We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Mistral: Mistral Nemo
mistralai/mistral-nemoTry Mistral: Mistral Nemo now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
Mistral: Mistral Nemo at a glance
- Input price is 94% lower than the median of 434 Text models.
- Context window of 131,072 tokens, enough for long documents and multi-turn conversations.
- Supports tool (function) calling for agents and integrations.
- Supports structured JSON output with a schema.
- A typical request (1,000 input / 500 output tokens) costs about $0.000154.
About Mistral: Mistral Nemo
Mistral Nemo is a text model from Mistral, built in collaboration with NVIDIA. It is a 12B parameter model, and its provider release date was 19 July 2024. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese and other languages. If you are choosing a model for a project, this one sits in the smaller, efficient tier of Mistral's lineup rather than the largest flagship models.
The model takes text as input and returns text as output, so it is a straightforward language model with no image or audio handling. Its context window is 131072 tokens, which is large enough to hold long documents, extended conversations or sizeable code files in a single request. The maximum output is 16384 tokens, so responses can be long but are capped well below the input limit. Its knowledge cutoff is 30 April 2024, which matters if your task depends on events or information after that date.
Those capabilities point to a few practical uses. The long context suits summarising or extracting information from lengthy reports, contracts and transcripts, and the multilingual support helps with translation and with applications that serve users in several languages. Because the model accepts and returns text only, it fits chat assistants, question answering over supplied documents, drafting and rewriting, classification and other text transformation tasks. The 16384 token output ceiling means very long generated documents may need to be produced in several passes.
You can call the model through api14's OpenAI-compatible API using the model id "mistralai/mistral-nemo". The supported request parameters are frequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs and top_p. That set covers sampling controls, deterministic seeding, stop sequences, structured outputs and tool calling, so you can shape both the style of the output and its format without leaving the standard interface.
A few limits are worth keeping in mind. Input and output are text only, so tasks that require analysing images or audio need a different model. The knowledge cutoff of 30 April 2024 means the model has no built-in awareness of later events, and the 16384 token output cap constrains single-response length. If your workload depends on any of these, another model may fit better.
How to call the Mistral: Mistral Nemo API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "mistralai/mistral-nemo".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "mistralai/mistral-nemo",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pSpecifications
- Context length
- 131,072
- Max output
- 16,384
- Input
- text
- Output
- text
- Knowledge cutoff
- 2024-04-30
Requests on api14 · last 7 days
Mistral: Mistral Nemo: frequently asked questions
- How much does the Mistral: Mistral Nemo API cost?
- Mistral: Mistral Nemo costs Input $0.10 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of Mistral: Mistral Nemo?
- Mistral: Mistral Nemo reads up to 131,072 tokens per request: prompt, history and documents together. It writes up to 16,384 output tokens per response.
- What can Mistral: Mistral Nemo do?
- Mistral: Mistral Nemo accepts text and returns text. It supports tool calling, structured JSON output.
- How do I call Mistral: Mistral Nemo from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "mistralai/mistral-nemo". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Mistral: Mistral Nemo?
- Comparable Text models at a similar price: ScaleDown: Summarize, ScaleDown: Extract, inclusionAI: Ling 3.0 Flash. Each runs through the same API key, so switching is one string.
Mistral: Mistral Nemo community
New topicThis community has no topics yet. Open the first one about Mistral: Mistral Nemo.