What are the token costs and operational benchmarks for OpenAI o1?

OpenAI o1 is priced at $15.00 per million input tokens and $60.00 per million output tokens. It features a 204.8k token context window, an average response latency of 850ms TTFT, and achieves 48.9% on SWE-bench Verified and 83.3% on MMLU-Pro.
Verified daily via automated API latency tests and official documentation.
Input / 1M $15.00
Output / 1M $60.00
Context Limit 204.8k
TTFT Latency 850ms
SWE-bench 48.9%
Throughput 65 t/s

Architectural Overview

Frontier foundation model developed by OpenAI featuring Large-Scale Reasoning Model architecture.

Optimal Production Use Cases

Complex PhD-level multi-step science research, formal algorithm synthesis, and high-stakes reasoning pipelines.

Interactive Monthly Token Economics & ROI Forecaster

Model your expected production workload across prompt (input) and completion (output) tokens.

Live Calculation Engine
10.0M Tokens
100K 50M 250M 500M+
2.5M Tokens
100K 10M 50M 100M+

Estimated Monthly Spend

OpenAI o1 $5.45

$15/1M in · $60/1M out

GPT-5.6 Luna $67.50

$0.18/1M in · $0.72/1M out

Projected Monthly Cost Reduction
$62.05 / mo
(91.9% lower cost)

Head-to-Head Comparisons Involving OpenAI o1

Versus Comparison

OpenAI o1 vs Claude 3.5 Haiku

Claude 3.5 Haiku is 94.7% cheaper for input tokens ($0.80 vs. $15.00 per 1M tokens) and $4.00 vs. $60.00 for output tokens (18.8x cost difference). In terms of operational performance, Claude 3.5 Haiku delivers faster response latency with 140ms TTFT (710ms faster than OpenAI o1). OpenAI o1 leads coding benchmarks at 48.9% SWE-bench vs. 40.6% for Claude 3.5 Haiku.

Versus Comparison

OpenAI o1 vs Claude 3.5 Sonnet

Claude 3.5 Sonnet is 80.0% cheaper for input tokens ($3.00 vs. $15.00 per 1M tokens) and $15.00 vs. $60.00 for output tokens (5.0x cost difference). In terms of operational performance, Claude 3.5 Sonnet delivers faster response latency with 320ms TTFT (530ms faster than OpenAI o1). Claude 3.5 Sonnet leads coding benchmarks at 63.7% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs Claude 3.7 Sonnet

Claude 3.7 Sonnet is 80.0% cheaper for input tokens ($3.00 vs. $15.00 per 1M tokens) and $15.00 vs. $60.00 for output tokens (5.0x cost difference). In terms of operational performance, Claude 3.7 Sonnet delivers faster response latency with 650ms TTFT (200ms faster than OpenAI o1). Claude 3.7 Sonnet leads coding benchmarks at 70.3% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs Claude Opus 5

Claude Opus 5 is 66.7% cheaper for input tokens ($5.00 vs. $15.00 per 1M tokens) and $25.00 vs. $60.00 for output tokens (3.0x cost difference). In terms of operational performance, Claude Opus 5 delivers faster response latency with 340ms TTFT (510ms faster than OpenAI o1). Claude Opus 5 leads coding benchmarks at 82.4% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs Codestral 25.01

Codestral 25.01 is 98.0% cheaper for input tokens ($0.30 vs. $15.00 per 1M tokens) and $0.90 vs. $60.00 for output tokens (50.0x cost difference). In terms of operational performance, Codestral 25.01 delivers faster response latency with 150ms TTFT (700ms faster than OpenAI o1). OpenAI o1 leads coding benchmarks at 48.9% SWE-bench vs. 44.2% for Codestral 25.01.

Versus Comparison

OpenAI o1 vs Composer 2.5

Composer 2.5 is 88.0% cheaper for input tokens ($1.80 vs. $15.00 per 1M tokens) and $7.20 vs. $60.00 for output tokens (8.3x cost difference). In terms of operational performance, Composer 2.5 delivers faster response latency with 180ms TTFT (670ms faster than OpenAI o1). Composer 2.5 leads coding benchmarks at 74.6% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs DeepSeek-R1

DeepSeek-R1 is 96.3% cheaper for input tokens ($0.55 vs. $15.00 per 1M tokens) and $2.19 vs. $60.00 for output tokens (27.3x cost difference). In terms of operational performance, OpenAI o1 delivers faster response latency with 850ms TTFT (950ms faster than DeepSeek-R1). DeepSeek-R1 leads coding benchmarks at 49.2% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs DeepSeek-V3

DeepSeek-V3 is 99.1% cheaper for input tokens ($0.14 vs. $15.00 per 1M tokens) and $0.28 vs. $60.00 for output tokens (107.1x cost difference). In terms of operational performance, DeepSeek-V3 delivers faster response latency with 340ms TTFT (510ms faster than OpenAI o1). OpenAI o1 leads coding benchmarks at 48.9% SWE-bench vs. 42.0% for DeepSeek-V3.

