o1 (2024-12-17) API pricing
Updated
The cheapest standard price for o1 (2024-12-17) is Microsoft Azure at USD 15 per 1M input tokens and USD 60 per 1M output tokens. Every price is read from the provider's own pricing page, checked 2026-11-14.
Does OpenAI sell o1 (2024-12-17) directly?
OpenAI publishes no price for o1 (2024-12-17) on its own API that we could find, so this page compares hosts only.
o1 (2024-12-17) price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Microsoft Azure cheapestNotes and source quoteAzure OpenAI Global (global standard) deployment. “o1 2024-12-17 Global Input: $15 | Cached Input: $7.50 | Output: $60” | USD 15 | USD 7.50 | USD 60 | USD 26.25 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does o1 (2024-12-17) cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| Microsoft Azure | USD 2,025 | USD 3,960 | USD 20,925 |
What does o1 (2024-12-17) cost in other languages?
The same text needs a different number of tokens in each language. With the GPT (o200k) tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for o1 (2024-12-17):
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 3.20 | Microsoft Azure |
| Arabic MSA | USD 4.79 | Microsoft Azure |
| Hindi | USD 4.83 | Microsoft Azure |
| Chinese | USD 11.57 | Microsoft Azure |
| Code | USD 3.81 | Microsoft Azure |
From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.
Estimate your own bill
- LLM API cost calculator with o1 (2024-12-17) preloaded: your traffic and cache rate, against any of 428 models.
- Token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does o1 (2024-12-17) compare with other OpenAI models?
The OpenAI models whose cheapest standard price is closest to o1 (2024-12-17)'s (USD 26.25 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| GPT-6 Astra | USD 10 | USD 50 | 1,050,000 | 6 |
| GPT-5 Pro | USD 15 | USD 120 | — | 2 |
| GPT-5.2 Pro | USD 21 | USD 168 | — | 2 |
| GPT Chat Latest | USD 5 | USD 30 | — | 2 |
| GPT-5.5 | USD 5 | USD 30 | 1,050,000 | 6 |
| GPT-5.4 Pro | USD 30 | USD 180 | — | 3 |
Priced closest from other makers: Claude Fable 5 (Anthropic, USD 20) · Claude Fable 5.1 (Anthropic, USD 20) · Claude Fable 5.2 (Anthropic, USD 16).
All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the o1 (2024-12-17) API cost per token?
From USD 15 per 1M input tokens (USD 0.000015 per token) and USD 60 per 1M output tokens (USD 0.00006 per token) at the cheapest standard price. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for o1 (2024-12-17)?
Microsoft Azure is the only provider with a paid standard price, USD 15 input and USD 60 output per 1M tokens, so there is nothing to rank yet.
Does OpenAI sell o1 (2024-12-17) on its own API?
OpenAI publishes no price for o1 (2024-12-17) on its own API that we could find, so there is no maker price to compare. The cheapest host is Microsoft Azure at USD 15 / USD 60 per 1M tokens.
Does o1 (2024-12-17) have cached input pricing?
Yes. The lowest is USD 7.50 per 1M at Microsoft Azure. Providers without one bill cached input at the input price. What cached input means.
How much does a coding agent cost per month on o1 (2024-12-17)?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 20,925 a month at Microsoft Azure. Most of the input is cached, so the cache price matters as much as the input price. Try your own numbers.
Is o1 (2024-12-17) free to use through an API?
No provider in our data lists a free price for o1 (2024-12-17) as of 2026-11-14. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.