Llama 3.2 3B vs Llama 3.2 1B API pricing
Updated
Llama 3.2 3B: USD 0.0509 input, USD 0.335 output per 1M tokens (Featherless). Llama 3.2 1B: USD 0.027 input, USD 0.201 output per 1M tokens (Cloudflare Workers AI and 1 other). At 3 input tokens per output token, Llama 3.2 3B costs 73% more than Llama 3.2 1B (USD 0.1219 vs USD 0.0705 per 1M).
How do Llama 3.2 3B and Llama 3.2 1B differ on price?
- Cheapest input price: Llama 3.2 1B USD 0.027 against USD 0.0509 per 1M tokens, so Llama 3.2 3B costs 1.89× as much (89% more).
- Cheapest output price: Llama 3.2 1B USD 0.10 against USD 0.15 per 1M tokens, so Llama 3.2 3B costs 1.5× as much (50% more).
- Among the 201 indexed models, Llama 3.2 3B ranks 27th cheapest and Llama 3.2 1B 10th on the 3:1 blend.
- No input:output mix changes the answer: Llama 3.2 1B is cheaper at every mix before cache discounts.
- Neither model has a standard price with a cached-input discount, so prompt caching does not lower either bill.
- Llama 3.2 3B states up to 128,000 tokens of context, 3.9× the 32,768 of Llama 3.2 1B.
- Llama 3.2 3B has 4 providers with a standard price, 1 more than Llama 3.2 1B; 3 providers sell both (Featherless, Cloudflare Workers AI and Amazon Bedrock).
- On one account, Featherless charges USD 0.1219 for Llama 3.2 3B (its cheapest price) and USD 0.0705 for Llama 3.2 1B (its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for Llama 3.2 3B: its dearest standard price is 2.2× its cheapest, against 1.42× for Llama 3.2 1B.
- For the one-developer coding agent preset, the gap is USD 663.12 a year in Llama 3.2 1B's favour (Llama 3.2 3B USD 121.95 a month, Llama 3.2 1B USD 66.69).
- Per character of input, Llama 3.2 3B costs 1.89× as much as Llama 3.2 1B in every measured language, because both use the Llama 3.3 70B tokenizer.
Llama 3.2 3B and Llama 3.2 1B prices side by side
USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.
| Price | Llama 3.2 3B | Llama 3.2 1B |
|---|---|---|
| Model page | Llama 3.2 3B Instruct Meta · 4 providers | Llama 3.2 1B Instruct Meta · 3 providers |
| Cheapest standard price, blended 3:1 | USD 0.1219 USD 0.0509 in / USD 0.335 out at Featherless Featherless page checked 2026-11-15 | USD 0.0705 lower USD 0.027 in / USD 0.201 out at Cloudflare Workers AI and 1 other Cloudflare Workers AI page checked 2026-11-14 |
| Cheapest input | USD 0.0509 Featherless source | USD 0.027 lower Cloudflare Workers AI source |
| Cheapest cached input | No standard price lists a cache price; cached tokens bill at the input price. | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 0.15 Amazon Bedrock source | USD 0.10 lower Amazon Bedrock source |
| Maker's own API | Meta publishes no paid standard price on its own API that we found. | Meta publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.1005 / USD 0.335 input / output, 4 prices | USD 0.027 / USD 0.201 input / output, 3 prices |
| Context window | 128,000 tokens, largest stated; from 32,768 at some providers | 32,768 tokens, largest stated |
| Providers with a standard price | 4 | 3 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do Llama 3.2 3B and Llama 3.2 1B cost for a real workload?
30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).
| Workload | Llama 3.2 3B | Llama 3.2 1B | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 10.61 Featherless | USD 6.05 Cloudflare Workers AI | USD 4.56 Llama 3.2 1B lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 17.24 Featherless | USD 9.50 Cloudflare Workers AI | USD 7.75 Llama 3.2 1B lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 121.95 Cloudflare Workers AI | USD 66.69 Cloudflare Workers AI | USD 55.26 Llama 3.2 1B lower |
Llama 3.2 1B is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 83% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
Llama 3.2 1B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Llama 3.2 3B's, so the input:output ratio never changes the answer.
