o3 (2025-04-16) API pricing
Updated
3 providers tie for the cheapest standard price for o3 (2025-04-16) on the 3:1 blend; OpenAI charges USD 2 per 1M input tokens and USD 8 per 1M output tokens. The median across 3 standard prices is USD 2 / USD 8. That is OpenAI's own API. Every price is read from the provider's own pricing page, checked 2026-11-14.
What does OpenAI charge for o3 (2025-04-16)?
- Input
- USD 2
- Cached input
- USD 0.50
- Output
- USD 8
- Blended 3:1
- USD 3.50
USD per 1M tokens on OpenAI, model o3, standard tier. Source, checked 2026-11-14.
Other OpenAI tiers: batch USD 1 / USD 4 · flex / spot USD 1 / USD 4 · fast USD 3.50 / USD 14.
Is a host cheaper than OpenAI? They tie. DigitalOcean and OpenAI's own API both work out at USD 3.50 per 1M tokens on the 3:1 blend.
o3 (2025-04-16) price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 0% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | OpenAI tied cheapest makero3Notes and source quote“| o3 | $2.00 | $8.00 | $0.50 |” | USD 2 | USD 0.50 | USD 8 | USD 3.50 | not stated | not stated | OpenAI page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | DigitalOcean tied cheapestNotes and source quote“o3 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$2.00$8.00$0.50” | USD 2 | USD 0.50 | USD 8 | USD 3.50 | not stated | not stated | DigitalOcean page checked 2026-11-14 re-checked 2026-11-16 |
| 3 | Microsoft Azure tied cheapestNotes and source quoteAzure OpenAI Global (global standard) deployment. “o3 2025-04-16 Global Input: $2 | Cached Input: $0.50 | Output: $8” | USD 2 | USD 0.50 | USD 8 | USD 3.50 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
| — | OpenAI maker batcho3Notes and source quoteBatch API (asynchronous). “| o3 | $1.00 | $4.00 | - |” | USD 1 | not published | USD 4 | USD 1.75 | not stated | not stated | OpenAI page checked 2026-11-14 re-checked 2026-11-16 |
| — | Microsoft Azure batchNotes and source quoteAzure OpenAI Global deployment, "Pricing with Batch API (1M Tokens)" column. “o3 2025-04-16 Global Input: $1 | Output: $4” | USD 1 | not published | USD 4 | USD 1.75 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
| — | OpenAI maker flex / spoto3Notes and source quoteFlex processing. “| o3 | $1.00 | $4.00 | $0.25 |” | USD 1 | USD 0.25 | USD 4 | USD 1.75 | not stated | not stated | OpenAI page checked 2026-11-14 re-checked 2026-11-16 |
| — | DigitalOcean flex / spotNotes and source quote“o3 — Processing modePrompt lengthInputOutputCache read: Flex Mode All prompts$1.00$4.00$0.25” | USD 1 | USD 0.25 | USD 4 | USD 1.75 | not stated | not stated | DigitalOcean page checked 2026-11-14 re-checked 2026-11-16 |
| — | OpenAI maker fasto3Notes and source quoteFast mode (formerly Priority processing). “| o3 | $3.50 | $14.00 | $0.875 |” | USD 3.50 | USD 0.875 | USD 14 | USD 6.125 | not stated | not stated | OpenAI page checked 2026-11-14 re-checked 2026-11-16 |
| — | DigitalOcean fastNotes and source quote“o3 — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$3.50$14.00$0.875” | USD 3.50 | USD 0.875 | USD 14 | USD 6.125 | not stated | not stated | DigitalOcean 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.
- Other tiers (batch, flex / spot and fast): batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
- 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 o3 (2025-04-16) 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) |
|---|---|---|---|
| OpenAI (maker) | USD 243.00 | USD 492.00 | USD 2,025 |
| DigitalOcean | USD 243.00 | USD 492.00 | USD 2,025 |
| Microsoft Azure | USD 243.00 | USD 492.00 | USD 2,025 |
For the support chatbot, the cheapest price (OpenAI and 2 others, tied, USD 243.00 a month) saves USD 0 against the median (USD 243.00). For the coding agent the gap is USD 0 a month.
