OpenAI GPT API pricing 2026 — GPT-5.4, 5.5, Mini & Codex costs, examples, cheaper access

This is OpenAI GPT API pricing for 2026: the per-model token rates for the GPT-5 family, worked cost examples, and the levers that cut a GPT bill the most. Kunavo prices the family about 60% below OpenAI's list rate behind one OpenAI-compatible API.

Rates last verified July 2, 2026. Kunavo's per-token prices below are read live from the model catalog, and the “OpenAI list” column tracks OpenAI's published rate — the official source is openai.com/api/pricing (developer detail at platform.openai.com/docs/pricing).

GPT API pricing at a glance

Rates are per 1M tokens, in USD, as billed on Kunavo. The “OpenAI list” column is OpenAI's published rate for the same model.

Live rates always show on the pricing page and each model page. Mini is the cheap workhorse, GPT-5.4 the balanced default, Codex the coding specialist, GPT-5.5 and 5.5 Pro the heavy reasoners.

How GPT token pricing works

You pay for input tokens (system prompt, context, messages) and output tokens (the completion). On the GPT-5 family output runs ~6× the input rate, so the biggest lever on cost is how much the model writes. These are reasoning models: the hidden reasoning tokens they generate are billed at the output rate, which is why capping max_tokens and lowering the reasoning effort matter.

Worked cost examples

Real numbers at Kunavo's rates:

So a million cheap Mini turns runs about $630. The math, runnable:

# Kunavo GPT rates (USD per 1M tokens): (input, output)
RATES = {
    "gpt-5-4-mini":  (0.225, 1.35),
    "gpt-5-4":       (1.00, 6.00),
    "gpt-5-3-codex": (0.70, 5.60),
    "gpt-5-5":       (2.00, 12.00),
}

def cost(model: str, in_tokens: int, out_tokens: int) -> float:
    i, o = RATES[model]
    # NOTE: on GPT-5 reasoning models, reasoning tokens are billed as output.
    return in_tokens / 1_000_000 * i + out_tokens / 1_000_000 * o

print(cost("gpt-5-4-mini", 1_000, 300))   # cheap turn   -> $0.00063
print(cost("gpt-5-4", 6_000, 500))        # RAG answer   -> $0.009
print(cost("gpt-5-5", 20_000, 3_000))     # hard problem -> $0.076

Kunavo pricing and Stripe billing

No subscription, no OpenAI Platform billing setup. Top up a balance (Stripe or local payment methods) and calls draw down at the rates above. Pay-as-you-go from a $5 minimum top-up, the balance never expires, and larger top-ups carry bonus credit. The same balance covers GPT, Claude, Gemini, image, video and audio models — one wallet, one invoice.

Which GPT model should I choose?

• gpt-5-4-mini — default for high-volume chat, extraction and classification. Cheapest capable GPT tier.
• gpt-5-4 — the balanced default for most reasoning and RAG.
• gpt-5-3-codex — tuned for code generation and agentic coding.
• gpt-5-5 / gpt-5-5-pro — reach for these only when the cheaper tiers aren't accurate enough on the hardest problems.

Route by difficulty — send the easy 80% to Mini, escalate the hard 20% — and see the AI cost optimization guide for the pattern in code. Comparing providers? See the Claude and Gemini pricing guides.

FAQ

Is the GPT API free?

OpenAI has no free GPT API tier — you pay per token from the first call. Kunavo is pay-as-you-go from a $5 minimum top-up, with per-token rates about 60% under OpenAI's list and a balance that never expires.

How much does the GPT-5 API cost?

On Kunavo, GPT-5.4 is $1.00 / $6.00 per 1M tokens — about 60% under OpenAI's $2.50 / $15.00. GPT-5.4 Mini is $0.225 / $1.35 and GPT-5.5 is $2.00 / $12.00.

Are reasoning tokens billed separately on GPT-5?

GPT-5 reasoning models emit hidden reasoning tokens billed at the output rate. Cap max_tokens and lower reasoning effort where the task allows — output is the pricey side of the meter.

Can I call GPT with the OpenAI SDK through Kunavo?

Yes — keep the OpenAI SDK, set base_url to https://api.kunavo.com/v1, and use a GPT slug like gpt-5-4. To start, see the quickstart.