GPT-4 vs Mercury 2 compared — price per token, context window, multimodality, openness and which to choose. Full 2026 breakdown.
GPT-4 — full profile › · Mercury 2 — full profile ›
Prices & specs refreshed from live data · olud.ai
Open-model prices = cheapest provider via OpenRouter; official maker rates may be higher.
| Spec | GPT-4 | Mercury 2 | Winner |
|---|---|---|---|
| Maker | OpenAI | Inception | – |
| Type | Proprietary | Proprietary | – |
| Context window | 8K tokens | 128K tokens | INMercury 2 |
| Input price | $30/M | $0.25/M | INMercury 2 |
| Output price | $60/M | $0.75/M | INMercury 2 |
| Vision / multimodal | No | No | – |
| Tool / function calling | Yes | Yes | = Tie |
| Self-hostable | No (API only) | No (API only) | – |
| License | Proprietary | Proprietary | – |
Mercury 2 is ~80× cheaper than GPT-4 on output tokens ($0.75 vs $60 per M tokens).
| Capability | GPT-4 | Mercury 2 |
|---|---|---|
| Open weights (downloadable) | ✗ | ✗ |
| Self-hostable | ✗ | ✗ |
| Runs fully offline | ✗ | ✗ |
| Vision / multimodal | ✗ | ✗ |
| Tool / function calling | ✓ | ✓ |
| 1M+ context window | ✗ | ✗ |
Independent benchmark scores measured by Artificial Analysis. Higher is better (except latency).
Benchmark data by Artificial Analysis.
| Criterion | GPT-4 | Mercury 2 |
|---|---|---|
| Cost-efficiency | 2.0 | 5.0 |
| Context window | 2.0 | 3.5 |
| Openness | 1.5 | 1.5 |
| Self-hosting | 1.0 | 1.0 |
| Multimodality | 3.5 | 3.5 |
Scores come from live data — output price (cost), context length, open vs closed weights (openness & self-hosting) and vision/tool support (multimodality). Raw task quality isn't scored here; it depends on your benchmark — see the verdict.
OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
Mercury 2 is cheaper on output ($0.75/M vs $60/M).
Mercury 2 offers the larger context window (128K tokens).
Choose Mercury 2 for the lower output price ($0.75/M vs $60/M). It also gives you the larger 128K context window.
Browse the full open-source model leaderboard, thousands of tools and live benchmarks — all in one place.
Open the leaderboard →