Openai · Llm model

ChatGPT API / GPT-5.4

Frontier reasoning, 1M-token context, and Codex-grade coding in one API.

Generate on Coinis Read the docs

One API key. Every model.

per 1m tokens
Example
AI text
Commercial use included Verified May 26, 2026 Outputs are yours No training on your data
Endpoints

Start building with ChatGPT API / GPT-5.4.

One model. Three ways to call it. Same key, same bill.

IN

Llm

One call. Same key. Same bill.

$4.25 / 1m tokens

OUT

Llm

One call. Same key. Same bill.

$25.5 / 1m tokens

IN

Llm

One call. Same key. Same bill.

$1.28 / 1m tokens

OUT

Llm

One call. Same key. Same bill.

$7.65 / 1m tokens

IN

Llm

One call. Same key. Same bill.

$0.26 / 1m tokens

OUT

Llm

One call. Same key. Same bill.

$1.02 / 1m tokens

Capabilities

What it does best.

GPT-5 capabilities

Context and output

  • GPT-5.4 supports a 1M+ token context window (922K input, 128K output per response), enabling high-context reasoning in a single call[^1]
  • GPT-5.4 Mini supports a 400K token context window with 128K max output, optimized for high-throughput agent workloads[^2]
  • GPT-4o Mini supports a 128K token context window, positioned for fast and inexpensive everyday tasks[^3]

Modalities

  • Accepts text and image inputs, returns text output, with full multilingual support across all three variants[^4]

Tools

  • Supports function calling, web search, file search, computer use, streaming, and structured output[^5]

Reasoning

  • Configurable reasoning effort via the reasoning parameter. Reasoning tokens are visible in the response for full transparency[^6]

Benchmarks

  • 92.0% on GPQA Diamond (graduate-level scientific reasoning)[^7]
  • 57.2 on Artificial Analysis Coding Index, placing GPT-5.4 in the top 99% of all models[^7]
  • 68.0 on Agentic Index, placing GPT-5.4 in the top 98% of all models[^7]

Pricing tiers

  • GPT-5.4 on Coinis: $4.25/1M input tokens, $25.50/1M output tokens (gpt-5-4-in / gpt-5-4-out)[^8]
  • GPT-5.4 Mini on Coinis: $1.275/1M input tokens, $7.65/1M output tokens (gpt-5-4-mini-in / gpt-5-4-mini-out)[^8]
  • GPT-4o Mini on Coinis: $0.255/1M input tokens, $1.02/1M output tokens (gpt-4o-mini-in / gpt-4o-mini-out)[^8]
  • Long-context requests above 270K tokens incur higher wholesale rates from OpenAI. Check the official docs for current tier details[^8]
  • Batch API processing (async, up to 24-hour turnaround) reduces token costs by 50%[^9]
  • Cached input pricing is available for repeated context. Check the official docs for cached rates[^9]
API

Call ChatGPT API / GPT-5.4 in three lines.

One key. One base URL. Same SDK shape you already use. 

# 1. set your key
export COINIS_API_KEY="sk_live_..."

# 2. call the model
curl https://api.app.coinis.com/v1/llm/generate \
  -H "Authorization: Bearer $COINIS_API_KEY" \
  -d '{"prompt":"neon city, rain, tracking shot"}'
import { Coinis } from "@coinis/sdk";
const coinis = new Coinis(process.env.COINIS_API_KEY);

const job = await coinis.llm.generate({
  model: "models/openai/gpt-5",
  prompt: "neon city, rain, tracking shot",
});
from coinis import Coinis
coinis = Coinis(os.environ["COINIS_API_KEY"])

job = coinis.llm.generate(
    model="models/openai/gpt-5",
    prompt="neon city, rain, tracking shot",
)
Response 
{
  "id": "gen_8fa2c1",
  "status": "succeeded",
  "model": "models/openai/gpt-5",
  "output": {
    "image_url": 
                "https://cdn.coinis.com/gen_8fa2c1.mp4"
              
              ,
    "format": "mp4"
  },
  "tokens_used": 10
}

Already on another provider's SDK? Change the host. Keep the call.

Pricing

Token pricing. No surprises.

One wallet across every model. No API accounts to juggle.

ChatGPT API / GPT-5.4 · IN
42.5 tokens
per 1m tokens · $4.25
Frontier LLM
$4.25 / 1m tokens
One key. Every model. One invoice. 1 token = $0.10
1 1m tokens ≈ 43 tokens ($4.25)
Budget variant: IN · $0.26 / 1m tokens
Start free. 15 tokens a week.

No credit card.

Why pay through Coinis
  • One wallet for every model. No API keys. No separate bills.
  • Generate ads. Launch to Meta. Track in one place.
  • On-brand output from your Brand Profile.

1 token = $0.10 pay-as-you-go. Less on a plan.

Standard vs Fast

Pick the run for the job.

IN

Final renders, studios
Resolution —
Price $4.25 / 1m tokens

OUT

Rapid tests, high volume
Resolution —
Price $25.5 / 1m tokens
Use cases

Two buyers. One model.

