← All models
Coder Large vs GPT-5.4 Nano
List-price comparison · Coder Large details · GPT-5.4 Nano details
For a typical workload (100,000 requests / mo), GPT-5.4 Nano costs 20% less — $74.00/mo vs $92.00/mo.
| Coder Large | GPT-5.4 Nano | |
|---|---|---|
| Input / 1M tokens | $0.500 | $0.200 |
| Output / 1M tokens | $0.800 | $1.25 |
| Typical request (1,200 in + 400 out) | $0.0009 | $0.0007 |
| Context window | 32,768 tokens | 400k tokens |
| Max output | — | 128k tokens |
| Tier | Flash | Flash |
| Provider | Arcee AI | OpenAI |
Projected monthly cost
1,000 requests / month$0.92 vs $0.7410,000 requests / month$9.20 vs $7.40100,000 requests / month$92.00 vs $74.00
Rows open both models in the calculator — adjust volume and token counts there.
Coder Large
Auto-synced from OpenRouter — no editorial write-up yet.
GPT-5.4 Nano
Cheapest OpenAI option for high-throughput classification, tagging, and routing — ideal as a first-pass filter before a stronger model.
Limited reasoning depth means it should be treated as a triage layer, not a final answer source, for anything business-critical.
More comparisons
Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.