GPT-5.1-Codex-Mini vs GPT-5 Mini
Prices checked
GPT-5.1-Codex-Mini takes 1 of 5 rounds against GPT-5 Mini. It is also the cheaper of the two to run, at $0.61 per million tokens against $0.63.
OpenAIWins 1 roundGPT-5.1-Codex-Mini
400k context · tool calling · reads images
$0.61/M tokensCheapest price, at Poe · $0.24 per 1,000 pages
OpenAIGPT-5 Mini
400k context · tool calling · reads images
$0.63/M tokensCheapest price, at Poe · $0.25 per 1,000 pages
Maker's price in (lower wins)
$0.25/M
$0.25/M
Maker's price out (lower wins)
$2/M
$2/M
Cheapest price (lower wins)
$0.61/M at Poe
$0.63/M at Poe
Maker's price, blended (lower wins)
$0.69/M
$0.69/M
Cost per 1,000 pages (lower wins)
$0.24
$0.25
Context
400k tokens
400k tokens
Open weights
not published
no
Tool calling
yes
yes
Structured output
yes
yes
Reads images
yes
yes
Reasoning
yes
yes
Released
13 Nov 2025
7 Aug 2025
Providers selling it
18
39
Price we measure against
OpenRouter
the maker's own
Trains on your prompts (no is better)
not published
not published
Providers selling both · 16
Poe$0.61 / $0.63
Jiekou$0.65 / $0.65
Azure AI Foundry$0.69 / $0.69
Azure Cognitive Services$0.69 / $0.69
Helicone$0.69 / $0.69
Impossibl$0.69 / $0.69
Kilo Gateway$0.69 / $0.69
LLM Gateway$0.69 / $0.69
GPT-5.1-Codex-Mini, then GPT-5 Mini, per million tokens; the 8 cheapest of 16.
Go further
Add a third or fourth model, or change the weighting, in the tool.
What moved this week
AI/ML API · 23% cheaper ·
$0.25 / $2 $0.33 / $2.60
Frequently asked
- Which is cheaper, GPT-5.1-Codex-Mini or GPT-5 Mini?
- GPT-5.1-Codex-Mini, at $0.61 per million tokens against $0.63 for GPT-5 Mini, blended 3 in : 1 out, read on 31 Oct 2026.
- Where is each one cheapest?
- GPT-5.1-Codex-Mini: $0.61 at Poe. GPT-5 Mini: $0.63 at Poe.
- Can I buy both from one provider?
- Yes. 16 providers sell both: Poe, Jiekou, Azure AI Foundry, Azure Cognitive Services, Helicone, Impossibl, and more. The cheapest of them for the two together is Poe.
- Which holds more context?
- Both hold 400k tokens in one call.
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