Versus Comparison

OpenAI o1 vs DeepSeek-V4 Flash

DeepSeek-V4 Flash is 99.1% cheaper for input tokens ($0.14 vs. $15.00 per 1M tokens) and $0.56 vs. $60.00 for output tokens (107.1x cost difference). In terms of operational performance, DeepSeek-V4 Flash delivers faster response latency with 150ms TTFT (700ms faster than OpenAI o1). DeepSeek-V4 Flash leads coding benchmarks at 62.4% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs Fable 5

Fable 5 is 86.7% cheaper for input tokens ($2.00 vs. $15.00 per 1M tokens) and $8.00 vs. $60.00 for output tokens (7.5x cost difference). In terms of operational performance, Fable 5 delivers faster response latency with 240ms TTFT (610ms faster than OpenAI o1). Fable 5 leads coding benchmarks at 58.0% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs Gemini 2.0 Flash

Gemini 2.0 Flash is 99.3% cheaper for input tokens ($0.10 vs. $15.00 per 1M tokens) and $0.40 vs. $60.00 for output tokens (150.0x cost difference). In terms of operational performance, Gemini 2.0 Flash delivers faster response latency with 380ms TTFT (470ms faster than OpenAI o1). OpenAI o1 leads coding benchmarks at 48.9% SWE-bench vs. 48.0% for Gemini 2.0 Flash.

Versus Comparison

OpenAI o1 vs Gemini 3.7 Flash

Gemini 3.7 Flash is 99.5% cheaper for input tokens ($0.08 vs. $15.00 per 1M tokens) and $0.32 vs. $60.00 for output tokens (187.5x cost difference). In terms of operational performance, Gemini 3.7 Flash delivers faster response latency with 75ms TTFT (775ms faster than OpenAI o1). Gemini 3.7 Flash leads coding benchmarks at 68.2% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs GLM 5.3 Flash

GLM 5.3 Flash is 99.0% cheaper for input tokens ($0.15 vs. $15.00 per 1M tokens) and $0.50 vs. $60.00 for output tokens (100.0x cost difference). In terms of operational performance, GLM 5.3 Flash delivers faster response latency with 130ms TTFT (720ms faster than OpenAI o1). GLM 5.3 Flash leads coding benchmarks at 54.2% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs OpenAI GPT-4o

OpenAI GPT-4o is 83.3% cheaper for input tokens ($2.50 vs. $15.00 per 1M tokens) and $10.00 vs. $60.00 for output tokens (6.0x cost difference). In terms of operational performance, OpenAI GPT-4o delivers faster response latency with 280ms TTFT (570ms faster than OpenAI o1). OpenAI o1 leads coding benchmarks at 48.9% SWE-bench vs. 38.8% for OpenAI GPT-4o.

Versus Comparison

OpenAI o1 vs GPT-5.6 Luna

GPT-5.6 Luna is 98.8% cheaper for input tokens ($0.18 vs. $15.00 per 1M tokens) and $0.72 vs. $60.00 for output tokens (83.3x cost difference). In terms of operational performance, GPT-5.6 Luna delivers faster response latency with 90ms TTFT (760ms faster than OpenAI o1). OpenAI o1 leads coding benchmarks at 48.9% SWE-bench vs. 48.5% for GPT-5.6 Luna.

Versus Comparison

OpenAI o1 vs GPT-5.6 Sol

GPT-5.6 Sol is 46.7% cheaper for input tokens ($8.00 vs. $15.00 per 1M tokens) and $32.00 vs. $60.00 for output tokens (1.9x cost difference). In terms of operational performance, GPT-5.6 Sol delivers faster response latency with 420ms TTFT (430ms faster than OpenAI o1). GPT-5.6 Sol leads coding benchmarks at 79.5% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs GPT-5.6 Terra

GPT-5.6 Terra is 90.0% cheaper for input tokens ($1.50 vs. $15.00 per 1M tokens) and $6.00 vs. $60.00 for output tokens (10.0x cost difference). In terms of operational performance, GPT-5.6 Terra delivers faster response latency with 210ms TTFT (640ms faster than OpenAI o1). GPT-5.6 Terra leads coding benchmarks at 65.4% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs Grok 3