Which o3 (2025-04-16) provider is cheapest for your traffic?
All 3 providers charge the same standard price, USD 2 input and USD 8 output per 1M tokens, so the per-token price does not decide between them: compare the cache and context lines below.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| OpenAI (maker) | USD 3.50 cheapest | USD 2.938 cheapest | USD 2.487 cheapest |
| DigitalOcean | USD 3.50 cheapest | USD 2.938 cheapest | USD 2.487 cheapest |
| Microsoft Azure | USD 3.50 cheapest | USD 2.938 cheapest | USD 2.487 cheapest |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
All 3 providers publish a cached-input price below the input price: OpenAI (75% off), DigitalOcean (75% off), Microsoft Azure (75% off).
No provider states a context window for o3 (2025-04-16) on its pricing page.
What does o3 (2025-04-16) 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 o3 (2025-04-16):
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.427 | DigitalOcean |
| Arabic MSA | USD 0.639 | DigitalOcean |
| Hindi | USD 0.644 | DigitalOcean |
| Chinese | USD 1.54 | DigitalOcean |
| Code | USD 0.508 | DigitalOcean |
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 o3 (2025-04-16) 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 o3 (2025-04-16) compare with other OpenAI models?
The OpenAI models whose cheapest standard price is closest to o3 (2025-04-16)'s (USD 3.50 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| GPT-4.1 (2025-04-14) | USD 2 | USD 8 | — | 3 |
| GPT-5 (2025-08-07) | USD 1.25 | USD 10 | — | 3 |
| GPT-5.1 | USD 1.25 | USD 10 | — | 2 |
| GPT-6 Sol | USD 2 | USD 10 | 1,050,000 | 6 |
| GPT-6.1 Sol | USD 2 | USD 10 | 1,050,000 | 6 |
| GPT-4o | USD 2.50 | USD 10 | — | 2 |
Priced closest from other makers: Gemini 2.5 Pro (Google, USD 3.438) · Gemini 3.5 Flash (Google, USD 3.375) · Kimi K3 (Moonshot AI, USD 3.763).
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 o3 (2025-04-16) API cost per token?
From USD 2 per 1M input tokens (USD 0.000002 per token) and USD 8 per 1M output tokens (USD 0.000008 per token) at the cheapest standard price. The median of 3 standard prices is USD 2 input and USD 8 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for o3 (2025-04-16)?
3 providers are tied for the cheapest: OpenAI, DigitalOcean and Microsoft Azure, each USD 3.50 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 2 (OpenAI and 2 others, tied); for output alone, USD 8 (OpenAI and 2 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Is o3 (2025-04-16) cheaper from a host than from OpenAI?
They tie. DigitalOcean and OpenAI's own API both work out at USD 3.50 per 1M tokens on the 3:1 blend.
Does o3 (2025-04-16) have cached input pricing?
All 3 standard prices include one. The lowest is USD 0.50 per 1M at OpenAI; the median is USD 0.50. Providers without one bill cached input at the input price. What cached input means.
How much does a coding agent cost per month on o3 (2025-04-16)?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 2,025 a month at OpenAI, USD 2,025 at the median price and USD 2,025 at Microsoft Azure. Try your own numbers.
Is there a batch, flex or priority price for o3 (2025-04-16)?
Yes: batch from OpenAI at USD 1 / USD 4; flex / spot from OpenAI at USD 1 / USD 4; fast from OpenAI at USD 3.50 / USD 14 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.
Is o3 (2025-04-16) free to use through an API?
No provider in our data lists a free price for o3 (2025-04-16) as of 2026-11-14. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.