Nemotron 3 Super vs gpt-oss-120b API pricing
Updated
Nemotron 3 Super: USD 0.075 input, USD 0.40 output per 1M tokens (DeepInfra). gpt-oss-120b: USD 0.03 input, USD 0.17 output per 1M tokens (CoreWeave Forge). At 3 input tokens per output token, Nemotron 3 Super costs 2.4× as much as gpt-oss-120b (USD 0.1563 vs USD 0.065 per 1M).
How do Nemotron 3 Super and gpt-oss-120b differ on price?
- Cheapest input price: gpt-oss-120b USD 0.03 against USD 0.075 per 1M tokens, so Nemotron 3 Super costs 2.5× as much.
- Cheapest output price: gpt-oss-120b USD 0.17 against USD 0.40 per 1M tokens, so Nemotron 3 Super costs 2.4× as much.
- Among the 201 indexed models, Nemotron 3 Super ranks 48th cheapest and gpt-oss-120b 9th on the 3:1 blend.
- No input:output mix changes the answer: gpt-oss-120b is cheaper at every mix before cache discounts.
- Only gpt-oss-120b lists a cached-input discount: gpt-oss-120b at 4 standard prices of 21, from USD 0.015 (Fireworks AI, 90% below that provider's input price). Nemotron 3 Super's cached tokens bill at the input price.
- Nemotron 3 Super states up to 262,144 tokens of context, 2× the 131,072 of gpt-oss-120b.
- gpt-oss-120b has 21 providers with a standard price, 18 more than Nemotron 3 Super; 3 providers sell both (DeepInfra, Amazon Bedrock and Cloudflare Workers AI).
- On one account, DeepInfra charges USD 0.1563 for Nemotron 3 Super (its cheapest price) and USD 0.07025 for gpt-oss-120b (1.08× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for gpt-oss-120b: its dearest standard price is 6.9× its cheapest, against 4.8× for Nemotron 3 Super.
- Nemotron 3 Super has no batch price on file; gpt-oss-120b has a batch price at 2 providers, from USD 0.07875 at 3:1 (Google Vertex AI).
- For the one-developer coding agent preset, the gap is USD 1,220 a year in gpt-oss-120b's favour (Nemotron 3 Super USD 171.00 a month, gpt-oss-120b USD 69.30).
- Per character of input, the gap depends on the language: Nemotron 3 Super costs 3× as much as gpt-oss-120b on Hindi text but 2.3× as much as gpt-oss-120b on Arabic MSA, because the two tokenizers split those languages differently.
Nemotron 3 Super and gpt-oss-120b 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 | Nemotron 3 Super | gpt-oss-120b |
|---|---|---|
| Model page | NVIDIA Nemotron 3 Super 120B A12B NVIDIA · 3 providers | OpenAI GPT OSS 120B OpenAI · 21 providers |
| Cheapest standard price, blended 3:1 | USD 0.1563 USD 0.075 in / USD 0.40 out at DeepInfra DeepInfra page checked 2026-11-14 | USD 0.065 lower USD 0.03 in / USD 0.17 out at CoreWeave Forge CoreWeave Forge page checked 2026-11-15 |
| Cheapest input | USD 0.075 DeepInfra source | USD 0.03 lower CoreWeave Forge source |
| Cheapest cached input | No standard price lists a cache price; cached tokens bill at the input price. | USD 0.015 Fireworks AI source |
| Cheapest output | USD 0.40 DeepInfra source | USD 0.17 lower CoreWeave Forge source |
| Maker's own API | NVIDIA publishes no paid standard price on its own API that we found. | OpenAI publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.15 / USD 0.65 input / output, 3 prices | USD 0.10 / USD 0.60 input / output, 21 prices |
| Context window | 262,144 tokens, largest stated | 131,072 tokens, largest stated; from 128,000 at some providers |
| Providers with a standard price | 3 | 21 |
- 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 Nemotron 3 Super and gpt-oss-120b 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 | Nemotron 3 Super | gpt-oss-120b | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 13.95 DeepInfra | USD 5.76 CoreWeave Forge | USD 8.19 gpt-oss-120b lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 24.00 DeepInfra | USD 9.75 CoreWeave Forge | USD 14.25 gpt-oss-120b lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 171.00 DeepInfra | USD 69.30 CoreWeave Forge | USD 101.70 gpt-oss-120b lower |
gpt-oss-120b is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 2.47× as much as the cheaper one.
