openai/gpt-3.5-turbo-0125

openai/gpt-3.5-turbo-0125
ToolsJSON
by openai

Cost-effective text model from OpenAI with 46.2 MMLU-Pro score, accessed via OrcaRouter API.

Max output4.1K
Inputtext
p50 TTFT3.64 s
INPUT$0.50/ 1M tokens
OUTPUT$1.50/ 1M tokens
p50 TTFT3.64 s7d
p95 TTFT3.64 s7d
TRAFFIC5.8Ktokens / 7d

openai/gpt-3.5-turbo-0125 is a text generation model developed by OpenAI and available through OrcaRouter's API. It is part of the GPT-3.5-Turbo family, optimized for conversational tasks and…

What is openai/gpt-3.5-turbo-0125?

Who should use this model?

How does OrcaRouter deliver this model?

What are the input/output characteristics?

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-3.5-turbo-0125",
    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
  • parallel_tool_calls

Pricing

Input / 1M tokens$0.500
Output / 1M tokens$1.50
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $8.00

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000760

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

Performance

p50 TTFT
3.64 s
Output speed
Collecting…
p95 TTFT
3.64 s
Error rate
0%

Public benchmarks

10.7
AA Coding
Better than 2% of models compared
#118 of 123
3.6
AA Intelligence
Better than 0% of models compared
#122 of 125
GPQA Diamond
29.7
MATH-500
44.1
MMLU-Pro
46.2
Source: artificialanalysis.ai

How it compares

openai/gpt-3.5-turbo-0125GPT-5.2 ProGPT-5.4 ProGPT-5.5
Input $/M$0.50$21.00$60.00$5.00
Output $/M$1.50$168.00$270.00$30.00
Context400K1.1M
Quality2/1010/1010/1010/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to use openai/gpt-3.5-turbo-0125 on OrcaRouter?
Pricing is exactly OpenAI's direct rate with zero markup: $0.50 per 1 million input tokens and $1.50 per 1 million output tokens. There are no additional fees.
What is the context window size?
The model supports a total context of 16,385 tokens (input + output), with output capped at 4096 tokens per generation. This is widely known public information for this model version.
What are the main strengths of this model?
It offers a strong balance of speed, cost, and quality for text tasks. It scores 46.2 on MMLU-Pro and handles instruction following, chat, and structured outputs reliably.
How does it compare to GPT-4?
GPT-4 outperforms it on complex reasoning but costs significantly more per token. Use GPT-3.5-Turbo-0125 for cost-sensitive or high-volume applications where near-GPT-4 accuracy isn't required.
Does OrcaRouter log or store my data?
OrcaRouter processes requests to OpenAI's API. It does not log or store prompts or completions beyond what is necessary for billing and operational security. Review OpenAI's privacy policy for their data handling.
How do I call this model using an OpenAI-compatible API?
Set base URL to https://api.orcarouter.ai/v1, model to 'openai/gpt-3.5-turbo-0125', and use your OrcaRouter API key in the Authorization header. Standard chat completions format works.
Can I stream responses?
Yes. Set the 'stream' parameter to true in your request. Responses will be sent as server-sent events with token deltas, matching the OpenAI streaming format.
What is the maximum output length?
The model can generate up to 4096 tokens in a single response. Use the 'max_tokens' parameter to control this, but it cannot exceed 4096.
Is this model suitable for multilingual tasks?
It works across many languages but performs best in English. Accuracy may drop for low-resource languages or complex idiomatic expressions.

Embed this badge

openai/gpt-3.5-turbo-0125$0.50/M in3644ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/openai/gpt-3.5-turbo-0125" target="_blank"> <img src="https://www.orcarouter.ai/embed/openai/gpt-3.5-turbo-0125.svg" alt="openai/gpt-3.5-turbo-0125 on OrcaRouter" /> </a>
Markdown [![openai/gpt-3.5-turbo-0125](https://www.orcarouter.ai/embed/openai/gpt-3.5-turbo-0125.svg)](https://www.orcarouter.ai/models/openai/gpt-3.5-turbo-0125)

Model card as data

GET /api/public/models/openai/gpt-3.5-turbo-0125Open
Machine-readable:/llms.txt/llms-full.txt