The model that brought large language models into mainstream production, GPT-3.5 Turbo is believed to run at roughly 20B parameters based on leaked research, achieving better performance than the 175B GPT-3 through RLHF fine-tuning. It supports function calling, JSON mode, and a 16K context window, and dominated the API market through 2023 as the default cost-performance choice.
GPT-3.5 Turbo scores 70.0% on MMLU (5-shot) and 7.94 on MT-Bench, establishing the quality baseline for the chat model category when it launched. Compared to GPT-4 (86.4% MMLU, 8.99 MT-Bench) on the same sheet, it trades 16 points of general knowledge for significantly lower cost and faster inference. It remains the most-used model for applications where speed and cost matter more than maximum reasoning depth.
Telnyx Inference offers a cost-effective solution for running GPT-3.5 Turbo. It costs $0.0010 for every 1,000 tokens when running the model. For example, if you analyze 1,000,000 customer chats, and each chat has 1,000 tokens, it will cost $1,000.
Discover the power and diversity of large language models available with Telnyx. Explore the options below to find the perfect model for your project.
| Organization | Model Name | Tasks | Languages Supported | Context Length | Parameters | Model Tier | License |
|---|---|---|---|---|---|---|---|
| Telnyx | DeepSeek-V4-Flash-0731 | text generation | English | 1,048,576 | 284.0B | unlisted | mit |
| Telnyx | DeepSeek-V4.1-Flash | text generation | English | 1,048,576 | 552.0B | unlisted | mit |
| gemma-2b-it | text generation | English | 8,192 | 2.5B | small | gemma | |
| gemma-4-26B-A4B-it | text to-text | Multilingual | 262,144 | 25.8B | small | apache-2.0 | |
| gemma-4-31B-it | text generation | Multilingual | 131,072 | 30.7B | unlisted | apache-2.0 | |
| meta-llama | Llama-3.3-70B-Instruct | text generation | Multilingual | 99,000 | 70.6B | large | llama3.3 |
| meta-llama | Meta-Llama-3.1-70B-Instruct | text generation | Multilingual | 99,000 | 70.6B | large | llama3.1 |
| meta-llama | Meta-Llama-3.1-8B-Instruct | text generation | Multilingual | 131,072 | 8.0B | small | llama3.1 |
| minimaxai | MiniMax-M2.7 | text generation | Multilingual | 200,000 | 0 | large | minimaxai |
| minimaxai | MiniMax-M3-MXFP8 | text generation | Multilingual | 1,000,000 | 428.0B | large | minimax-community |
| moonshotai | Kimi-K2.5 | text generation | Multilingual | 256,000 | 1.0T | large | modified-mit |
| moonshotai | Kimi-K2.6 | text generation | Multilingual | 262,144 | 1.0T | large | modified-mit |
| moonshotai | Kimi-K3 | text generation | English | 1,000,000 | 2.8M | large | MIT Modified |
| Qwen | Qwen3-235B-A22B | text generation | English | 32,768 | 235.1B | large | apache-2.0 |
| Telnyx | Qwen3.8-27B | text generation | English | 262,144 | 27.0B | unlisted | Apache 2.0 |
| zai-org | GLM-5.1-FP8 | text generation | Multilingual | 202,752 | 753.9B | large | mit |
| zai-org | GLM-5.2 | text generation | English | 1,000,000 | 753.9B | large | MIT |
| Telnyx | GLM-5.3 | text generation | English | 1,048,576 | 753.0B | unlisted | glm-5.3 |
| zai-org | GLM-5.3-Flash | text generation | English | 1,048,576 | 320.0B | unlisted | mit |
| anthropic | claude-haiku-4-5 | text generation | Multilingual | 400,000 | 0 | large | openai |
| gemini-2.5-flash | text generation | Multilingual | 400,000 | 0 | large | openai | |
| gemini-3.7-flash | text generation | Multilingual | 400,000 | 0 | large | openai | |
| groq | gpt-oss-120b | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-4.1 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-4o | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-4o-mini | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.1 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.2 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.4 | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.4-mini | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.6-luna | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-5.6-sol | text generation | Multilingual | 400,000 | 0 | large | openai |
| openai | gpt-live-1 | speech to-speech | Multilingual | 400,000 | 0 | large | openai |
Check out our helpful tools to help get you started.
Yes, GPT-3.5 Turbo remains available through the API, with the 0125 snapshot being the latest version. OpenAI recommends GPT-4o mini as the successor for new projects.
GPT-3.5 Turbo is not free through the API but is one of OpenAI's most affordable models. It may be accessible through ChatGPT's free tier, and inference providers offer hosted access.
GPT-4 is significantly more capable than GPT-3.5 Turbo on reasoning, coding, and complex tasks. GPT-3.5 Turbo's advantages are speed and cost, making it suitable for high-volume, straightforward tasks.
GPT-3.5 Turbo is priced at $0.50-$1.50 per million input tokens depending on the snapshot. It is one of the cheapest options in OpenAI's lineup.
GPT-3.5 Turbo was the original ChatGPT model and handles conversational tasks well at low cost. For new chatbot projects, GPT-4o mini offers better performance at competitive pricing.
GPT-3.5 Turbo supports a 16K token context window in its latest snapshots. For applications requiring longer context, newer models like GPT-4o mini (128K) or GPT-4.1 (1M) are better options.
