NewHow we catch a seller listing the wrong model, and refund you if one does.
UberLLM

Cheapest GPT API: below OpenAI on 10 of 10 models (November 2026)

Updated November 20, 2026, 09:00 UTC. UberLLM prices are read live when the page is built (every hour); other providers' prices were checked November 19, 2026 or read from their public price lists at build. UberLLM wrote this page and is one of the providers in it.

On November 20, 2026, UberLLM was below OpenAI’s own price on both input and output for 10 of the 10 GPT models we compared, with UberLLM’s card fee added. Among the real-time prices in the table, UberLLM was lowest on 15 of the 15 models. UberLLM prices are the best seller’s price now; they move during the day.

Some UberLLM prices here are more than 70% below list. They are what buyers were billed, not errors. Why so cheap?

ProviderHow you payPrice against OpenAI’s
UberLLMPer token, prepaid; 5.5% + $0.50 card fee when adding creditBelow it on 10 of 10 models (card fee added)
OpenAI APIPer token, direct from OpenAIThe list price
OpenRouterPrepaid credit; 5.5% when buying creditAgainst OpenAI’s price: the same on 10 of 10
Vercel AI GatewayCredit in your Vercel accountAgainst OpenAI’s price: the same on 10 of 10
RequestyPrepaid; 5% on model costs, added when you top upAgainst OpenAI’s price: the same on 10 of 10

UberLLM first, then OpenAI’s own API, then the other providers that list these models. The table below shows, model by model, who is lowest. An empty cell means we could not confirm it on the provider's own pages.

GPT prices, model by model ($ per 1M input / output tokens)

ModelUberLLMOpenAIOpenRouterVercel AI GatewayRequesty
GPT-6.1 SolWhy so cheap?$0.0692 / $0.346$2.00 / $10.00$2.00 / $10.00$2.00 / $10.00$2.00 / $10.00
GPT-6 LunaWhy so cheap?$0.00299 / $0.015$0.10 / $0.50$0.10 / $0.50$0.10 / $0.50$0.10 / $0.50
GPT-6.2 Sol$0.20 / $1.00$2.00 / $10.00$2.00 / $10.00$2.00 / $10.00
GPT-6.1 TerraWhy so cheap?$0.1183 / $0.5914$1.00 / $5.00$1.00 / $5.00$1.00 / $5.00$1.00 / $5.00
GPT-6 AstraWhy so cheap?$0.50 / $2.50$10.00 / $50.00$10.00 / $50.00$10.00 / $50.00$10.00 / $50.00
GPT-5.6 LunaWhy so cheap?$0.02 / $0.12$0.20 / $1.20$0.20 / $1.20$0.20 / $1.20$0.20 / $1.20
GPT-5.4 MiniWhy so cheap?$0.073 / $0.4379$0.75 / $4.50$0.75 / $4.50$0.75 / $4.50$0.75 / $4.50
GPT-6.2 AstraWhy so cheap?$1.0065 / $5.0325$8.00 / $40.00$8.00 / $40.00$8.00 / $40.00$8.00 / $40.00
GPT-5.5$1.1935 / $7.161$5.00 / $30.00$5.00 / $30.00$5.00 / $30.00
GPT-4oWhy so cheap?$0.2463 / $0.985$2.50 / $10.00$2.50 / $10.00$2.50 / $10.00$2.50 / $10.00
GPT-6 SolWhy so cheap?$0.0546 / $0.273$2.00 / $10.00$2.00 / $10.00$2.00 / $10.00$2.00 / $10.00
GPT-6.2 Sol Pro$1.596 / $7.98$2.00 / $10.00
GPT 5.4 NanoWhy so cheap?$0.0315 / $0.1971$0.20 / $1.25$0.20 / $1.25$0.20 / $1.25$0.20 / $1.25
GPT-6.2 Astra Pro$6.384 / $31.92$8.00 / $40.00
GPT-6.1 Terra Pro$0.798 / $3.99$1.00 / $5.00

UberLLM: the best seller’s price, read November 20, 2026; the 5.5% card fee is not in the cell. OpenAI: its own pricing page, checked November 19, 2026; an empty cell means its page does not list that model. OpenRouter, Vercel AI Gateway and Requesty: each one’s public model list, read when this page was built.

Each provider, good and bad

UberLLM

Pick it if: You want GPT below OpenAI’s price, billed per request with no plan, and the same key for every other model.

Watch for: Requests go to third-party providers, not to OpenAI directly: if you need OpenAI’s own data terms, use its API. The price is a market price and can be higher when the lower-priced sellers are busy (cap it with provider.max_price).

Source: UberLLM GPT prices (live, November 20, 2026)

OpenAI API

Pick it if: You want OpenAI’s own terms, every new feature first and its Batch, Flex and background tiers.

Watch for: The list price for real-time use; Fast mode (formerly Priority) costs more.

Source: OpenAI pricing (checked 2026-11-19)

OpenRouter

Pick it if: You already use OpenRouter for other models and want automatic failover.

Watch for: Its 5.5% credit fee comes on top of the prices in the table.

Source: OpenRouter pricing, its model list (checked 2026-11-19)

Vercel AI Gateway

Pick it if: Your app runs on Vercel or uses the AI SDK.

Watch for: No markup on provider token prices, so no saving per token either.

Source: Vercel AI Gateway pricing, its model list (checked 2026-11-19)

Requesty

Pick it if: You want routing rules, fallbacks and per-team spend limits.

Watch for: The 5% top-up fee comes on top of the prices in the table.

Source: Requesty pricing, its model list (checked 2026-11-19)

How to switch to UberLLM

UberLLM takes OpenAI-style requests: change the base URL, the key and the model id (GPT ids on UberLLM start with openai/).

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.uberllm.dev/v1",  # was: https://api.openai.com/v1
    api_key="ull_your_key_here",
)

resp = client.chat.completions.create(
    model="openai/gpt-6.1-sol",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

No UberLLM fee on requests. Adding credit by card costs 5.5% + $0.50.

Questions

Is the OpenAI Batch API cheaper?

Yes. OpenAI lists separate, lower Batch and Flex prices for work that can wait; for example GPT-6.2 Astra is $4 / $20 per 1M tokens in Batch against $8 / $40 standard. Results are not real-time.

What happened to OpenAI Priority processing?

OpenAI renamed Priority processing to Fast mode on July 30, 2026. It costs more than the standard price.

Does UberLLM work with the OpenAI SDK?

Yes. Set base_url to https://api.uberllm.dev/v1 and use an UberLLM key; /v1/chat/completions and /v1/responses both work.

Can I cap what a GPT request costs on UberLLM?

Yes. Send provider.max_price with the most you will pay per million tokens; the request only goes to sellers at or under it.

Are there other fees on UberLLM?

No UberLLM fee on requests. Adding credit by card costs 5.5% + $0.50.