openai/gpt-4-turbo-2024-04-09

openai/gpt-4-turbo-2024-04-09
VisionToolsJSON
by openai

OpenAI's GPT‑4 Turbo with 128K context, text/image input, accessed via OrcaRouter's API.

ctx128K tokens
Max output4.1K
Inputtext + image
Outputtext
p50 TTFT4.14 s
INPUT$10.00/ 1M tokens
OUTPUT$30.00/ 1M tokens
p50 TTFT4.14 s7d
p95 TTFT10.00 s7d
TRAFFIC584.4Ktokens / 7d

openai/gpt-4-turbo-2024-04-09 is a specific version of OpenAI's GPT-4 Turbo model, released on April 9, 2024. It accepts both text and image inputs and offers a context window of 128,000 tokens,…

What is openai/gpt-4-turbo-2024-04-09?

Who is this model designed for?

How does this model differ from earlier GPT-4 versions?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="openai/gpt-4-turbo-2024-04-09",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • frequency_penalty
  • logit_bias
  • logprobs
  • max_tokens
  • presence_penalty
  • response_format
  • seed
  • stop
  • stream
  • temperature
  • tool_choice
  • tools
  • top_logprobs
  • top_p

Pricing

Input / 1M tokens$10.00
Output / 1M tokens$30.00
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $160

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.0152

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
4.14 s
Output speed
30.6 tok/s
p95 TTFT
10.00 s
Error rate
0%

Public benchmarks

21.5
AA Coding
Better than 21% of models compared
#83 of 106
13.7
AA Intelligence
Better than 10% of models compared
#98 of 110
AIME
15.0
Humanity's Last Exam
3.3
LiveCodeBench
29.1
MATH-500
73.7
MMLU-Pro
69.4
SciCode
31.9
Source: artificialanalysis.ai

How it compares

openai/gpt-4-turbo-2024-04-09GPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$10.00$21.00$60.00$5.00
Output $/M$30.00$168.00$270.00$30.00
Context128K400K1.1M
Quality2/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost of using openai/gpt-4-turbo-2024-04-09 on OrcaRouter?
OrcaRouter bills at OpenAI's provider rate with zero markup. Input tokens cost $10.00 per 1M tokens, output tokens cost $30.00 per 1M tokens. Both text and image tokens are counted according to OpenAI's tokenization rules.
What is the context window size of this model?
The model has a context window of 128,000 tokens. It can accept up to 128K tokens in the input (including both text and image tokens) and generate up to 4,096 output tokens per request.
What are the model's main strengths?
The model excels at mathematical reasoning (scored 73.7 on MATH-500), handles very long contexts (128K tokens), and supports multimodal inputs (text and images). It is suitable for complex reasoning, long-document analysis, and vision-language tasks.
How does openai/gpt-4-turbo-2024-04-09 compare to GPT-4o?
GPT-4o is a newer, faster, and cheaper multimodal model also with 128K context. It typically achieves higher benchmark scores. GPT-4 Turbo may still be preferred if you have optimized prompts for this version or need specific behavior. Both are available on OrcaRouter.
How is data handled when using OrcaRouter?
OrcaRouter passes requests directly to OpenAI's API without storing or modifying the content. Your API key is used only for authentication. Data privacy follows OpenAI's policies. Refer to OrcaRouter's privacy documentation for details.
How do I call this model via the OpenAI-compatible API on OrcaRouter?
Set the base URL to https://api.orcarouter.ai/v1, use your OrcaRouter API key, and specify model="openai/gpt-4-turbo-2024-04-09" in your chat completions request. All standard parameters (temperature, max_tokens, etc.) are supported.
What is the maximum output token length?
The maximum output token length is 4,096 tokens. You can set max_tokens up to this value. If you need longer outputs, you will need to use multiple calls or a model with a higher output limit.
Can I use image inputs with this model?
Yes, the model accepts image inputs as base64-encoded strings or URLs. Include them in the messages array as content with type "image_url". Image tokens are charged at the input token rate.
Does OrcaRouter offer any caching or discounts for high volume?
OrcaRouter does not offer token caching or volume discounts for this model. Pricing is strictly per-token at the provider rate (zero markup). To reduce costs, optimize prompt length or switch to a cheaper model.
What are the known limitations of this model?
Limitations include potential for hallucination, verbosity, and lack of knowledge events after its training cutoff. It may also struggle with strict formatting instructions. For safety-critical applications, always validate outputs.

Embed this badge

openai/gpt-4-turbo-2024-04-09$10.00/M in4142ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-4-turbo-2024-04-09" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-4-turbo-2024-04-09.svg" alt="openai/gpt-4-turbo-2024-04-09 on OrcaRouter" /> </a>
Markdown [![openai/gpt-4-turbo-2024-04-09](https://www.orcarouter.ai/embed/openai/gpt-4-turbo-2024-04-09.svg)](https://www.orcarouter.ai/models/openai/gpt-4-turbo-2024-04-09)

Model card as data

GET /api/public/models/openai/gpt-4-turbo-2024-04-09Open
Machine-readable:/llms.txt/llms-full.txt