impulse

o1

Frontier lab
API id o1Released 17 Dec 2024 (Dec 2024)
A newer model in this line is out: o3, released 16 Apr 2025.
Azure OpenAI retires it on 19 Nov 2026 (tomorrow). 3 hosts keep serving it.
Input / 1M
$15.00
at OpenAI
Output / 1M
$60.00
at OpenAI
Context window
200K
tokens
Max output
100K
tokens per reply
Hosts
4
10 listings
Released
Dec 2024
17 Dec 2024

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$15.00$60.00
Cached input
50% off input
$7.50
Batch
50% off
$7.50$30.00

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$8,325
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$7,560
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$15,300
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$25,200
Use your own numbers

Where to run it

4 hosts serve o1. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
o1
$15.00 / $60.00
$15.00 / $60.00
Retires 19 Nov 2026
ReplicateInference
o1
$15.00 / $60.00
$15.00 / $60.00
Show 6 more listings: regions, snapshots and variants
OpenAI
2024-12-17
o1-2024-12-17
$15.00 / $60.00
Azure OpenAI
2024-12-17
o1-2024-12-17
$15.00 / $60.00
Retires 19 Nov 2026
eu
o1
$16.50 / $66.00
+10% vs headline
Retires 19 Nov 2026
us
o1
$16.50 / $66.00
+10% vs headline
Retires 19 Nov 2026
eu · 2024-12-17
o1-2024-12-17
$16.50 / $66.00
+10% vs headline
Retires 19 Nov 2026
us · 2024-12-17
o1-2024-12-17
$16.50 / $66.00
+10% vs headline
Retires 19 Nov 2026

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImagesPDFs
Produces
Text
Features
PDF inputPrompt caching

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than OpenAI.

Smaller OpenAI models

  • GPT-6.2 Astra
    OpenAI · on OpenAI
    $8.00 / $40.00
    Has every key capability
    39% less
  • GPT-5.3 Codex
    OpenAI · on OpenAI
    $1.75 / $14.00
    Has every key capability
    82% less
  • GPT-6.2 Sol
    OpenAI · on OpenAI
    $2.00 / $10.00
    Has every key capability
    85% less

Other frontier labs

  • Claude Fable 5.2
    Anthropic · on Anthropic
    $8.00 / $40.00
    Has every key capability
    39% less
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    85% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    89% less
  • Claude Opus 5.5
    Anthropic · on Anthropic
    $4.00 / $20.00
    Has every key capability
    70% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    85% less
  • Qwen4 Max
    Alibaba Qwen · on Together AI
    $1.43 / $4.28
    Has every key capability
    92% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    93% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    98% less

Benchmarks

Scores published on the model card.

  • Aider Polyglot61.7%

Model line

Newer and older versions, at each lab's own price.

  1. Apr 2025o3Latest$2.00 / $8.00
  2. Dec 2024o1This page$15.00 / $60.00

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="o1", input="Hello")
print(response.output_text)

Quick answers

How much does o1 cost?

On OpenAI, o1 costs $15.00 per million input tokens and $60.00 per million output tokens. Cached input costs $7.50 per million tokens.

Which APIs offer o1?

o1 runs on 4 APIs: OpenAI, Azure OpenAI, Replicate and Vercel AI Gateway.

What is o1's context window?

200K tokens, with up to 100K tokens in one reply.

Is o1 being retired?

Azure OpenAI retires it on 19 Nov 2026. 3 hosts keep serving it.

Is there a newer version of o1?

Yes. o3 is the newest model in this line, released on 16 Apr 2025.

What are cheaper alternatives to o1?

Models that cost less and keep most of what it can do: GPT-6.2 Astra on OpenAI (39% less), Claude Fable 5.2 on Anthropic (39% less), Gemini 4 Carbon on Google AI Studio (85% less) and Kimi K3.1 Pro on Databricks (85% less). Savings are on a mix of 3 input tokens to 1 output token.

When was o1 released?

OpenAI released it on 17 Dec 2024.

What is o1's API model id?

Use o1 with OpenAI.

Sources

Raw catalog entry for o1 on OpenAI
{
  "cache_read_input_token_cost": 0.0000075,
  "deprecation_date": "2026-10-23",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-5.6-sol",
  "input_cost_per_token": 0.000015,
  "input_cost_per_token_batches": 0.0000075,
  "litellm_provider": "openai",
  "max_input_tokens": 200000,
  "max_output_tokens": 100000,
  "mode": "chat",
  "output_cost_per_token": 0.00006,
  "fedramp_uplift_multiplier": 1.1,
  "output_cost_per_token_batches": 0.00003,
  "source": "https://developers.openai.com/api/docs/pricing",
  "supports_function_calling": true,
  "supports_parallel_function_calling": false,
  "supports_pdf_input": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_system_messages": true,
  "supports_tool_choice": true,
  "supports_vision": true
}