GPT-6 Astra
by OpenAI · openai/gpt-6-astra · #404 cheapest of 422 paid models
Prices updated Sep 20, 2026, 12:34 AM UTC · refreshed hourly
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$10.00
per 1M tokens
Output
$50.00
per 1M tokens
Blended (3:1)
$20.00
3 input : 1 output
Cache read
$1.00
per 1M cached tokens
Cache write
$12.50
per 1M tokens
Cache & batch economics
Effective prices for GPT-6 Astra with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $20.00 | $1.07 | — |
| 50% | $16.63 | $0.62 | −42% |
| 90% | $13.93 | $0.26 | −76% |
*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 | $0.02 | $20.00 |
| Document summary | 8,000 | 1,000 | $0.13 | $130.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.4 | $400.00 |
| Long-context analysis | 150,000 | 5,000 | $1.75 | $1,750 |
Performance
Intelligence Index
52.7
AA composite quality
Coding Index
76.9
Math Index
—
Agentic Index
51.5
Output speed
63 tok/s
median
Time to first token
204.28s
median
Time to first answer
204.28s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 96.1% |
| Humanity's Last Exam | 54.7% |
| SciCode | 56.5% |
| AA-LCR (Long Context Reasoning) | 80.7% |
| Terminal-Bench 2.1 | 88.4% |
| τ³-Bench Banking | 41.4% |
Specs
Context window
1.05M
tokens
Max output
128K
tokens
Input modalities
file, image, text
Tokenizer
GPT