GPT-6.2 Astra via the Tokenator API
What the model is for
GPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects. It is suited for real-world engineering, professional work and scientific research, with stronger visual reasoning for websites, slideshows and 3D designs. OpenAI reports new highs on its evals at less than a third of the cost per task of GPT-6 Astra.
Specification
| Full name | GPT-6.2 Astra |
| API ID | gpt-6.2-astra |
| Model vendor | OpenAI |
| Type | Text model (chat / completions) |
| Context window | 1.05M tokens |
| Max output | 128K tokens |
| Image input | yes |
| Tokenator usage multiplier | 3.5× |
| Output token multiplier | 6× |
| Badge | NEW |
| Input modalities | text, image, file |
| Aliases | cursor-gpt-6.2-astra |
| Supported API formats | /v1/chat/completions /v1/responses /v1/messages |
| Upstream providers | 1 |
| Current status | available |
| Data updated | 2026-11-22 |
Benchmarks
| Intelligence index | 60.1 |
| Vals Finance Index (Vals AI) | 57.3% |
| Vals Index (Vals AI) | 67.7% |
| Vals Legal Index (Vals AI) | 69.7% |
| Vals RSI Index (Vals AI) | 29% |
| Vals Science Index (Vals AI) | 68.4% |
| Terminal-Bench 4.0 (Vals AI) | 63.1% |
| Vibe Code Bench 1-100 v1.1 (Vals AI) | 55.2% |
| Vibe Code Bench v1.1 (Vals AI) | 89.9% |
| Autoform-Hard (Vals AI) | 87.5% |
| BioMysteryBench (Vals AI) | 80.7% |
| MysteryMechanism (Vals AI) | 53.2% |
| Robo-bench (Vals AI) | 32.7% |
| Terminal-Bench-Science (Vals AI) | 71.4% |
| EMB v1.1 (Vals AI) | 76% |
| Finance Agent v2.1 (Vals AI) | 60.7% |
| Tax Agent Bench (Vals AI) | 21.8% |
| HLAB-Vals-1.1 (Vals AI) | 16.3% |
| Legal Research Bench (Vals AI) | 42.8% |
Artificial Analysis and Vals AI data loaded into the catalog for this model.
Upstream providers
| Provider | Multiplier | Output token multiplier |
|---|---|---|
| AiPartners Ltd | 3.5× | 6× |
A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.
Example request
curl https://api.tokenator.top/v1/chat/completions \ -H "Authorization: Bearer sk-your-tokenator-key" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-6.2-astra", "messages": [{"role": "user", "content": "Hello"}] }'
Compatible tools
The model can be used in any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code, Cherry Studio, DeepSeek Harness, Hermes, Pi, OpenClaw.
See also
FAQ about GPT-6.2 Astra
What is the API ID of GPT-6.2 Astra?
gpt-6.2-astra — put this into the model field of your request.
What context window does GPT-6.2 Astra have?
1.05M tokens; max output is 128K tokens.
How many tokens will a request cost?
(input × 3.5×) + (output × 6×). See the documentation for details.
Which tools support this model?
Any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code. Setup guides are in the integrations section.