Tokely
All models

OpenAI

gpt-5-mini

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

textAPI availablestreamingreasoningfunction tools
gpt-5-miniVersion date 2025-08-07

Tokely price / 1M tokens

$0.459563input
$0.045957cached input
$3.6765output

USD · Published rate · Updated 2026-10-06

OpenRouter reference$0.25 input · $2 output / 1M tokensStandard listed rates · 2026-10-06

Context window

400,000tokens · model specification

Model max output

128,000tokens

First request

Available
curl https://tokely.me/v1/responses \
  -H "Authorization: Bearer $TOKELY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-mini",
    "input": "Hello!",
    "max_output_tokens": 1024,
    "store": false
  }'

Set TOKELY_API_KEY to your dashboard key. Requests require a funded Tokely balance. Base URL: https://tokely.me/v1.

Compare nearby prices

USD per million tokens. Compare price and context; these are not quality benchmarks.
ModelInputOutputContext
gpt-5-miniOpenAI · this model$0.459563$3.6765400,000
gpt-5-mini-2025-08-07OpenAI$0.459563$3.6765400,000
MiniMax-M2.7MiniMax$0.825$3.3204,800
gemini-3.1-flash-liteGoogle$0.597432$3.5845881,048,576
gemini-3.1-flash-lite-previewGoogle$0.597432$3.5845881,048,576

Capabilities & limits

Provider
OpenAI
API model ID
gpt-5-mini
Category
Text
Endpoints
POST /v1/responses
Tokely max output
65,536 tokens / request, including reasoning tokens
Default output
256 tokens. Set an explicit limit for longer responses.
Request limits
256 KB JSON body · 128 messages · 32 function tools
Rate limit
60 requests / minute / account, across its keys
Supported input
Text messages and function tool results
Model modalities
text, image, file. Tokely currently accepts text input.

The context includes your instructions, conversation history, tool definitions and generated output. Keep the input and requested output within the model’s context window.

OpenRouter model reference

API reference

Authenticate with Authorization: Bearer YOUR_TOKELY_API_KEY. Use an OpenAI SDK with the Tokely base URL.

model
Required string: gpt-5-mini
input
Text or an array of text messages and function call results. Send history in each request; use store=false.
max_output_tokens
Optional integer, 1–65,536. Defaults to 256.
stream
Set true for Server-Sent Events (SSE).
reasoning.effort
Optional reasoning effort. Supported values depend on the model; omit to use its default.
tools
Function definitions executed by your application. Provider-hosted tools are not enabled.

The response contains output items and usage (input_tokens, output_tokens, total_tokens). Streaming uses named Responses events.

400 / 415
Invalid request, parameter, endpoint for this model, or content type.
401 / 403
Invalid, revoked or restricted API key.
402
Insufficient account balance or API key budget.
429
Request limit reached. Retry after the indicated delay.
502 / 503 / 504
Upstream failure, temporary service unavailability or request timeout.

Frequently asked questions

How much does gpt-5-mini cost?

$0.459563 per million input tokens, $3.6765 per million output tokens and $0.045957 per million cached input tokens. Usage is charged to your Tokely balance.

Do I need a separate OpenAI account?

Use your Tokely API key and balance. A separate provider key is not required.

How do I switch to this model?

Set model to gpt-5-mini and use /v1/responses. Keep your Tokely base URL and API key.

What is the context window?

400,000 tokens, including input and output. The Tokely request body and output limits listed above also apply.

Related versions

gpt-52025-08-07gpt-5-mini-2025-08-072025-08-07