BroadRouter

Llama 3 8B Stheno V3.2 API pricing

Updated

Among the 2 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Llama 3 8B Stheno V3.2 is Novita AI at USD 0.05 per 1M input tokens and USD 0.05 per 1M output tokens. The median across 2 standard prices is USD 0.21 / USD 0.215. Each price is read from the provider's own pricing page.

Sao10K · slug l3-8b-stheno-v3.2 · up to 8,192 tokens of context · 2 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index.

Does Sao10K sell Llama 3 8B Stheno V3.2 directly?

Sao10K publishes no price for Llama 3 8B Stheno V3.2 on its own API that we could find, so this page compares hosts only.

Llama 3 8B Stheno V3.2 model facts

Facts from Sao10K's model card for Sao10K/L3-8B-Stheno-v3.2 and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

Llama 3 8B Stheno V3.2: facts as stated by the model card and the Hugging Face model API, with sources
FactAs statedSource
Open weightsYes. The weights are in a public Hugging Face repository (Sao10K/L3-8B-Stheno-v3.2) with no access gate.Hugging Face model API, checked 2026-11-16
Quote
“"private": false, "gated": false, 4 .safetensors files listed”
LicenceCC BY-NC 4.0 (cc-by-nc-4.0)Sao10K model card metadata, checked 2026-11-16
Quote
“license: cc-by-nc-4.0”
Parameters in the weight files (Hugging Face count, not the maker's figure)About 8.0 billion (8,030,261,248)Hugging Face model API, checked 2026-11-16
Quote
“"safetensors": { "total": 8030261248 }”
Context lengthNot found on Sao10K's model card when we read it; see the context column in the price tablechecked 2026-11-16
Tool callingNot found on Sao10K's model card when we read itchecked 2026-11-16
First published on Hugging Face (not necessarily the release date)2024-06-05Hugging Face model API, checked 2026-11-16
Quote
“"createdAt": "2024-06-05T10:30:57.000Z"”

Llama 3 8B Stheno V3.2 price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 7.4× the cheapest.

Llama 3 8B Stheno V3.2 API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1Novita AI cheapest
Sao10K/L3-8B-Stheno-v3.2
Notes and source quote
“Llama 3 8B Stheno V3.2 8K $0.05 /Mt $0.05 /Mt”
USD 0.05not publishedUSD 0.05USD 0.058,192not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
2Featherless
Sao10K/L3-8B-Stheno-v3.2
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits).

“PRICING: INPUT $0.37 / CACHED $0.074 / OUTPUT $0.38”
USD 0.37USD 0.074USD 0.38USD 0.37258,192FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does Llama 3 8B Stheno V3.2 cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on Llama 3 8B Stheno V3.2, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
Novita AIUSD 5.40exceeds contextexceeds context
FeatherlessUSD 24.16exceeds contextexceeds context

For the support chatbot, the cheapest price (Novita AI, USD 5.40 a month) saves USD 9.38 against the median (USD 14.78). For the coding agent the gap is USD 76.41 a month (45% lower).

Which Llama 3 8B Stheno V3.2 provider is cheapest for your traffic?

Novita AI has the lowest input price (USD 0.05) and the lowest output price (USD 0.05), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

Llama 3 8B Stheno V3.2: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
Novita AI (no cache price)USD 0.05 cheapestUSD 0.05 cheapestUSD 0.05 cheapest
FeatherlessUSD 0.3725USD 0.2615USD 0.1727

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

1 of 2 providers publishes a cached-input price below the input price: Featherless (80% off). Novita AI publishes none, so cached tokens there bill at the input price.

Both providers offer 8,192 tokens of context.

Estimate your own bill

The Sao10K models whose cheapest standard price is closest to Llama 3 8B Stheno V3.2's (USD 0.05 blended):

Sao10K models priced closest to Llama 3 8B Stheno V3.2
ModelCheapest inputCheapest outputMax contextProviders
L3.1-70B-Euryale-v2.2USD 0.72USD 0.72131,0722

Priced closest from other makers: Gemma 3 4B (Google, USD 0.05) · Qwen 2.5 7B (Qwen, USD 0.05) · Mistral-Small-24B-Instruct-2501 (Mistral AI, USD 0.0575).

All 431 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the Llama 3 8B Stheno V3.2 API cost per token?

From USD 0.05 per 1M input tokens (USD 0.00000005 per token) and USD 0.05 per 1M output tokens (USD 0.00000005 per token) at the lowest standard prices we found. The median of 2 standard prices is USD 0.21 input and USD 0.215 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for Llama 3 8B Stheno V3.2?

Among the 2 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is Novita AI, ranked on a blend of 3 input tokens to 1 output token (USD 0.05 per 1M). It also has the lowest input and the lowest output price. Batch, flex, priority and fast tiers are shown in the table but not ranked.

Does Sao10K sell Llama 3 8B Stheno V3.2 on its own API?

Sao10K publishes no price for Llama 3 8B Stheno V3.2 on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is Novita AI at USD 0.05 / USD 0.05 per 1M tokens.

Does Llama 3 8B Stheno V3.2 have cached input pricing?

1 of 2 standard prices includes one. The lowest is USD 0.074 per 1M at Featherless. Providers without one bill cached input at the input price. What cached input means.

What is the Llama 3 8B Stheno V3.2 context window?

8,192 tokens on every provider that states it.

How much does a coding agent cost per month on Llama 3 8B Stheno V3.2?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 94.50 a month at Novita AI, USD 170.91 at the median price and USD 247.32 at Featherless. Try your own numbers.

Is Llama 3 8B Stheno V3.2 free to use through an API?

No provider in our data lists a free price for Llama 3 8B Stheno V3.2 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Is Llama 3 8B Stheno V3.2 open source, with open weights, and what is its licence?

Sao10K publishes the weights on Hugging Face as Sao10K/L3-8B-Stheno-v3.2, in a public repository with no access gate. The licence, as the Sao10K model card metadata states it: CC BY-NC 4.0 (cc-by-nc-4.0). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Sao10K's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

How many parameters does Llama 3 8B Stheno V3.2 have?

Sao10K's model card does not state a total that we found. Hugging Face counts about 8.0 billion (8,030,261,248) parameters in the published weight files of Sao10K/L3-8B-Stheno-v3.2. That is a file-level count, not the maker's figure, and it can include extra modules (checked 2026-11-16).

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity