OpenAI: o1

openai/o1

o1 is OpenAI's budget option at $15/$60 per million input/output tokens, with a 200K-token context. It sits mid-board on capability, at #141 of 263 on the TryAii Score — it holds up best on reasoning (#4 on DROP). It's among the fastest models we track, at roughly 106-142 tokens/sec.

Prompt $/1M

$15.000

Completion $/1M

$60.000

Context

200,000 tok

Best provider

160 tok/s · openai

Specs

Model id: openai/o1
Display name: OpenAI: o1
Modality: text+image+file->text
Tokenizer: GPT
Instruct type: —
Context length: 200,000
Max completion: 100,000
Prompt $/1M: $15.000
Completion $/1M: $60.000
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
openaifastest	160	550 ms	550 ms
OpenAIfastest	89	2,712 ms	4,491 ms
azure	—	1,272 ms	1,272 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.