impulse

GPT-4o

Frontier labRetiring 14 Jan 2027

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability.

API id gpt-4oReleased 13 May 2024 (May 2024)
Azure OpenAI (2024-05-13 only), OpenAI retire it on 14 Jan 2027 (in 57 days); Azure OpenAI (except US government regions) on 14 Apr 2027. 4 hosts keep serving it.
Input / 1M
$2.50
at OpenAI
Output / 1M
$10.00
at OpenAI
Context window
128K
tokens
Max output
16K
tokens per reply
Hosts
5
30 listings
Released
May 2024
13 May 2024

Pricing

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

TierInput / 1MOutput / 1M
Standard$2.50$10.00
Cached input
50% off input
$1.25
Batch
50% off
$1.25$5.00
Priority
70% more
$4.25$17.00

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,388
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$1,260
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$2,550
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$4,200
Use your own numbers

Where to run it

5 hosts serve GPT-4o. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-4o
$2.50 / $10.00
Retires 14 Jan 2027
gpt-4o
$2.50 / $10.00
Retires 14 Apr 2027
GMI CloudInference
gpt-4o
$2.50 / $10.00
ReplicateInference
gpt-4o
$2.50 / $10.00
gpt-4o
$2.50 / $10.00
GitHub CopilotSubscription
gpt-4o
In the subscription
Show 24 more listings: regions, snapshots and variants
OpenAI
2024-08-06
gpt-4o-2024-08-06
$2.50 / $10.00
Retires 14 Jan 2027
2024-11-20
gpt-4o-2024-11-20
$2.50 / $10.00
Retires 14 Jan 2027
2024-05-13
gpt-4o-2024-05-13
$5.00 / $15.00
+71% vs headline
2024-08-06 · fine-tuning
ft:gpt-4o-2024-08-06
$3.75 / $15.00
Retires 14 Jan 2027
2024-11-20 · fine-tuning
ft:gpt-4o-2024-11-20
$3.75 / $15.00
Retires 14 Jan 2027
Azure OpenAI
Global Standard · 2024-08-06
gpt-4o-2024-08-06
$2.50 / $10.00
Retires 14 Apr 2027
global · 2024-08-06
gpt-4o-2024-08-06
$2.50 / $10.00
Retires 14 Apr 2027
2024-08-06
gpt-4o-2024-08-06
$2.50 / $10.00
Retires 14 Apr 2027
Global Standard · 2024-11-20
gpt-4o-2024-11-20
$2.50 / $10.00
Retires 14 Apr 2027
global · 2024-11-20
gpt-4o-2024-11-20
$2.50 / $10.00
Retires 14 Apr 2027
2024-11-20
gpt-4o-2024-11-20
$2.50 / $10.00
Retires 14 Apr 2027
eu
gpt-4o
$2.75 / $11.00
+10% vs headline
Retires 14 Apr 2027
us
gpt-4o
$2.75 / $11.00
+10% vs headline
Retires 14 Apr 2027
eu · 2024-08-06
gpt-4o-2024-08-06
$2.75 / $11.00
+10% vs headline
Retires 14 Apr 2027
us · 2024-08-06
gpt-4o-2024-08-06
$2.75 / $11.00
+10% vs headline
Retires 14 Apr 2027
eu · 2024-11-20
gpt-4o-2024-11-20
$2.75 / $11.00
+10% vs headline
Retires 14 Apr 2027
us · 2024-11-20
gpt-4o-2024-11-20
$2.75 / $11.00
+10% vs headline
Retires 14 Apr 2027
us-gov
gpt-4o
$3.44 / $13.75
+38% vs headline
2024-05-13
gpt-4o-2024-05-13
$5.00 / $15.00
+71% vs headline
Retires 14 Jan 2027
eu · 2024-05-13
gpt-4o-2024-05-13
$5.50 / $16.50
+89% vs headline
Retires 14 Jan 2027
us · 2024-05-13
gpt-4o-2024-05-13
$5.50 / $16.50
+89% vs headline
Retires 14 Jan 2027
GitHub Copilot
2024-05-13
gpt-4o-2024-05-13
In the subscription
2024-08-06
gpt-4o-2024-08-06
In the subscription
2024-11-20
gpt-4o-2024-11-20
In the subscription

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
Parallel tool callsPDF 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 Sol
    OpenAI · on OpenAI
    $2.00 / $10.00
    Has every key capability
    9% less
  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    54% less
  • GPT-5.4 Mini
    OpenAI · on OpenAI
    $0.75 / $4.50
    Has every key capability
    61% less

Other frontier labs

  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    9% less
  • Claude Sonnet 5.5
    Anthropic · on Anthropic
    $2.00 / $10.00
    Has every key capability
    9% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    31% less
  • Gemini 4 Argon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    9% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    9% less
  • Qwen4 Max
    Alibaba Qwen · on Alibaba DashScope
    $1.50 / $4.50
    Has every key capability
    49% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    61% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    88% less

Benchmarks

Scores published on the model card.

  • Aider Polyglot18.2%

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-4o", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-4o cost?

On OpenAI, GPT-4o costs $2.50 per million input tokens and $10.00 per million output tokens. Cached input costs $1.25 per million tokens.

Which APIs offer GPT-4o?

GPT-4o runs on 5 APIs: OpenAI, Azure OpenAI, GMI Cloud, Replicate and Vercel AI Gateway.

What is GPT-4o's context window?

128K tokens, with up to 16K tokens in one reply.

Is GPT-4o being retired?

Azure OpenAI (2024-05-13 only) and OpenAI retire it on 14 Jan 2027; Azure OpenAI (except US government regions) on 14 Apr 2027. 4 hosts keep serving it.

What are cheaper alternatives to GPT-4o?

Models that cost less and keep most of what it can do: GPT-6.2 Sol on OpenAI (9% less), Gemini 4 Carbon on Google AI Studio (9% less), Claude Sonnet 5.5 on Anthropic (9% less) and Kimi K3.1 Pro on Databricks (9% less). Savings are on a mix of 3 input tokens to 1 output token.

When was GPT-4o released?

OpenAI released it on 13 May 2024.

What is GPT-4o's API model id?

Use gpt-4o with OpenAI.

Sources

Raw catalog entry for gpt-4o on OpenAI
{
  "cache_read_input_token_cost": 0.00000125,
  "cache_read_input_token_cost_priority": 0.000002125,
  "deprecation_date": "2027-01-14",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-6-luna",
  "input_cost_per_token": 0.0000025,
  "input_cost_per_token_batches": 0.00000125,
  "input_cost_per_token_priority": 0.00000425,
  "litellm_provider": "openai",
  "max_input_tokens": 128000,
  "max_output_tokens": 16384,
  "mode": "chat",
  "output_cost_per_token": 0.00001,
  "fedramp_uplift_multiplier": 1.1,
  "output_cost_per_token_batches": 0.000005,
  "output_cost_per_token_priority": 0.000017,
  "source": "https://developers.openai.com/api/docs/pricing",
  "supports_function_calling": true,
  "supports_parallel_function_calling": true,
  "supports_pdf_input": true,
  "supports_prompt_caching": true,
  "supports_response_schema": true,
  "supports_system_messages": true,
  "supports_tool_choice": true,
  "supports_vision": true
}