GPT-6.2 Astra Pro
Launch tracker · day 5
GPT-6.2 Astra Pro at launch: the first independent results
As of 21 Nov 2026, GPT-6.2 Astra Pro (OpenAI, released 17 Nov 2026) has independent results from Epoch AI (SimpleBench 79.2%). It has no BenchLeader Index yet: the Index needs at least five independent results across two categories. It is listed at $8.00 in / $40.00 out per 1M tokens, with a 1.1M-token context window. Not yet measured by Artificial Analysis, LMArena, Vals AI, LiveBench, ARC Prize, Scale AI and SWE-bench.
- Released
- 17 Nov 2026 (day 5)
- Provider
- OpenAI
- Price
- $8.00 in / $40.00 out per 1M tokens
- Context window
- 1.1M tokens
- Open weights
- Not stated
- BenchLeader Index
- Not yet (needs five results in two categories)
| Independent board | Results so far |
|---|---|
| Epoch AI | SimpleBench 79.2% |
Boards usually post results within days of a launch; this page is rebuilt every three hours.
Launch comparisons
Scores from independent publishers only; benchmark figures a provider publishes about its own model are not shown.
Good value at this level: no ranked model within 2 Index points costs three quarters of the price or less.
No cheaper ranked model scores higher: it is on the price frontier.
As of 21 Nov 2026, GPT-6.2 Astra Pro by OpenAI is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. API pricing: $8.00 per 1M input tokens and $40.00 per 1M output tokens ($16.00 blended at 3:1), list price on 21 Nov 2026. It streams about 56 tokens/s (OpenRouter). Released 17 Nov 2026.
Key facts (as of 21 Nov 2026)
- GPT-6.2 Astra Pro API pricing: $8.00 per 1M input tokens and $40.00 per 1M output tokens ($16.00 blended at 3:1) (list price, 21 Nov 2026).
- GPT-6.2 Astra Pro streams about 56 tokens/s (OpenRouter, 21 Nov 2026).
- GPT-6.2 Astra Pro was released on 17 Nov 2026 (OpenAI).
In detail. GPT-6.2 Astra Pro is an OpenAI model, released 17 Nov 2026. It is not yet ranked: the index needs at least five independent results across two categories. At $16.00 per million tokens blended it is among the most expensive ranked models. Output speed of 56 tokens per second puts it slower than most, with a first token in 8.3 s. Last measured 17 Nov 2026.
- Blended price
- $16.00/M
- $8.00 in · $40.00 out
- via OpenRouter
- Output speed
- 56 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 8.34 s
- Context
- 1.1M
- via OpenRouter
- Accepts
- Text · Images · PDFs
- via models.dev, OpenRouter
- Cost per task
- –
- Tokens per task
- –
- Released
- 17 Nov 2026
- Reasoning68
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | max | Source |
|---|---|---|
| SimpleBench | 79.2%#16 | SimpleBench |
API pricing: where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| OpenAI | 77 tok/s | 6.88 s | $8.00 | $40.00 | 1.1M | – |
| Azure | 71 tok/s | 72 s | $8.00 | $40.00 | 1.1M | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.400 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.015 | $0.013 | 13.7 s |
| Summarize a 30-page report | 12,000 / 600 | $0.120 | $0.052 | 19.1 s |
| Code edit | 6,000 / 1,500 | $0.108 | $0.074 | 35.1 s |
| Agentic coding session | 60,000 / 4,000 | $0.640 | $0.298 | 1.3 min |
| Structured extraction | 2,000 / 200 | $0.024 | $0.013 | 11.9 s |
More from OpenAI
Compare GPT-6.2 Astra Pro with…
See also
Questions people ask
- Why does GPT-6.2 Astra Pro have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories, and as of 21 Nov 2026 GPT-6.2 Astra Pro does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does GPT-6.2 Astra Pro cost per 1M tokens?
- As of 21 Nov 2026, GPT-6.2 Astra Pro costs $8.00 per 1M input tokens and $40.00 per 1M output tokens, $16.00 blended (three input tokens per output token).
- Is GPT-6.2 Astra Pro better than GPT-6.1 Terra?
- As of 21 Nov 2026, only one of these has enough independent results to rank; on price, GPT-6.1 Terra (max) is 8.0× cheaper. The head-to-head page has the benchmark-by-benchmark detail.
- When was GPT-6.2 Astra Pro released?
- OpenAI released GPT-6.2 Astra Pro on 17 Nov 2026.
Data as of 21 Nov 2026. Compare with another model.
Cite as: BenchLeader, “GPT-6.2 Astra Pro: benchmarks, pricing, speed and rank”, data as of 21 Nov 2026, https://www.benchleader.com/models/gpt-6-2-astra-pro.