host is cheapest for Llama 3.2 3B Instruct?
- Cheapest host: Parasail at $0.05 input / $0.33 output per 1M tokens, 2% below the price we quote on the blended price (30% input, 70% output). All of them charge within 10% of one another. Host rates as listed on 2026-10-22.
- Does Llama 3.2 3B Instruct offer batch or cached pricing?
- No. Neither a batch rate nor a prompt-cache rate is published for Llama 3.2 3B Instruct as of 2026-10-22.
- What would Llama 3.2 3B Instruct cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $24 on Llama 3.2 3B Instruct at the list price quoted on 2026-10-22.
- Can Llama 3.2 3B Instruct be self-hosted?
- Yes, within the terms of its licence. Llama 3.2 3B Instruct is open weights, which is not the same as open source: the weights are published, but under Llama 3.x, a licence that restricts some uses. Read it before self-hosting commercially.
- Has the price of Llama 3.2 3B Instruct changed?
- Llama 3.2 3B Instruct entered our daily price archive on 2026-10-18; tracking began on 2026-08-15. It listed at $0.05 input / $0.33 output per 1M tokens that day. The price we quote has changed once since then. The latest change, on 2026-10-19, was +1.5% on the blended price (30% input, 70% output), to $0.0509 input / $0.335 output.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server