The Orchestrator › Models › OpenAI
OpenAI: GPT-4.1 Nano
For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
Specifications
| Provider | OpenAI |
| Model ID | openai/gpt-4.1-nano |
| Context window | 1.0M tokens (1,047,576) |
| Modalities | text + image + file → text |
| Tokenizer | GPT |
| Router sources | OpenRouter, Vercel AI Gateway, Cloudflare |
| Released | 2025-04-14 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | openai/gpt-4.1-nano | $0.1 | $0.4 | 1.0M |
| batch | OpenRouter | openai/gpt-4.1-nano:batch | $0.05 | $0.2 | 1.0M |
| standard | Vercel AI Gateway | openai/gpt-4.1-nano | $0.1 | $0.4 | 1.0M |
| standard | Cloudflare | openai/gpt-4.1-nano | $0.1 | $0.4 | — |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.1 | $0.4 | — |
| 2026-11-14 | $0.1 | $0.4 | 1.0M |
| 2026-11-14 | $0.1 | $0.4 | 1.0M |
Capabilities
Vision (image input)File inputAgentic tool useStructured outputs1M+ context windowZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
max_completion_tokens, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_p