curl --request POST \
--url https://api.iotools.cloud/v1/tool/gpu-vram-calculator \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"ioParams": 1000.0005,
"ioHiddenDim": 32800,
"ioLayers": 128.5,
"ioBatchSize": 2048.5,
"ioSeqLen": 524288.5,
"ioMixedPrecision": true,
"ioGradCheckpoint": true
}
'import requests
url = "https://api.iotools.cloud/v1/tool/gpu-vram-calculator"
payload = {
"ioParams": 1000.0005,
"ioHiddenDim": 32800,
"ioLayers": 128.5,
"ioBatchSize": 2048.5,
"ioSeqLen": 524288.5,
"ioMixedPrecision": True,
"ioGradCheckpoint": True
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
ioParams: 1000.0005,
ioHiddenDim: 32800,
ioLayers: 128.5,
ioBatchSize: 2048.5,
ioSeqLen: 524288.5,
ioMixedPrecision: true,
ioGradCheckpoint: true
})
};
fetch('https://api.iotools.cloud/v1/tool/gpu-vram-calculator', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.iotools.cloud/v1/tool/gpu-vram-calculator",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'ioParams' => 1000.0005,
'ioHiddenDim' => 32800,
'ioLayers' => 128.5,
'ioBatchSize' => 2048.5,
'ioSeqLen' => 524288.5,
'ioMixedPrecision' => true,
'ioGradCheckpoint' => true
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.iotools.cloud/v1/tool/gpu-vram-calculator"
payload := strings.NewReader("{\n \"ioParams\": 1000.0005,\n \"ioHiddenDim\": 32800,\n \"ioLayers\": 128.5,\n \"ioBatchSize\": 2048.5,\n \"ioSeqLen\": 524288.5,\n \"ioMixedPrecision\": true,\n \"ioGradCheckpoint\": true\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.iotools.cloud/v1/tool/gpu-vram-calculator")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"ioParams\": 1000.0005,\n \"ioHiddenDim\": 32800,\n \"ioLayers\": 128.5,\n \"ioBatchSize\": 2048.5,\n \"ioSeqLen\": 524288.5,\n \"ioMixedPrecision\": true,\n \"ioGradCheckpoint\": true\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.iotools.cloud/v1/tool/gpu-vram-calculator")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"ioParams\": 1000.0005,\n \"ioHiddenDim\": 32800,\n \"ioLayers\": 128.5,\n \"ioBatchSize\": 2048.5,\n \"ioSeqLen\": 524288.5,\n \"ioMixedPrecision\": true,\n \"ioGradCheckpoint\": true\n}"
response = http.request(request)
puts response.read_body{
"tool": "<string>",
"tool_version": "<string>",
"outputs": {
"ioBreakdown": "<string>",
"ioGpuFit": "<string>"
},
"credits_used": 123,
"request_id": "<string>",
"credits_remaining": 123
}{
"type": "https://iotools.cloud/docs/errors/validation_error",
"title": "Invalid request",
"status": 400,
"code": "validation_error",
"detail": "One or more inputs are invalid — see `fields`.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/invalid_api_key",
"title": "Invalid API key",
"status": 401,
"code": "invalid_api_key",
"detail": "Provide 'Authorization: Bearer <key>'.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/insufficient_credits",
"title": "Insufficient credits",
"status": 402,
"code": "insufficient_credits",
"detail": "This call costs 1 credit and 0 remain in this month's allowance.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/tool_not_allowed",
"title": "Tool not available over the API",
"status": 403,
"code": "tool_not_allowed",
"detail": "\"Background Remover\" is available on iotools.cloud but has no API endpoint.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/tool_not_found",
"title": "Tool not found",
"status": 404,
"code": "tool_not_found",
"detail": "No tool with that slug. See GET /v1/tools.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/payload_too_large",
"title": "Payload too large",
"status": 413,
"code": "payload_too_large",
"detail": "Request body exceeds this tool's size limit.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/rate_limited",
"title": "Rate limit exceeded",
"status": 429,
"code": "rate_limited",
"detail": "Too many requests. Retry in 30s.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/processing_error",
"title": "Tool failed to run",
"status": 500,
"code": "processing_error",
"detail": "The tool failed to run. Please try again.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/tool_disabled",
"title": "Tool temporarily disabled",
"status": 503,
"code": "tool_disabled",
"detail": "This tool is temporarily unavailable. Try again shortly.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}GPU VRAM Calculator
Estimate the GPU VRAM needed to run or train a transformer / large language model. Enter parameter count, precision (fp16, int8, int4…), context length and batch size to break down weights, KV cache, activations, gradients and optimizer state, and check which GPUs it fits on.
