As of August 30, 2026, Llama 3.1 Nemotron 70B Instruct API pricing is $1.20 per million input tokens and $1.20 per million output tokens. A typical 100K-in / 20K-out request costs $0.14. Source: https://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct
Blended / 1M
$2.40
Input
$1.20
Output
$1.20
100K / 20K
$0.14
Specs
131.1K
Oct 1, 2024
Dec 1, 2023
Open source
Percentile against every model with a published score on that eval. Click a row for the full board.
MMLU against blended input+output $/M. Log price. Llama 3.1 Nemotron 70B Instruct is the green point.
Published scores
11 evals · 2 groups
Same search as the hub. Pick any model, or jump into a priced matchup.
NVIDIA
OpenAI
Anthropic
Google
xAI
DeepSeek
MiniMax
As of August 30, 2026, Llama 3.1 Nemotron 70B Instruct NVIDIA API pricing is $1.20 per million input tokens and $1.20 per million output tokens. Input tokens are the prompt you send; output tokens are the completion. Long answers therefore cost more than short ones even when the prompt stays the same. Source: https://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct
On this page the blended Llama 3.1 Nemotron 70B Instruct API cost is $2.40 for 1 million input tokens plus 1 million output tokens. That 1:1 mix is the comparison scale used across the LLM pricing table. A 3:1 mix (three million input tokens per one million output tokens), which some calculators use, would be about $4.80.
A typical Llama 3.1 Nemotron 70B Instruct API request with 100K input tokens and 20K output tokens costs about $0.14 at current rates as of August 30, 2026. Multiply that by daily or monthly volume to estimate spend. Caching, batch APIs, and volume discounts from NVIDIA can bring the real invoice lower than the public list rate at https://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct.
Llama 3.1 Nemotron 70B Instruct supports a 131K token context window. The context window is the total prompt plus conversation history the model can see in one call. Larger windows cost more when you fill them, because every input token is billed per million tokens.
Yes. Llama 3.1 Nemotron 70B Instruct is an open-weight model by NVIDIA. You can download the weights and self-host, or pay NVIDIA's hosted API and skip GPU ops. Hosted API pricing on this page is the public per-million-token rate, not the electricity cost of running the weights yourself.
Llama 3.1 Nemotron 70B Instruct currently reports MMLU 80.2%, HellaSwag 85.6%, GSM8K 91.4%. See the performance table for the full eval set. Use those scores with the token prices above when you are choosing between a cheaper LLM and a frontier model. GPQA, SWE-bench, and HLE are the evals people usually compare first.
Llama 3.1 Nemotron 70B Instruct has a published knowledge cutoff of 2023-12-01. Facts after that date are not guaranteed to be in the weights. For current events you still need retrieval or tools, which adds input tokens and therefore API cost per million tokens.
Use the Compare picker on this page to start an LLM comparison. Search by model or provider, pick a second model, and AnotherWrapper opens a dedicated Llama 3.1 Nemotron 70B Instruct vs page with per-million-token prices, blended 1M-in / 1M-out cost, context window, throughput, and benchmarks. You can also open any model from the sidebar, or go back to the LLM pricing table to sort the full index.
The cheapest LLM alternative depends on whether you optimize for blended token cost, coding evals, or context window. Start with the popular matchups on this page, then sort the LLM pricing table by blended cost to see which hosted APIs undercut Llama 3.1 Nemotron 70B Instruct. Open-weight models can be cheaper still if you self-host, but that is not the same as NVIDIA API pricing on this page.
Llama 3.1 Nemotron 70B Instruct is called through NVIDIA's API with an API key. Bill against input and output tokens separately; cache or shorten prompts if spend is high. If you are shipping a full product, AnotherWrapper includes pre-built API routes and templates for NVIDIA and 5+ other providers with auth, payments, and deployment already configured.
This Llama 3.1 Nemotron 70B Instruct page tracks the latest published NVIDIA API pricing from NVIDIA, quoted per million tokens. List rates can differ from invoices because of prompt caching, batch discounts, committed-use tiers, and private contracts. Official rate sheet: https://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct. Benchmark scores come from official publications and independent evals, not from a private lab run by AnotherWrapper.
Llama 3.1 Nemotron 70B Instruct is a open-source model from NVIDIA. Current API pricing is $1.20 per million input tokens and $1.20 per million output tokens, with a 131.1K token context window. A blended 1M-in / 1M-out workload costs $2.40.
Source: NVIDIA pricing (https://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct)
Rank it on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
344 models across 36 providers. Search or jump to a lab — every model page stays linked here.
Next step
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
