gpt-oss-20b vs Llama 3 8B Stheno V3.2 API pricing
Updated
gpt-oss-20b: USD 0.018 input, USD 0.09 output per 1M tokens (AkashML, promotional). Llama 3 8B Stheno V3.2: USD 0.05 input, USD 0.05 output per 1M tokens (Novita AI). At 3 input tokens per output token, Llama 3 8B Stheno V3.2 costs 39% more than gpt-oss-20b (USD 0.05 vs USD 0.036 per 1M).
How do gpt-oss-20b and Llama 3 8B Stheno V3.2 differ on price?
- Cheapest input price: gpt-oss-20b USD 0.018 against USD 0.05 per 1M tokens, so Llama 3 8B Stheno V3.2 costs 2.8× as much.
- Cheapest output price: Llama 3 8B Stheno V3.2 USD 0.05 against USD 0.09 per 1M tokens, so gpt-oss-20b costs 1.8× as much (80% more).
- Among the 201 indexed models, gpt-oss-20b ranks 3rd cheapest and Llama 3 8B Stheno V3.2 4th on the 3:1 blend.
- The cheaper model changes at 1.2 input tokens per output token.
- Both list cached-input discounts: gpt-oss-20b at 4 standard prices of 10, from USD 0.007 (Google Vertex AI, 90% below that provider's input price); Llama 3 8B Stheno V3.2 at 1 standard price of 2, from USD 0.074 (Featherless, 80% below that provider's input price).
- gpt-oss-20b states up to 131,072 tokens of context, 16× the 8,192 of Llama 3 8B Stheno V3.2.
- gpt-oss-20b has 10 providers with a standard price, 8 more than Llama 3 8B Stheno V3.2; 1 provider sells both (Featherless).
- On one account, Featherless charges USD 0.0675 for gpt-oss-20b (1.88× its cheapest price) and USD 0.3725 for Llama 3 8B Stheno V3.2 (7.4× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for Llama 3 8B Stheno V3.2: its dearest standard price is 7.4× its cheapest, against 6.3× for gpt-oss-20b.
- gpt-oss-20b has a batch price at 2 providers, from USD 0.0575 at 3:1 (Google Vertex AI); Llama 3 8B Stheno V3.2 has no batch price on file.
gpt-oss-20b and Llama 3 8B Stheno V3.2 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 | gpt-oss-20b | Llama 3 8B Stheno V3.2 |
|---|---|---|
| Model page | GPT OSS 20B OpenAI · 10 providers | Llama 3 8B Stheno V3.2 Sao10K · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.036 lower promo USD 0.018 in / USD 0.09 out at AkashML AkashML page checked 2026-11-15 | USD 0.05 USD 0.05 in / USD 0.05 out at Novita AI Novita AI page checked 2026-11-14 |
| Cheapest input | USD 0.018 lower promo AkashML source | USD 0.05 Novita AI source |
| Cheapest cached input | USD 0.007 lower Google Vertex AI source | USD 0.074 Featherless source |
| Cheapest output | USD 0.09 promo AkashML source | USD 0.05 lower Novita AI source |
| Cheapest non-promotional price | USD 0.03 / USD 0.13 CoreWeave Forge, USD 0.055 blended source | The cheapest price is not promotional. |
| Maker's own API | OpenAI publishes no paid standard price on its own API that we found. | Sao10K publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.04 / USD 0.19 input / output, 10 prices | USD 0.21 / USD 0.215 input / output, 2 prices |
| Context window | 131,072 tokens, largest stated | 8,192 tokens, largest stated |
| Providers with a standard price | 10 | 2 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
- Promo: the provider calls the price promotional or discounted, so it is current now and can end without notice.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do gpt-oss-20b and Llama 3 8B Stheno V3.2 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 | gpt-oss-20b | Llama 3 8B Stheno V3.2 | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 2.75 AkashML | USD 5.40 Novita AI | USD 2.65 gpt-oss-20b lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 5.02 AkashML | exceeds context | — |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 26.73 AkashML | exceeds context | — |
gpt-oss-20b is cheaper on 1 workload. The widest gap is on Support chatbot: the dearer model costs 96% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
The cheaper model changes with the mix: below 1.2 input tokens per output token, Llama 3 8B Stheno V3.2 is cheaper; above 1.2, gpt-oss-20b is cheaper. At the site's 3:1 blend, gpt-oss-20b is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
| Input : output tokens | gpt-oss-20b | Llama 3 8B Stheno V3.2 |
|---|---|---|
| 1 : 3 (long answers) | USD 0.072 AkashML | USD 0.05 lower Novita AI |
| 1 : 1 | USD 0.054 AkashML | USD 0.05 lower Novita AI |
| 3 : 1 (the site’s blend) | USD 0.036 lower AkashML | USD 0.05 Novita AI |
| 10 : 1 (retrieval, long prompts) | USD 0.02455 lower AkashML | USD 0.05 Novita AI |
| 30 : 1 (agents, big contexts) | USD 0.02032 lower AkashML | USD 0.05 Novita AI |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do gpt-oss-20b and Llama 3 8B Stheno V3.2 cost per character in other languages?
Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Llama 3 8B Stheno V3.2 is not among them. Count tokens on your own text with the counters below.
Check it on your own traffic
- GPT OSS 20B API pricing: all 10 providers and other tiers.
- Llama 3 8B Stheno V3.2 API pricing: all 2 providers and other tiers.
- Cost calculator with gpt-oss-20b and Llama 3 8B Stheno V3.2 preloaded
- gpt-oss token counter
- Token counter
- Prompt caching calculator
More comparisons: gpt-oss-120b vs gpt-oss-20b · Gemma 4 26B A4B vs gpt-oss-20b · gpt-oss-20b vs Qwen3.6 35B A3B · every gpt-oss-20b comparison · every Llama 3 8B Stheno V3.2 comparison · all 662 price comparisons
Questions
Is gpt-oss-20b cheaper than Llama 3 8B Stheno V3.2?
Yes. On a blend of 3 input tokens to 1 output token, gpt-oss-20b costs USD 0.036 per 1M tokens and Llama 3 8B Stheno V3.2 USD 0.05, at each model's cheapest standard price. For input alone, gpt-oss-20b is cheaper (USD 0.018 against USD 0.05 per 1M); for output alone, Llama 3 8B Stheno V3.2 is (USD 0.05 against USD 0.09). This compares price only, not quality.
What do gpt-oss-20b and Llama 3 8B Stheno V3.2 cost per 1M tokens?
gpt-oss-20b: from USD 0.018 input and USD 0.09 output at AkashML (promotional); median of 10 standard prices USD 0.04 / USD 0.19. Llama 3 8B Stheno V3.2: from USD 0.05 input and USD 0.05 output at Novita AI; median of 2 standard prices USD 0.21 / USD 0.215. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both gpt-oss-20b and Llama 3 8B Stheno V3.2?
1 provider has a standard price for both: Featherless (USD 0.0675 and USD 0.3725 at 3:1). Buying each model from its own cheapest provider costs USD 0.036 and USD 0.05.
At what input:output ratio does the cheaper of gpt-oss-20b and Llama 3 8B Stheno V3.2 change?
The cheaper model changes with the mix: below 1.2 input tokens per output token, Llama 3 8B Stheno V3.2 is cheaper; above 1.2, gpt-oss-20b is cheaper. At the site's 3:1 blend, gpt-oss-20b is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
Do gpt-oss-20b and Llama 3 8B Stheno V3.2 have cached input pricing?
gpt-oss-20b from USD 0.007 per 1M cached input tokens (Google Vertex AI; 4 of 10 standard prices list a discount). Llama 3 8B Stheno V3.2 from USD 0.074 per 1M cached input tokens (Featherless; 1 of 2 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, gpt-oss-20b or Llama 3 8B Stheno V3.2?
gpt-oss-20b: up to 131,072 tokens, against 8,192 for Llama 3 8B Stheno V3.2, 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.