o3 (batch)
by OpenAI · openai/o3:batch · #288 cheapest of 422 paid models
Prices updated Sep 19, 2026, 9:36 PM UTC · refreshed hourly
o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$1.00
per 1M tokens
Output
$4.00
per 1M tokens
Blended (3:1)
$1.75
3 input : 1 output
Cache read
$0.25
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for o3 (batch) with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.75 | $0.106 | — |
| 50% | $1.47 | $0.0685 | −35% |
| 90% | $1.24 | $0.0385 | −64% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.0017 | $1.70 |
| Document summary | 8,000 | 1,000 | $0.012 | $12.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.038 | $38.00 |
| Long-context analysis | 150,000 | 5,000 | $0.17 | $170.00 |
Performance
Intelligence Index
20.2
AA composite quality
Coding Index
—
Math Index
88.3
Agentic Index
—
Output speed
136 tok/s
median
Time to first token
5.43s
median
Time to first answer
5.43s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 85.3% |
| GPQA Diamond | 82.7% |
| Humanity's Last Exam | 20.1% |
| LiveCodeBench | 80.8% |
| MATH-500 | 99.2% |
| AIME | 90.3% |
| AIME 2025 | 88.3% |
| IFBench | 71.4% |
| AA-LCR (Long Context Reasoning) | 74.7% |
| Terminal-Bench Hard | 37.1% |
| τ²-Bench (Telecom) | 80.7% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,048 |
| UI components | 1,032 |
| Data viz | 1,200 |
| Game dev | 1,058 |
| Code categories | 1,035 |
Specs
Context window
200K
tokens
Max output
100K
tokens
Input modalities
image, text, file
Tokenizer
GPT