Grok 3 is 80.0% cheaper for input tokens ($3.00 vs. $15.00 per 1M tokens) and $15.00 vs. $60.00 for output tokens (5.0x cost difference). In terms of operational performance, OpenAI o1 delivers faster response latency with 850ms TTFT (0ms faster than Grok 3). Grok 3 leads coding benchmarks at 58.5% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs xAI Grok 4.6

xAI Grok 4.6 is 86.7% cheaper for input tokens ($2.00 vs. $15.00 per 1M tokens) and $6.00 vs. $60.00 for output tokens (7.5x cost difference). In terms of operational performance, xAI Grok 4.6 delivers faster response latency with 280ms TTFT (570ms faster than OpenAI o1). xAI Grok 4.6 leads coding benchmarks at 76.8% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs Llama 3.3 70B Instruct

Llama 3.3 70B Instruct is 98.8% cheaper for input tokens ($0.18 vs. $15.00 per 1M tokens) and $0.40 vs. $60.00 for output tokens (83.3x cost difference). In terms of operational performance, Llama 3.3 70B Instruct delivers faster response latency with 420ms TTFT (430ms faster than OpenAI o1). OpenAI o1 leads coding benchmarks at 48.9% SWE-bench vs. 38.8% for Llama 3.3 70B Instruct.

Versus Comparison

OpenAI o1 vs Mistral Large 2

Mistral Large 2 is 86.7% cheaper for input tokens ($2.00 vs. $15.00 per 1M tokens) and $6.00 vs. $60.00 for output tokens (7.5x cost difference). In terms of operational performance, Mistral Large 2 delivers faster response latency with 550ms TTFT (300ms faster than OpenAI o1). OpenAI o1 leads coding benchmarks at 48.9% SWE-bench vs. 39.0% for Mistral Large 2.

Versus Comparison

OpenAI o1 vs o3-mini

o3-mini is 92.7% cheaper for input tokens ($1.10 vs. $15.00 per 1M tokens) and $4.40 vs. $60.00 for output tokens (13.6x cost difference). In terms of operational performance, OpenAI o1 delivers faster response latency with 850ms TTFT (350ms faster than o3-mini). o3-mini leads coding benchmarks at 49.3% SWE-bench vs. 48.9% for OpenAI o1.

Versus Comparison

OpenAI o1 vs Microsoft Phi-4 (14B)

Microsoft Phi-4 (14B) is 99.2% cheaper for input tokens ($0.12 vs. $15.00 per 1M tokens) and $0.36 vs. $60.00 for output tokens (125.0x cost difference). In terms of operational performance, Microsoft Phi-4 (14B) delivers faster response latency with 110ms TTFT (740ms faster than OpenAI o1). OpenAI o1 leads coding benchmarks at 48.9% SWE-bench vs. 42.1% for Microsoft Phi-4 (14B).

Versus Comparison

OpenAI o1 vs Qwen 2.5 72B Instruct

Qwen 2.5 72B Instruct is 97.7% cheaper for input tokens ($0.35 vs. $15.00 per 1M tokens) and $0.40 vs. $60.00 for output tokens (42.9x cost difference). In terms of operational performance, Qwen 2.5 72B Instruct delivers faster response latency with 420ms TTFT (430ms faster than OpenAI o1). OpenAI o1 leads coding benchmarks at 48.9% SWE-bench vs. 44.0% for Qwen 2.5 72B Instruct.

Versus Comparison

OpenAI o1 vs Qwen 2.5 Max

Qwen 2.5 Max is 98.1% cheaper for input tokens ($0.28 vs. $15.00 per 1M tokens) and $0.84 vs. $60.00 for output tokens (53.6x cost difference). In terms of operational performance, Qwen 2.5 Max delivers faster response latency with 480ms TTFT (370ms faster than OpenAI o1). OpenAI o1 leads coding benchmarks at 48.9% SWE-bench vs. 44.2% for Qwen 2.5 Max.

Versus Comparison

OpenAI o1 vs Qwen 3.8 Flash Next

Qwen 3.8 Flash Next is 99.2% cheaper for input tokens ($0.12 vs. $15.00 per 1M tokens) and $0.48 vs. $60.00 for output tokens (125.0x cost difference). In terms of operational performance, Qwen 3.8 Flash Next delivers faster response latency with 120ms TTFT (730ms faster than OpenAI o1). Qwen 3.8 Flash Next leads coding benchmarks at 56.8% SWE-bench vs. 48.9% for OpenAI o1.

Frequently Asked Questions & Query Fan-Out

How much does OpenAI o1 cost per 1M tokens?

OpenAI o1 costs $15.00 per million prompt (input) tokens and $60.00 per million completion (output) tokens.

What is the context window for OpenAI o1?

OpenAI o1 supports a maximum context window of 204,800 tokens, with a maximum single-generation output of 100,000 tokens.

What are the primary use cases for OpenAI o1?

Complex PhD-level multi-step science research, formal algorithm synthesis, and high-stakes reasoning pipelines.