Does the cheaper model change with your input:output ratio?
gpt-oss-120b 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 Nemotron 3 Super's, so the input:output ratio never changes the answer.
| Input : output tokens | Nemotron 3 Super | gpt-oss-120b |
|---|---|---|
| 1 : 3 (long answers) | USD 0.3188 DeepInfra | USD 0.135 lower CoreWeave Forge |
| 1 : 1 | USD 0.2375 DeepInfra | USD 0.10 lower CoreWeave Forge |
| 3 : 1 (the site’s blend) | USD 0.1563 DeepInfra | USD 0.065 lower CoreWeave Forge |
| 10 : 1 (retrieval, long prompts) | USD 0.1045 DeepInfra | USD 0.04273 lower CoreWeave Forge |
| 30 : 1 (agents, big contexts) | USD 0.08548 DeepInfra | USD 0.03452 lower CoreWeave Forge |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do Nemotron 3 Super and gpt-oss-120b cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the Nemotron 3 Ultra tokenizer for Nemotron 3 Super and the gpt-oss (o200k_harmony) tokenizer for gpt-oss-120b:
| Content | Nemotron 3 Super | gpt-oss-120b |
|---|---|---|
| English | USD 0.016 DeepInfra | USD 0.0064 lower CoreWeave Forge |
| Arabic MSA | USD 0.022 DeepInfra | USD 0.0096 lower CoreWeave Forge |
| Egyptian Arabic | USD 0.024 DeepInfra | USD 0.0100 lower CoreWeave Forge |
| Hindi | USD 0.029 DeepInfra | USD 0.0097 lower CoreWeave Forge |
| Chinese | USD 0.068 DeepInfra | USD 0.023 lower CoreWeave Forge |
| Spanish | USD 0.018 DeepInfra | USD 0.0068 lower CoreWeave Forge |
| Code | USD 0.020 DeepInfra | USD 0.0076 lower CoreWeave Forge |
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
- NVIDIA Nemotron 3 Super 120B A12B API pricing: all 3 providers and other tiers.
- OpenAI GPT OSS 120B API pricing: all 21 providers and other tiers.
- Cost calculator with Nemotron 3 Super and gpt-oss-120b preloaded
- Nemotron 3 token counter
- gpt-oss token counter
- Prompt caching calculator
More comparisons: gpt-oss-120b vs gpt-oss-20b · gpt-oss-120b vs Llama 3.3 70B · gpt-oss-120b vs DeepSeek V4.1 Flash · GPT-6 Luna vs gpt-oss-120b · gpt-oss-120b vs Qwen3.8 27B · gpt-oss-120b vs Gemma 4 26B A4B · every Nemotron 3 Super comparison · every gpt-oss-120b comparison · all 662 price comparisons
Questions
Is Nemotron 3 Super cheaper than gpt-oss-120b?
No. On a blend of 3 input tokens to 1 output token, gpt-oss-120b costs USD 0.065 per 1M tokens and Nemotron 3 Super USD 0.1563, at each model's cheapest standard price. For input alone, gpt-oss-120b is cheaper (USD 0.03 against USD 0.075 per 1M); for output alone, gpt-oss-120b is (USD 0.17 against USD 0.40). This compares price only, not quality.
What do Nemotron 3 Super and gpt-oss-120b cost per 1M tokens?
Nemotron 3 Super: from USD 0.075 input and USD 0.40 output at DeepInfra; median of 3 standard prices USD 0.15 / USD 0.65. gpt-oss-120b: from USD 0.03 input and USD 0.17 output at CoreWeave Forge; median of 21 standard prices USD 0.10 / USD 0.60. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both Nemotron 3 Super and gpt-oss-120b?
3 providers have a standard price for both: DeepInfra (USD 0.1563 and USD 0.07025 at 3:1), Amazon Bedrock (USD 0.275 and USD 0.2625 at 3:1), Cloudflare Workers AI (USD 0.75 and USD 0.45 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.1563 and USD 0.065.
Which is cheaper for a coding agent or a chatbot, Nemotron 3 Super or gpt-oss-120b?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 171.00 a month on Nemotron 3 Super (DeepInfra) against USD 69.30 on gpt-oss-120b (CoreWeave Forge), a difference of USD 101.70. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 13.95 a month on Nemotron 3 Super (DeepInfra) against USD 5.76 on gpt-oss-120b (CoreWeave Forge), a difference of USD 8.19. 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 Nemotron 3 Super and gpt-oss-120b change?
gpt-oss-120b 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 Nemotron 3 Super's, so the input:output ratio never changes the answer.
Do Nemotron 3 Super and gpt-oss-120b have cached input pricing?
Nemotron 3 Super: no standard price lists a cached-input discount. gpt-oss-120b from USD 0.015 per 1M cached input tokens (Fireworks AI; 4 of 21 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, Nemotron 3 Super or gpt-oss-120b?
Nemotron 3 Super: up to 262,144 tokens, against 131,072 for gpt-oss-120b, 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.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- DeepInfra: pricing (checked 2026-11-14)
- CoreWeave Forge: pricing (checked 2026-11-15)
- Fireworks AI: pricing (checked 2026-11-14)
- DeepInfra: pricing (checked 2026-11-14)
- Amazon Bedrock: pricing (checked 2026-11-14)
- Cloudflare Workers AI: pricing (checked 2026-11-14)
- Google Vertex AI: pricing (checked 2026-11-14)