| Input : output tokens | Llama 3.2 3B | Llama 3.2 1B |
|---|---|---|
| 1 : 3 (long answers) | USD 0.15 Amazon Bedrock | USD 0.10 lower Amazon Bedrock |
| 1 : 1 | USD 0.15 Amazon Bedrock | USD 0.10 lower Amazon Bedrock |
| 3 : 1 (the site’s blend) | USD 0.1219 Featherless | USD 0.0705 lower Cloudflare Workers AI |
| 10 : 1 (retrieval, long prompts) | USD 0.07673 Featherless | USD 0.04282 lower Cloudflare Workers AI |
| 30 : 1 (agents, big contexts) | USD 0.06006 Featherless | USD 0.03261 lower Cloudflare Workers AI |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do Llama 3.2 3B and Llama 3.2 1B cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the Llama 3.3 70B tokenizer for Llama 3.2 3B (the same one for both, so the gap equals the price gap):
| Content | Llama 3.2 3B | Llama 3.2 1B |
|---|---|---|
| English | USD 0.011 Featherless | USD 0.0059 lower Cloudflare Workers AI |
| Arabic MSA | USD 0.020 Featherless | USD 0.010 lower Cloudflare Workers AI |
| Egyptian Arabic | USD 0.020 Featherless | USD 0.011 lower Cloudflare Workers AI |
| Hindi | USD 0.027 Featherless | USD 0.014 lower Cloudflare Workers AI |
| Chinese | USD 0.041 Featherless | USD 0.022 lower Cloudflare Workers AI |
| Spanish | USD 0.014 Featherless | USD 0.0072 lower Cloudflare Workers AI |
| Code | USD 0.013 Featherless | USD 0.0069 lower Cloudflare Workers AI |
From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.
Check it on your own traffic
- Llama 3.2 3B Instruct API pricing: all 4 providers and other tiers.
- Llama 3.2 1B Instruct API pricing: all 3 providers and other tiers.
- Cost calculator with Llama 3.2 3B and Llama 3.2 1B preloaded
- Llama 3 token counter
- Prompt caching calculator
Questions
Is Llama 3.2 3B cheaper than Llama 3.2 1B?
No. On a blend of 3 input tokens to 1 output token, Llama 3.2 1B costs USD 0.0705 per 1M tokens and Llama 3.2 3B USD 0.1219, at each model's cheapest standard price. For input alone, Llama 3.2 1B is cheaper (USD 0.027 against USD 0.0509 per 1M); for output alone, Llama 3.2 1B is (USD 0.10 against USD 0.15). This compares price only, not quality.
What do Llama 3.2 3B and Llama 3.2 1B cost per 1M tokens?
Llama 3.2 3B: from USD 0.0509 input and USD 0.335 output at Featherless; median of 4 standard prices USD 0.1005 / USD 0.335. Llama 3.2 1B: from USD 0.027 input and USD 0.201 output at Cloudflare Workers AI and 1 other; median of 3 standard prices USD 0.027 / USD 0.201. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both Llama 3.2 3B and Llama 3.2 1B?
3 providers have a standard price for both: Featherless (USD 0.1219 and USD 0.0705 at 3:1), Cloudflare Workers AI (USD 0.122 and USD 0.0705 at 3:1), Amazon Bedrock (USD 0.15 and USD 0.10 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.1219 and USD 0.0705.
Which is cheaper for a coding agent or a chatbot, Llama 3.2 3B or Llama 3.2 1B?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 121.95 a month on Llama 3.2 3B (Cloudflare Workers AI) against USD 66.69 on Llama 3.2 1B (Cloudflare Workers AI), a difference of USD 55.26. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 10.61 a month on Llama 3.2 3B (Featherless) against USD 6.05 on Llama 3.2 1B (Cloudflare Workers AI), a difference of USD 4.56. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.
At what input:output ratio does the cheaper of Llama 3.2 3B and Llama 3.2 1B change?
Llama 3.2 1B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Llama 3.2 3B's, so the input:output ratio never changes the answer.
Do Llama 3.2 3B and Llama 3.2 1B have cached input pricing?
Llama 3.2 3B: no standard price lists a cached-input discount. Llama 3.2 1B: no standard price lists a cached-input discount. Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, Llama 3.2 3B or Llama 3.2 1B?
Llama 3.2 3B: up to 128,000 tokens, against 32,768 for Llama 3.2 1B, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.