A side-by-side comparison of Gemini 4 Argon and GPT-6.1 Sol: input/output pricing, capabilities and available endpoints, served live from 370.AI. Both are reachable with the same API key.
| Item | Gemini 4 Argon | GPT-6.1 Sol |
|---|---|---|
| Input (per 1M tokens) | $1.5 | $1.3 |
| Output (per 1M tokens) | $7.5 | $6.5 |
| Cache read implicit (per 1M tokens) | $0.075 | — |
| Cache read explicit (per 1M tokens) | — | $0.065 |
| Cache write 5m (per 1M tokens) | — | $1.625 |
| Item | Gemini 4 Argon | GPT-6.1 Sol |
|---|---|---|
| Context window | 1,048,576 | 922,000 |
| Max output | 65,536 | 128,000 |
| Item | Gemini 4 Argon | GPT-6.1 Sol |
|---|---|---|
| audio_input | Yes | — |
| function_calling | Yes | Yes |
| prompt_caching | Yes | Yes |
| vision | Yes | Yes |
On input, GPT-6.1 Sol is cheaper ($1.5 vs $1.3 per 1M tokens). On output, GPT-6.1 Sol is cheaper ($7.5 vs $6.5 per 1M tokens). All prices are per million tokens in USD.
Gemini 4 Argon does — Gemini 4 Argon accepts 1,048,576 input tokens and GPT-6.1 Sol accepts 922,000.
both support function_calling, prompt_caching, vision; only Gemini 4 Argon supports audio_input.
Yes. Both are available on 370.AI through one API key and the same OpenAI-compatible endpoint — switching means changing the model field from "gemini-4-argon" to "gpt-6.1-sol", nothing else.
Both are available on 370.AI under one API key — switching between them means changing the model field and nothing else, so you can use each where it fits rather than picking one.