OpenAI
GPT-6 Astra
GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.
Model facts
- Context window
- 1.05M tokens
- Maximum output
- 128K tokens
- Cheapest paid input
- $5 per 1M tokens
- Cheapest paid output
- $25 per 1M tokens
- Open weights
- no
- Providers
- 12
Capabilities and modalities
reasoning, tool calling, structured output, attachments, text, image, pdf.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| max | 54.7 | 76.9 | not measured | not measured |
| xhigh | 54.3 | 75.9 | not measured | not measured |
| high | 53.4 | 77.1 | not measured | not measured |
| medium | 52.2 | 76.7 | not measured | not measured |
| low | 49.3 | 75.7 | not measured | not measured |
| Non-reasoning | 47.8 | 76.2 | not measured | not measured |
Observed price history
- 2026-09-05: $5 input / $25 output per 1M tokens
API providers
- OpenRouter (batch) — model id openai/gpt-6-astra:batch; $5 input / $25 output per 1M tokens; provider documentation
- DevPass (LLM Gateway) — model id gpt-6-astra; $10 input / $50 output per 1M tokens; provider documentation
- GitHub Copilot — model id gpt-6-astra; $10 input / $50 output per 1M tokens; provider documentation
- Kilo Gateway — model id openai/gpt-6-astra; $10 input / $50 output per 1M tokens; provider documentation
- LLM Gateway (OpenAI) — model id openai/gpt-6-astra; $10 input / $50 output per 1M tokens; provider documentation
- Merge Gateway — model id openai/gpt-6-astra; $10 input / $50 output per 1M tokens; provider documentation
- NanoGPT — model id openai/gpt-6-astra; $10 input / $50 output per 1M tokens; provider documentation
- OpenAI — model id gpt-6-astra; $10 input / $50 output per 1M tokens; provider documentation
- OpenRouter — model id openai/gpt-6-astra; $10 input / $50 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id openai/gpt-6-astra; $10 input / $50 output per 1M tokens; provider documentation
- Venice AI — model id openai-gpt-6-astra; $12.5 input / $62.5 output per 1M tokens; provider documentation
- Vercel AI Gateway (Fast) — model id openai/gpt-6-astra-fast; $20 input / $100 output per 1M tokens; provider documentation