Routin
Loading...
Loading...
GPT-6 Astra is our most capable model, built for the hardest end-to-end work. Use it for complex reasoning, coding, computer use, research, and document creation. reasoning.effort supports low, medium, high, xhigh, and max.
同系列或更低输入价的公开模型。 / Same provider or cheaper catalog alternatives.
| Model | Provider | Type | Input | Output |
|---|---|---|---|---|
| text-embedding-3-small | OpenAI | chat | 0.0200 Token / 1M tokens | — |
| gpt-5-nano | OpenAI | chat | 0.0500 Token / 1M tokens | 0.4000 Token / 1M tokens |
| gpt-5-nano-2025-08-07 | OpenAI | chat | 0.0500 Token / 1M tokens | 0.4000 Token / 1M tokens |
| gpt-4.1-nano | OpenAI | chat | 0.1000 Token / 1M tokens | 0.4000 Token / 1M tokens |
| gpt-4.1-nano-2025-04-14 | OpenAI | chat | 0.1000 Token / 1M tokens |
A quick read of the model identity, commercial setup, and access footprint.
Published rates, tier transitions, and modality-specific surcharges in the current catalog entry.
| Context Length | Prompt | Output | 5m cache write | Cache hit |
|---|---|---|---|---|
| 0 - 272,000 tokens | $0.5714/1M tokens | $2.8571/1M tokens | $0.7143/1M tokens | $0.0571/1M tokens |
| >= 272,000 tokens | $1.1429/1M tokens | $4.2857/1M tokens | $1.4286/1M tokens | $0.1143/1M tokens |
Hourly usage, latency, reliability, and throughput for this model.
Top 10 AI coding agents using this model during the last 15 days.
Top 10 official SDKs and language HTTP clients using this model during the last 15 days.
| 0.4000 Token / 1M tokens |
| sora-2 | OpenAI | video | 0.1000 Token / 1M tokens | — |
| # | SDK / Language | Total Tokens | Requests | Success rate | Last active |
|---|---|---|---|---|---|
| #1 |  Node.js Language SDK / HTTP client | 0 | 3 | 0.0% | 2026-09-04 |
| #2 |  Go Language SDK / HTTP client | 0 | 5 | 0.0% | 2026-09-04 |
| #3 |  JavaScript Language SDK / HTTP client |
| 0 |
| 4 |
| 0.0% |
| 2026-09-04 |
| #4 |  cURL / HTTP Client Language SDK / HTTP client | 0 | 1 | 0.0% | 2026-09-04 |