OpenAI GPT API pricing 2026 — GPT-6, GPT-5.6 & GPT-5.5 costs, examples, cheaper access

This is OpenAI GPT API pricing for 2026: the per-model token rates for the GPT-5 and GPT-6 families, worked cost examples, and the levers that cut a GPT bill the most. Kunavo prices the family about 65% below OpenAI's list rate behind one OpenAI-compatible API.

Rates last verified September 29, 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. Where OpenAI is running a promotion, the rate it charges today is shown under the list rate, and “You save” gives the gap to both.

Live rates always show on the pricing page and each model page. GPT-6 Luna is the cheapest tier, GPT-6 Sol the balanced default for coding and agents at a lower output rate than GPT-5.6 Terra, and GPT-5.6 Sol, GPT-5.5 and GPT-6 Astra the heavy reasoners.

GPT-6 is OpenAI's newest family. GPT-6 Astra arrived September 3, 2026 as OpenAI's most capable model; GPT-6 Sol and GPT-6 Luna followed on September 22, and OpenAI says they "build on the advances behind GPT-6 Astra". All three carry a 1.05M-token context window. On Kunavo GPT-6 Sol costs $0.80 / $4.00 and GPT-6 Luna $0.04 / $0.20 — the GPT-6 API guide covers which to call and working code.

GPT-5.6 Sol is the flagship of the GPT-5.6 generation — top-tier reasoning and agentic coding with a 1.05M-token context window, still on sale for prompts validated on it. Its list price is $5.00 / $30.00 per 1M, the same list price as GPT-5.5, so on Kunavo it lands at the same $2.00 / $12.00 — about 60% under list. OpenAI is currently charging a promotional $4.00 / $20.00 for Sol, available at least through November 21, 2026 according to its pricing page; against what OpenAI charges today, Kunavo is about 40% under on output rather than 60%. If you are already on gpt-5-5, moving to gpt-5-6-sol is a one-word change that costs the same per token on Kunavo.

One caveat on very long requests. OpenAI bills requests above 272,000 input tokens at 2× input and 1.5× output for the entire request, cached input included. Kunavo applies the same tier on GPT-5.5, GPT-5.6 Sol and Terra, and GPT-6 Astra, Sol and Luna, so past that threshold those models' rates double on input and rise by half on output — and the saving versus calling OpenAI directly is the same percentage on either side of it, because both prices move together.

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 GPT-5.6 Terra turns runs about $1,960. To price your own traffic mix, use the OpenAI API pricing calculator. The math, runnable:

# Kunavo GPT rates (USD per 1M tokens): (input, output)
RATES = {
    "gpt-5-6-terra": (0.70, 4.20),
    "gpt-5-5":       (2.00, 12.00),
    "gpt-5-6-sol":   (2.00, 12.00),
    "gpt-6-sol":     (0.80, 4.00),
    "gpt-6-luna":    (0.04, 0.20),
}

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-5-6-terra", 1_000, 300))  # cheap turn      -> $0.00196
print(cost("gpt-5-6-terra", 6_000, 500))  # RAG answer      -> $0.0063
print(cost("gpt-5-5", 20_000, 3_000))     # hard problem    -> $0.076
print(cost("gpt-5-6-sol", 20_000, 3_000)) # 5.6 flagship    -> $0.076
print(cost("gpt-6-sol", 20_000, 3_000))   # GPT-6 Sol       -> $0.028
print(cost("gpt-6-luna", 1_000, 300))     # cheapest turn   -> $0.000100

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 $10 minimum top-up, the balance never expires, and larger top-ups carry bonus credit. The same balance covers GPT, Claude, image, video and audio models — one wallet, one key.

Which GPT model should I choose?

• gpt-6-luna — the cheapest GPT on Kunavo, at $0.04 / $0.20: high-volume classification, extraction and routing, where OpenAI positions it.
• gpt-6-sol — the balanced default for coding and agentic work, at $0.80 / $4.00: a lower output rate than GPT-5.6 Terra's $4.20, and a higher input rate than its $0.70.
• gpt-5-6-terra / gpt-5-6-sol — the GPT-5.6 tiers, for prompts already validated on them.
• gpt-5-5 / gpt-6-astra — reach for these only when the cheaper tiers aren't accurate enough on the hardest problems. GPT-6 Astra is the deep-horizon tier, so justify it before you reach for it.

Route by difficulty — send the easy 80% to Luna, escalate the hard 20% — and see the AI cost optimization guide for the pattern in code. Comparing providers? See the Claude pricing guide. Hitting ceilings rather than costs? OpenAI API rate limits covers which of RPM/TPM/RPD you actually hit and the retry that fixes it.

FAQ