curl --request POST \
--url https://api.iotools.cloud/v1/tool/gpu-vram-calculator \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"ioParams": 1000.0005,
"ioHiddenDim": 32800,
"ioLayers": 128.5,
"ioBatchSize": 2048.5,
"ioSeqLen": 524288.5,
"ioMixedPrecision": true,
"ioGradCheckpoint": true
}
'import requests
url = "https://api.iotools.cloud/v1/tool/gpu-vram-calculator"
payload = {
"ioParams": 1000.0005,
"ioHiddenDim": 32800,
"ioLayers": 128.5,
"ioBatchSize": 2048.5,
"ioSeqLen": 524288.5,
"ioMixedPrecision": True,
"ioGradCheckpoint": True
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
ioParams: 1000.0005,
ioHiddenDim: 32800,
ioLayers: 128.5,
ioBatchSize: 2048.5,
ioSeqLen: 524288.5,
ioMixedPrecision: true,
ioGradCheckpoint: true
})
};
fetch('https://api.iotools.cloud/v1/tool/gpu-vram-calculator', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.iotools.cloud/v1/tool/gpu-vram-calculator",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'ioParams' => 1000.0005,
'ioHiddenDim' => 32800,
'ioLayers' => 128.5,
'ioBatchSize' => 2048.5,
'ioSeqLen' => 524288.5,
'ioMixedPrecision' => true,
'ioGradCheckpoint' => true
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.iotools.cloud/v1/tool/gpu-vram-calculator"
payload := strings.NewReader("{\n \"ioParams\": 1000.0005,\n \"ioHiddenDim\": 32800,\n \"ioLayers\": 128.5,\n \"ioBatchSize\": 2048.5,\n \"ioSeqLen\": 524288.5,\n \"ioMixedPrecision\": true,\n \"ioGradCheckpoint\": true\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.iotools.cloud/v1/tool/gpu-vram-calculator")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"ioParams\": 1000.0005,\n \"ioHiddenDim\": 32800,\n \"ioLayers\": 128.5,\n \"ioBatchSize\": 2048.5,\n \"ioSeqLen\": 524288.5,\n \"ioMixedPrecision\": true,\n \"ioGradCheckpoint\": true\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.iotools.cloud/v1/tool/gpu-vram-calculator")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"ioParams\": 1000.0005,\n \"ioHiddenDim\": 32800,\n \"ioLayers\": 128.5,\n \"ioBatchSize\": 2048.5,\n \"ioSeqLen\": 524288.5,\n \"ioMixedPrecision\": true,\n \"ioGradCheckpoint\": true\n}"
response = http.request(request)
puts response.read_body{
"tool": "<string>",
"tool_version": "<string>",
"outputs": {
"ioBreakdown": "<string>",
"ioGpuFit": "<string>"
},
"credits_used": 123,
"request_id": "<string>",
"credits_remaining": 123
}{
"type": "https://iotools.cloud/docs/errors/validation_error",
"title": "Invalid request",
"status": 400,
"code": "validation_error",
"detail": "One or more inputs are invalid — see `fields`.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/invalid_api_key",
"title": "Invalid API key",
"status": 401,
"code": "invalid_api_key",
"detail": "Provide 'Authorization: Bearer <key>'.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/insufficient_credits",
"title": "Insufficient credits",
"status": 402,
"code": "insufficient_credits",
"detail": "This call costs 1 credit and 0 remain in this month's allowance.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/tool_not_allowed",
"title": "Tool not available over the API",
"status": 403,
"code": "tool_not_allowed",
"detail": "\"Background Remover\" is available on iotools.cloud but has no API endpoint.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/tool_not_found",
"title": "Tool not found",
"status": 404,
"code": "tool_not_found",
"detail": "No tool with that slug. See GET /v1/tools.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/payload_too_large",
"title": "Payload too large",
"status": 413,
"code": "payload_too_large",
"detail": "Request body exceeds this tool's size limit.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/rate_limited",
"title": "Rate limit exceeded",
"status": 429,
"code": "rate_limited",
"detail": "Too many requests. Retry in 30s.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/processing_error",
"title": "Tool failed to run",
"status": 500,
"code": "processing_error",
"detail": "The tool failed to run. Please try again.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}{
"type": "https://iotools.cloud/docs/errors/tool_disabled",
"title": "Tool temporarily disabled",
"status": 503,
"code": "tool_disabled",
"detail": "This tool is temporarily unavailable. Try again shortly.",
"request_id": "e4042b29-8f1e-4c7a-9b52-6f0d1a3c7e11"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Model Preset
custom, gpt2-124m, llama-3-2-1b, llama-3-2-3b, mistral-7b, llama-3-8b, llama-2-13b, mixtral-8x7b, llama-3-70b, llama-3-1-405b Parameters (B)
0.001 <= x <= 2000Hidden Dim
64 <= x <= 65536Layers
1 <= x <= 256Workload
inference, training Precision
fp32, fp16, int8, int4 Batch Size
1 <= x <= 4096Sequence Length
1 <= x <= 1048576Optimizer
adam, sgd-momentum, sgd Mixed precision (fp32 master weights + grads)
Gradient checkpointing (recompute activations)
Response
Tool output
Output-contract version for this tool. Currently "1" for all tools.
Show child attributes
Show child attributes
Credits this call consumed, after any settlement refund. 0 when metering is disabled.
Credits left in the current monthly allowance, or null when metering is disabled.
Was this page helpful?