# GPT-6 Astra (Fast)

> GPT-6 Astra (Fast) is a proprietary language model from OpenAI, released on 4 Sept 2026. It accepts text, images and PDFs and generates text, with a 1.1M-token context window and up to 128K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $20 per million input tokens and $100 per million output tokens (Vercel AI Gateway), across 1 provider we track.

Source page: https://www.aimodel.directory/models/gpt-6-astra-fast
Last verified: 4 Oct 2026

## Specifications

- **Developer:** OpenAI
- **Release date:** 4 Sept 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-6-astra-fast.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-6-astra-fast.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-6-astra-fast.toml)
- **Context window:** 1.1M (1,050,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-6-astra-fast.toml)
- **Max output:** 128K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-6-astra-fast.toml)
- **Input:** Text, images and PDFs (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-6-astra-fast.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-6-astra-fast.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-6-astra-fast.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-6-astra-fast.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-6-astra-fast.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Vercel AI Gateway | $20 | $100 | $2 | 1.1M |

## FAQ

### What is the context window of GPT-6 Astra (Fast)?

GPT-6 Astra (Fast) has a context window of 1,050,000 tokens (1.1M) and can generate up to 128,000 tokens in a single response, according to models.dev.

### How much does the GPT-6 Astra (Fast) API cost?

GPT-6 Astra (Fast) is listed from $20 per million input tokens and $100 per million output tokens (Vercel AI Gateway). Prices last verified 4 Oct 2026.

### Is GPT-6 Astra (Fast) open source?

No. GPT-6 Astra (Fast) is a proprietary model; OpenAI has not released its weights. It is available through APIs including Vercel AI Gateway.

### When was GPT-6 Astra (Fast) released?

OpenAI released GPT-6 Astra (Fast) on 4 Sept 2026, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "GPT-6 Astra (Fast)", https://www.aimodel.directory/models/gpt-6-astra-fast