Gemini 2.5 Computer Use Preview 10-2025 vs GPT-5.1-Codex
Prices checked
GPT-5.1-Codex takes 2 of 5 rounds against Gemini 2.5 Computer Use Preview 10-2025. It is also the cheaper of the two to run, at $3.08 per million tokens against $3.44.
GoogleGemini 2.5 Computer Use Preview 10-2025
128k context · tool calling · reads images
$3.44/M tokensGoogle's own price · $1.35 per 1,000 pages
OpenAIWins 2 roundsGPT-5.1-Codex
400k context · tool calling · reads images
$3.08/M tokensCheapest price, at Poe · $1.20 per 1,000 pages
Maker's price in (lower wins)
$1.25/M
$1.25/M
Maker's price out (lower wins)
$10/M
$10/M
Cheapest price (lower wins)
none below the maker
$3.08/M at Poe
Maker's price, blended (lower wins)
$3.44/M
$3.44/M
Cost per 1,000 pages (lower wins)
$1.35
$1.20
Context
128k tokens
400k tokens
Open weights
no
not published
Tool calling
yes
yes
Structured output
not published
yes
Reads images
yes
yes
Reasoning
yes
yes
Released
7 Oct 2025
13 Nov 2025
Providers selling it
3
19
Price we measure against
the maker's own
OpenRouter
Trains on your prompts (no is better)
no provider to check
not published
Providers selling both · 0
No provider we read sells both, so running the two means two accounts.
Go further
Add a third or fourth model, or change the weighting, in the tool.
Frequently asked
- Which is cheaper, Gemini 2.5 Computer Use Preview 10-2025 or GPT-5.1-Codex?
- GPT-5.1-Codex, at $3.08 per million tokens against $3.44 for Gemini 2.5 Computer Use Preview 10-2025, blended 3 in : 1 out, read on 31 Oct 2026.
- Where is each one cheapest?
- Gemini 2.5 Computer Use Preview 10-2025: nobody sells it below the maker's own price with a stated reason, so $3.44 is the number to beat. GPT-5.1-Codex: $3.08 at Poe.
- Can I buy both from one provider?
- No provider we read sells both, so running the two means two accounts and two bills.
- Which holds more context?
- GPT-5.1-Codex, at 400k tokens against 128k.
Prices exclude tax, read 31 Oct 2026 from each provider's own catalog. They are per M tokens, blended 3 in : 1 out, and a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.
Related comparisons