GPT-6.2 Astra Pro
NEWOpenAI · Proprietary · Released Nov 17, 2026 · openai/gpt-6.2-astra-pro
Best $8.00 in / $40.00 out via OpenAI
1.05M contextVisionToolsReasoningStructured outputPrompt caching
Available from 6 providersUSD / MTOK · PRICES 19 MINUTES AGO · SPEED 2 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $8.00 | $40.00 | $0.40 | 1.05M | — | 7.6s | 3211 tok/s | 100.0% | |
| $8.00 | $40.00 | $0.40 | 1.05M | — | — | — | 100.0% | |
| $8.80 | $44.00 | $0.44 | 1.05M | — | — | — | 100.0% | |
| $9.60 | $48.00 | $0.48 | 1.05M | — | — | — | — | |
| $16.00 | $80.00 | $0.80 | 1.05M | — | — | — | — | |
| $24.00 | $120.00 | $1.20 | 1.05M | — | — | — | — |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 2 minutes ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$8.00 / $40.00
per MTok in / out
BATCH
$4.00 / $20.00
async batch
CACHE READ $0.40CACHE WRITE $10.00WEB SEARCH $0.01 / search
Recent changesRSS ↗
Nov 18, 2026model added
About
GPT-6.2 Astra Pro is the same underlying model as GPT-6.2 Astra, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...
Specifications
Context window1,050,000
Max output128,000
Modalities infile, image, text
Modalities outtext
LicenseProprietary
ReleasedNov 17, 2026
TokenizerGPT
Related
Compare with
Embed badge
[](https://modelindex.ai/models/openai/gpt-6.2-astra-pro)Sources
OpenRouter API19 minutes ago
AGGREGATORModelIndex benchmarks2 minutes ago
MEASUREDVerified 19 minutes ago · list prices, not negotiated rates.