impulse

GPT-4 Preview

Frontier labPreview
API id gpt-4-1106-preview
Input / 1M
$10.00
at OpenAI
Output / 1M
$30.00
at OpenAI
Context window
128K
tokens
Max output
4K
tokens per reply
Hosts
2
3 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$10.00$30.00

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$5,250
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$5,880
  • Coding agent1,000 requests a day, 40K in / 2K out$13,800
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$31,200
Use your own numbers

Where to run it

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

HostIn / out per 1M
OpenAILab API
1106
gpt-4-1106-preview
$10.00 / $30.00
0125
gpt-4-0125-preview
$10.00 / $30.00
Show 1 more listings: regions, snapshots and variants
Azure OpenAI
1106
gpt-4-1106-preview
$10.00 / $30.00

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
Text
Produces
Text
Features
Parallel tool callsPrompt 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-5.3 Codex
    OpenAI · on OpenAI
    $1.75 / $14.00
    Has every key capability
    68% less
  • GPT-6.2 Sol
    OpenAI · on OpenAI
    $2.00 / $10.00
    Has every key capability
    73% less
  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    87% less

Other frontier labs

  • Claude Opus 5.5
    Anthropic · on Anthropic
    $4.00 / $20.00
    Has every key capability
    47% less
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    73% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    80% less
  • Gemini 4 Argon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    73% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    73% less
  • Qwen3.8.2 4T A95B
    Alibaba Qwen · on DeepInfra
    $2.00 / $6.00
    Has every key capability
    80% less
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability
    87% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    89% less

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-4-1106-preview", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-4 Preview cost?

On OpenAI, GPT-4 Preview costs $10.00 per million input tokens and $30.00 per million output tokens.

Which APIs offer GPT-4 Preview?

GPT-4 Preview runs on 2 APIs: OpenAI and Azure OpenAI.

What is GPT-4 Preview's context window?

128K tokens, with up to 4K tokens in one reply.

Is GPT-4 Preview being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to GPT-4 Preview?

Models that cost less and keep most of what it can do: GPT-5.3 Codex on OpenAI (68% less), Claude Opus 5.5 on Anthropic (47% less), Gemini 4 Carbon on Google AI Studio (73% less) and Kimi K3.1 Pro on Databricks (73% less). Savings are on a mix of 3 input tokens to 1 output token.

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

Use gpt-4-1106-preview with OpenAI. Other hosts use their own ids: gpt-4-0125-preview on Azure OpenAI.

Sources

Raw catalog entry for gpt-4-1106-preview on OpenAI
{
  "deprecation_date": "2026-10-23",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-5.6-sol",
  "input_cost_per_token": 0.00001,
  "litellm_provider": "openai",
  "max_input_tokens": 128000,
  "max_output_tokens": 4096,
  "mode": "chat",
  "output_cost_per_token": 0.00003,
  "fedramp_uplift_multiplier": 1.1,
  "supports_function_calling": true,
  "supports_parallel_function_calling": true,
  "supports_prompt_caching": true,
  "supports_system_messages": true,
  "supports_tool_choice": true
}