For builders

Resell every model. One key. One bill.

Unified API across video, image, audio, and LLM.

Generate 500 variants overnight.

Async queue plus webhooks. Batch at scale.

White-label the output.

Ship it under your brand. Outputs are yours.

For creatives

Ship a Reel before lunch.

Prompt to platform-native clip in minutes.

Same product. Ten formats.

One generation, every aspect ratio.

Commercial UGC without a creator.

Authentic selfie-style ads, on brand.

Production coding agents and software engineering GPT-5.4 unifies Codex-grade coding with GPT-level reasoning in a single model. Use it to generate, review, and refactor production code, or to run multi-step software engineering workflows that require tool use and long-context understanding.[^10]

Long-context document synthesis and RAG Feed entire codebases, legal contracts, or research corpora into a single GPT-5.4 call. The 1M+ token context window lets you synthesize across hundreds of documents without chunking or losing coherence.[^1]

Multi-step agentic workflows GPT-5.4's computer use, web search, and file search tools make it the right choice for autonomous agents that need to browse, read, write, and act across multiple systems in a single session.[^5]

High-throughput chat, coding assistants, and subagents GPT-5.4 Mini is built for production chat applications and agent pipelines where you need strong capability at scale. At $1.275/1M input tokens on Coinis, it handles millions of interactions at a predictable cost.[^2]

Classification, routing, and low-cost inference GPT-4o Mini handles classification, intent detection, and routing tasks at $0.255/1M input tokens on Coinis. It is the right default for any pipeline step where a smaller, faster, cheaper model is sufficient.[^3]

Renders in seconds. Set a seed. Get the same frame back.

Outputs are yours. Sell them.

Safe for paid ads.

Your prompts are never used for training.

FAQ

ChatGPT API / GPT-5.4 FAQs

How much does GPT-5 cost per 1M tokens on the API?

On Coinis, GPT-5.4 costs $4.25/1M input tokens and $25.50/1M output tokens. GPT-5.4 Mini costs $1.275/1M input and $7.65/1M output. GPT-4o Mini costs $0.255/1M input and $1.02/1M output. All rates are pay-as-you-go with no minimum spend and no separate vendor contract.

What is the difference between GPT-5.4 and GPT-5.4 Mini?

GPT-5.4 is the full frontier model with a 1M+ token context window, top benchmark scores, and the deepest reasoning capability. GPT-5.4 Mini has a 400K token context window and is optimized for high-throughput production workloads including chat, coding assistants, and subagent pipelines. Choose GPT-5.4 when task complexity or context length demands it. Choose GPT-5.4 Mini when you need strong performance at a lower cost per call.

Should I use GPT-5.4 Mini or GPT-4o Mini for cheap, high-volume tasks?

GPT-5.4 Mini is the better choice for most new work. It is stronger on coding, computer use, and agentic tasks, and it offers a 400K token context window. GPT-4o Mini is older and cheaper at $0.255/1M input, and it remains useful for simple classification or routing steps where you have already tuned prompts against it. For anything new, start with GPT-5.4 Mini.

Does GPT-5 pricing change for long contexts above 270K tokens?

Yes. OpenAI applies higher wholesale rates for requests that exceed roughly 270K tokens. Those elevated rates are passed through on Coinis. For most workloads under that threshold, the standard rates apply. If you consistently process very long contexts, check the official pricing docs at openai.com/api/pricing/ for current tier details.

Is there a Batch API discount on GPT-5 through Coinis?

Yes. The Batch API processes requests asynchronously with up to a 24-hour turnaround and reduces token costs by 50% on both input and output. It is available for workloads that do not require real-time responses. Contact Coinis support or see the API docs to enable batch mode for your account.

Can I use GPT-5 with function calling, web search, and computer use on Coinis?

Yes. All tool capabilities supported by GPT-5.4 and GPT-5.4 Mini are available through the Coinis API endpoint, including function calling, web search, file search, computer use, streaming, and structured output. Configure them via the standard OpenAI-compatible request parameters.

How is Coinis different from calling the OpenAI API directly or via OpenRouter?

Calling OpenAI directly gives you wholesale rates but requires a separate billing account, quota management, and a new integration for every other model vendor. OpenRouter aggregates models but its GPT-5.4 price jumps above 272K tokens. Coinis gives you GPT-5.4, GPT-5.4 Mini, GPT-4o Mini, and models from Anthropic, Google, and others on a single API key, one invoice, and one unified endpoint. You switch models by changing a parameter, not by changing vendors.

Related

Pair it with.

Claude (Sonnet 4.6 / Opus 4.7 / Haiku 4.5)

Model

DeepSeek V4 Flash

Model

Gemini 3.1 / 2.5

Model

All LLM models

Catalog
Upscale this Edit a frame Add a voiceover

Start free

Your wallet. Every model. One call away.

Start free. 15 tokens a week. No card.

Generate on Coinis

No credit card.

Pricing and capabilities verified 2026-05-26. Read the docs .