OpenAI: o4 Mini

openai/o4-mini

o4 Mini is OpenAI's budget option at $1.1/$4.4 per million input/output tokens, with a 200K-token context. It sits mid-board on capability, at #120 of 260 on the TryAii Score — it holds up best on math (#3 on MATH). It's among the fastest models we track, at about 124 tokens/sec.

Prompt $/1M

$1.100

Completion $/1M

$4.400

Context

200,000 tok

Best provider

124 tok/s · OpenAI

Specs

Model id: openai/o4-mini
Display name: OpenAI: o4 Mini
Modality: text+image+file->text
Tokenizer: GPT
Instruct type: —
Context length: 200,000
Max completion: 100,000
Prompt $/1M: $1.100
Completion $/1M: $4.400
Free tier: no

Capabilities

Function callingyes
JSON modeno
System promptno
Visionyes
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
OpenAIfastest	124	2,520 ms	2,805 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.