OpenAI
GPT-6.1 Sol
$4.00 / 1M tokens
cheapest at OpenAI · $2.00 in · $10.00 out
Wins 1 of 4
Head to head · prices updated Oct 31, 2026
GPT-6.1 Sol and Gemini 4 Argon cost about the same at their cheapest providers.
OpenAI
$4.00 / 1M tokens
cheapest at OpenAI · $2.00 in · $10.00 out
Wins 1 of 4
Google Gemini and Gemma
$4.00 / 1M tokens
cheapest at Google Gemini API · $2.00 in · $10.00 out
Wins 2 of 4
Verdict
GPT-6.1 Sol and Gemini 4 Argon cost about the same at their cheapest providers.
Gemini 4 Argon scores higher on GPQA Diamond: 96.4% (high reasoning) vs 95.4% (max reasoning).
Gemini 4 Argon accepts longer prompts (1049K vs 1000K tokens).
Your monthly bill
Both cost the same for this workload.
| GPT-6.1 Sol | Gemini 4 Argon | |
|---|---|---|
| Cheapest blended price / 1M | $4.00 | $4.00 |
| Input / output per 1M | $2.00 / $10.00 | $2.00 / $10.00 |
| Accuracy (GPQA Diamond) | 95.4% (max reasoning) | 96.4% (high reasoning) |
| Max context | 1M | 1M |
| Providers we track | 3 | 2 |
Standard list prices at each model's cheapest provider we track; blended = 3 input : 1 output tokens. GPQA Diamond from Epoch AI (CC BY 4.0), best measured reasoning setting, named next to each score. Methodology.
GPT-6.1 Sol and Gemini 4 Argon cost about the same at their cheapest providers.
On GPQA Diamond (graduate-level science questions, measured by Epoch AI) GPT-6.1 Sol scores 95.4% (max reasoning) and Gemini 4 Argon 96.4% (high reasoning). One benchmark is not the whole picture; test both on your own prompts.
From $2.00 input and $10.00 output per 1M tokens at OpenAI, the cheapest of 3 providers we track.
From $2.00 input and $10.00 output per 1M tokens at Google Gemini API, the cheapest of 2 providers we track.
Swap a model