GPT-4.1
GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning.
gpt-4.1Released 14 Apr 2025 (Apr 2025)Pricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $2.00 | $8.00 | |
| Cached input 75% off input | $0.50 | 75% off input | |
| Batch 50% off | $1.00 | $4.00 | 50% off |
| Priority 75% more | $3.50 | $14.00 | 75% more |
| Web search $25.00 per 1,000 searches | $25.00 per 1,000 searches |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,065
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$888
- Coding agent1,000 requests a day, 40K in / 2K out, cached$1,620
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$3,360
Where to run it
4 hosts serve GPT-4.1. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API gpt-4.1 | $2.00 / $8.00 Retires 14 Jan 2027 | gpt-4.1 | Retires 14 Jan 2027 |
Azure OpenAICloud gpt-4.1 | $2.00 / $8.00 Retires 14 Apr 2027 | gpt-4.1 | Retires 14 Apr 2027 |
ReplicateInference gpt-4.1 | $2.00 / $8.00 | gpt-4.1 | |
Vercel AI GatewayGateway gpt-4.1 | $2.00 / $8.00 | gpt-4.1 | |
GitHub CopilotSubscription gpt-4.1 | In the subscription | gpt-4.1 |
Show 8 more listings: regions, snapshots and variantsHide regional listings
| OpenAI | |||||||
| 2025-04-14 gpt-4.1-2025-04-14 | $2.00 / $8.00 Retires 14 Jan 2027 | gpt-4.1-2025-04-14 | Retires 14 Jan 2027 | ||||
| 2025-04-14 · fine-tuning ft:gpt-4.1-2025-04-14 | $3.00 / $12.00 Retires 14 Jan 2027 | ft:gpt-4.1-2025-04-14 | Retires 14 Jan 2027 | ||||
| Azure OpenAI | |||||||
| 2025-04-14 gpt-4.1-2025-04-14 | $2.00 / $8.00 Retires 14 Apr 2027 | gpt-4.1-2025-04-14 | Retires 14 Apr 2027 | ||||
| eu gpt-4.1 | $2.20 / $8.80 +10% vs headline Retires 14 Apr 2027 | gpt-4.1 | Retires 14 Apr 2027 | ||||
| us gpt-4.1 | $2.20 / $8.80 +10% vs headline Retires 14 Apr 2027 | gpt-4.1 | Retires 14 Apr 2027 | ||||
| us · 2025-04-14 gpt-4.1-2025-04-14 | $2.20 / $8.80 +10% vs headline Retires 14 Apr 2027 | gpt-4.1-2025-04-14 | Retires 14 Apr 2027 | ||||
| us-gov gpt-4.1 | $2.75 / $11.00 +38% vs headline | gpt-4.1 | |||||
| GitHub Copilot | |||||||
| 2025-04-14 gpt-4.1-2025-04-14 | In the subscription | gpt-4.1-2025-04-14 | |||||
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
- ImagesTextPDFs
- Produces
- Text
- Features
- Parallel tool callsPDF inputPrompt cachingBuilt-in web search
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
- 43% less
- 52% less
- 87% less
Other frontier labs
- 14% less
- 14% less
- 94% less
- 57% less
Open-weight picks
- 36% less
- 51% less
- 80% less
- 85% less
Benchmarks
Scores published on the model card.
- Aider Polyglot52.4%
Model line
Newer and older versions, at each lab's own price.
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="gpt-4.1", input="Hello")
print(response.output_text)curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-4.1", "input": "Hello"}'from litellm import completion
response = completion(
model="openai/gpt-4.1",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GPT-4.1 cost?
On OpenAI, GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens. Cached input costs $0.50 per million tokens.
Which APIs offer GPT-4.1?
GPT-4.1 runs on 4 APIs: OpenAI, Azure OpenAI, Replicate and Vercel AI Gateway.
What is GPT-4.1's context window?
1M tokens, with up to 33K tokens in one reply.
Is GPT-4.1 being retired?
OpenAI retires it on 14 Jan 2027; Azure OpenAI (except US government regions) on 14 Apr 2027. 3 hosts keep serving it.
Is there a newer version of GPT-4.1?
Yes. GPT-5.6 is the newest model in this line.
What are cheaper alternatives to GPT-4.1?
Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (43% less), Gemini 4 Hydrogen on Google AI Studio (14% less), Grok 4.7 on xAI (14% less) and Qwen4 Max on Alibaba DashScope (36% less). Savings are on a mix of 3 input tokens to 1 output token.
When was GPT-4.1 released?
OpenAI released it on 14 Apr 2025.
What is GPT-4.1's API model id?
Use gpt-4.1 with OpenAI.
Sources
Raw catalog entry for gpt-4.1 on OpenAI
{
"cache_read_input_token_cost": 5e-7,
"cache_read_input_token_cost_priority": 8.75e-7,
"deprecation_date": "2027-01-14",
"deprecation_source": "https://developers.openai.com/api/docs/deprecations",
"successor_model": "gpt-6-luna",
"input_cost_per_token": 0.000002,
"input_cost_per_token_batches": 0.000001,
"input_cost_per_token_priority": 0.0000035,
"litellm_provider": "openai",
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 0.000008,
"fedramp_uplift_multiplier": 1.1,
"output_cost_per_token_batches": 0.000004,
"output_cost_per_token_priority": 0.000014,
"search_context_cost_per_query": {
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.025
},
"source": "https://developers.openai.com/api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": 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,
"supports_web_search": true
}