OpenAI: GPT-6 Astra
GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↓ lowerOutput $50 → $25
- ↓ lowerInput $10 → $5
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| tokenstatopenai/gpt-6-astra | OpenAI | $10 | $50 | $0 | N/A |
| OpenRoutercheapestopenai/gpt-6-astra:batch | OpenRouter | $5 | $25 | $0.5 | 1.1M |
| LiteLLMopenai/gpt-6-astra:batch | N/A | $5 | $25 | $0.5 | N/A |
| models.devopenai/gpt-6-astra | Ofox | $8 | $40 | $0.8 | 1.1M |
| models.devopenai/gpt-6-astra | Cloudflare | $10 | $50 | $1 | 1.1M |
| models.devopenai/gpt-6-astra | CrossModel | $10 | $50 | $1 | 1.1M |
| models.devopenai/gpt-6-astra | Eden AI | $10 | $50 | $1 | 1.1M |
| models.devopenai/gpt-6-astra | Kilo Gateway | $10 | $50 | $1 | 1.1M |
| models.devaws-mantle/gpt-6-astra | LLM Gateway | $10 | $50 | $1 | 1.1M |
| models.devopenai/gpt-6-astra | Merge Gateway | $10 | $50 | $1 | 1.1M |
| models.devopenai/gpt-6-astra | NanoGPT | $10 | $50 | $1 | 1.1M |
| models.devgpt-6-astra | OpenAI | $10 | $50 | $1 | 1.1M |
| OpenRouteropenai/gpt-6-astra | OpenRouter | $10 | $50 | $1 | 1.1M |
| models.devopenai/gpt-6-astra | Vercel AI Gateway | $10 | $50 | $1 | 1.1M |
| models.devopenai/gpt-6-astra | ZenMux | $10 | $50 | $1 | 1.1M |
| models.devgpt-6-astra | 302.AI | $10 | $50 | $0 | 1.1M |
| models.devgpt-6-astra | AIHubMix | $10 | $50 | $1 | 1.1M |
| models.devgpt-6-astra | Azure | $10 | $50 | $1 | 1.1M |
| models.devgpt-6-astra | Azure | $10 | $50 | $1 | 1.1M |
| models.devgpt-6-astra | GitHub Copilot | $10 | $50 | $1 | 1.1M |
| models.devgpt-6-astra | DevPass (LLM Gateway) | $10 | $50 | $1 | 1.1M |
| models.devgpt-6-astra | Neon | $10 | $50 | $1 | 1.1M |
| models.devgpt-6-astra | OpenCode Zen | $10 | $50 | $1 | 1.1M |
| models.devgpt-6-astra | Opper | $10 | $50 | $1 | 1.1M |
| models.devgpt-6-astra | Requesty | $10 | $50 | $1 | 1.1M |
| models.devgpt-6-astra | Vivgrid | $10 | $50 | $1 | 1.1M |
| models.devglobal.openai.gpt-6-astra | Amazon Bedrock | $10 | $50 | $1 | 1.1M |
| models.devopenai-gpt-6-astra | DigitalOcean | $10 | $50 | $1 | 1.1M |
| models.devopenai-gpt-6-astra | Venice AI | $10 | $50 | $1 | 1.1M |
| LiteLLMgpt-6-astra | N/A | $10 | $50 | $1 | N/A |
| LiteLLMglobal.openai.gpt-6-astra | N/A | $10 | $50 | $1 | N/A |
| LiteLLMazure_ai/gpt-6-astra | N/A | $10 | $50 | $1 | N/A |
| models.devopenai.gpt-6-astra | Amazon Bedrock | $11 | $55 | $1.10 | 1.1M |
| models.devus.openai.gpt-6-astra | Amazon Bedrock | $11 | $55 | $1.10 | 1.1M |
| LiteLLMopenai.gpt-6-astra | N/A | $11 | $55 | $1.10 | N/A |
| LiteLLMus.openai.gpt-6-astra | N/A | $11 | $55 | $1.10 | N/A |
| LiteLLMazure/us/gpt-6-astra | N/A | $11 | $55 | $1.10 | N/A |
| LiteLLMbedrock_mantle/openai.gpt-6-astra | N/A | $11 | $55 | $1.10 | N/A |
| LiteLLMus/gpt-6-astra | N/A | $11 | $55 | $1.10 | N/A |
| LiteLLMazure/eu/gpt-6-astra | N/A | $12 | $60 | $1.20 | N/A |
| LiteLLMeu/gpt-6-astra | N/A | $12 | $60 | $1.20 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: pdf
- In: file
- Out: text
- Out: image
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence61i
- AA coding76.9i
- AA agentic51i
- DeepSWE v1.174.1i
- Agents' Last Exam59.3i
- AutomationBench (Public)41.4i
- ARC-AGI-399.9i
- FrontierMath Tier 4 (v2)97.6i
- BenchCAD95.9i
- Terminal-Bench Science 0.164.6i
- GPQA Diamond96i
- GeneBench Pro37.8i
- HealthBench Professional63.4i
- ExploitBench100i
- SRE-Bench99.2i
- ARC-AGI-295i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.