OpenAI: GPT-4o-mini

openai/gpt-4o-mini

GPT-4o-mini is OpenAI's budget option at $0.15/$0.6 per million input/output tokens, with a 128K-token context. It sits toward the back of the board on capability, at #234 of 260 on the TryAii Score — its best showing is #10 on GSM8K. It's reasonably quick at roughly 84-92 tokens/sec.

Prompt $/1M

$0.150

Completion $/1M

$0.600

Context

128,000 tok

Best provider

96 tok/s · Azure

Specs

Model id: openai/gpt-4o-mini
Display name: OpenAI: GPT-4o-mini
Modality: text+image+file->text
Tokenizer: GPT
Instruct type: —
Context length: 128,000
Max completion: 16,384
Prompt $/1M: $0.150
Completion $/1M: $0.600
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedyes

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Azurefastest	96	622 ms	645 ms
OpenAI	80	491 ms	534 ms

Prompt caching by provider

Provider	Min tokens to cache	Notes
OpenAI	1,024 tokens	Caching-eligible (gpt-4o-and-newer rule) but the cached-read discount is per-model (50%-98.75% platform range) and was not published for these models in the 2026-07 research — verify live pricing.