fireworks_aiavailablesupports_function_callingsupports_reasoningsupports_tool_choice

Back to Model Explorer

Fireworks AiAvailable on AvalAI

Nemotron 3.5 Lightning API on AvalAI

nemotron-3.5-lightning

Nemotron 3.5 Lightning is an AI model from Nvidia that is available through AvalAI's OpenAI-compatible API.

Open dashboardCompare

Price display scale

Input price$0.05 / 1M tokens

Output price$0.20 / 1M tokens

Context window262,144 tokens

Maximum output— tokens

Release date2026-08-11

Use Nemotron 3.5 Lightning with the AvalAI API

Keep the API key in an environment variable and send requests from server-side code.

Bash

curl https://api.avalai.ir/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AVALAI_API_KEY" \
  -d '{"model": "nemotron-3.5-lightning", "messages": [{"role": "user", "content": "Give a concise, practical solution."}]}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AVALAI_API_KEY"],
    base_url="https://api.avalai.ir/v1",
)

response = client.chat.completions.create(
    model="nemotron-3.5-lightning",
    messages=[{"role": "user", "content": "Give a concise, practical solution."}],
)

print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AVALAI_API_KEY,
  baseURL: "https://api.avalai.ir/v1",
});

const response = await client.chat.completions.create({
  model: "nemotron-3.5-lightning",
  messages: [{ role: "user", content: "Give a concise, practical solution." }],
});

console.log(response.choices[0].message.content);

Create an API keyRead the quickstart

Capabilities and endpoints

• function_calling
• reasoning
• tool_choice

Third-party model parameters

Third-party reference data does not change AvalAI endpoint support; use the capabilities and endpoints above.

• frequency_penalty
• include_reasoning
• logit_bias
• logprobs
• max_tokens
• min_p
• presence_penalty
• reasoning
• repetition_penalty
• response_format
• seed
• stop
• structured_outputs
• temperature
• tool_choice
• tools
• top_k
• top_logprobs
• top_p

Nemotron 3.5 Lightning rate limits

Tier	RPM	TPM
0	3	40,000
1	50	1,000,000
2	100	4,000,000
3	200	8,000,000
4	750	10,000,000
5	5,000	30,000,000

AvalAI and reference marketplace pricing

Token role	AvalAI final price0% platform fee	OpenRouter cost breakdown
		Model rate	Credit purchase fee	Effective OpenRouter cost after fee
Input price	$0.05 / 1M tokens	$0.10 / 1M tokens	5.5%	$0.11 / 1M tokens
Output price	$0.20 / 1M tokens	$0.25 / 1M tokens	5.5%	$0.26 / 1M tokens

AvalAI pricing is final with a 0% platform fee. The effective OpenRouter prices add its 5.5% credit purchase fee to the highest reported model rate, including long-context tiers. OpenRouter charges a 5.5% fee when credits are purchased ($0.80 minimum), so small credit purchases can have a higher effective cost. OpenRouter FAQ

Peer benchmark performance

Independent, sourced scores with no composite rating.

Artificial Analysis Agentic Index

13.8index

Score	Peer rank	Direction	Source and date
13.8 index	No comparable data	Higher is better	OpenRouter · 2026-08-15

Artificial Analysis Coding Index

26.8index

Score	Peer rank	Direction	Source and date
26.8 index	No comparable data	Higher is better	OpenRouter · 2026-08-15

Artificial Analysis Intelligence Index

23.6index

Score	Peer rank	Direction	Source and date
23.6 index	No comparable data	Higher is better	OpenRouter · 2026-08-15

Third-party model data

Source: OpenRouter

Independent sources supplement this context; AvalAI remains authoritative for pricing, availability, and endpoint support.

Reviewed snapshot 2026-08-15

Provider count

—

Context window range

1,000,000

Maximum output range

262,144

OpenRouter model input rate range

$0.1 / 1M

OpenRouter model output rate range

$0.25 / 1M

OpenRouter fee

5.5% credit purchase fee · OpenRouter fee details

Effective input price range after fee

$0.1055 / 1M

Effective output price range after fee

$0.2638 / 1M

Related models

• nemotron-3-ultra
• nvidia_nim.nv-embedqa-e5-v5
• nvidia_nim.nv-embed-v1
• nvidia_nim.nemotron-parse

Frequently asked questions

What is the Nemotron 3.5 Lightning API on AvalAI?

Create an AvalAI API key and send the model ID nemotron-3.5-lightning to one of the supported endpoints shown on this page.

How much does the Nemotron 3.5 Lightning API cost on AvalAI?

The Nemotron 3.5 Lightning API on AvalAI costs $0.05 per 1M input tokens and $0.20 per 1M output tokens.

What is the token cost for Nemotron 3.5 Lightning?

Current AvalAI pricing for Nemotron 3.5 Lightning is $0.05 / 1M tokens for input and $0.20 / 1M tokens for output.

What is the Nemotron 3.5 Lightning context window?

The recorded maximum input context for Nemotron 3.5 Lightning is 262,144 tokens.

Third-party data and freshness

• Pricing, availability, endpoints, and rate limits: AvalAI structured data (authoritative)
• OpenRouter marketplace · Last checked: 2026-08-15