--- title: GPT-3.5 Turbo-0613—Performance and quality overview canonical: https://telnyx.com/llm-library/gpt-3-5-turbo-0613 --- # GPT-3.5 Turbo-0613—Performance and quality overview [Start building](https://telnyx.com/sign-up) ### Ask AI * [![GPT](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/chatgpt_icon-ea55e09d.jpeg?width=92&format=webp)](https://chat.openai.com/?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Claude](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/claude_icon-c7c8eef3.webp?width=92&format=webp)](https://claude.ai/new?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Perplexity](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/perplexity_icon-cd5b74f1.webp?width=92&format=webp)](https://www.perplexity.ai/search?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Gemini](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/gemini_icon-4ff1cbf4.webp?width=92&format=webp)](https://www.google.com/search?udm=50&aep=11&q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Grok](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/grok_icon-e588e5bd.webp?width=92&format=webp)](https://x.com/i/grok?text=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) # GPT-3.5 Turbo-0613 The June 2023 snapshot of GPT-3.5 Turbo, recognized for strong system prompt adherence and reliable instruction-following in chat and completion tasks. [Start building](https://telnyx.com/sign-up)[GET Available Models](https://developers.telnyx.com/docs/inference/models) ## about The June 2023 snapshot introduced [function calling to GPT-3.5 Turbo](https://developers.openai.com/docs/models/gpt-3.5-turbo), enabling structured JSON output for tool use through a new `functions` API parameter. It also improved system message steerability over the original 0301 snapshot, making it the first 3.5 variant widely adopted for production API workflows requiring consistent instruction-following. Licenseopenai Context window ## Explore Our LLM Library Discover the power and diversity of large language models available with Telnyx. Explore the options below to find the perfect model for your project. ### DeepSeek-V4-Flash-0731 OrganizationTelnyx Model NameDeepSeek-V4-Flash-0731 Taskstext generation Languages SupportedEnglish Context Length1,048,576 Parameters284.0B Model Tierunlisted Licensemit ### DeepSeek-V4.1-Flash ### gemma-2b-it ### gemma-4-26B-A4B-it ### gemma-4-31B-it ### Llama-3.3-70B-Instruct ### Meta-Llama-3.1-70B-Instruct ### Meta-Llama-3.1-8B-Instruct ### MiniMax-M2.7 ### MiniMax-M3-MXFP8 ### Kimi-K2.5 ### Kimi-K2.6 ### Kimi-K3 ### personaplex-7b-v1 ### Laguna-S-2.1 ### Qwen3-235B-A22B ### Qwen3.8-27B ### GLM-5.1-FP8 ### GLM-5.2 ### GLM-5.3 ### GLM-5.3-Flash ### claude-haiku-4-5 ### gemini-2.5-flash ### gemini-3.7-flash ### gpt-oss-120b ### gpt-4.1 ### gpt-4o ### gpt-4o-mini ### gpt-5 ### gpt-5.1 ### gpt-5.2 ### gpt-5.4 ### gpt-5.4-mini ### gpt-5.6-luna ### gpt-5.6-sol ### gpt-live-1 HOW IT WORKS ## Selecting LLMs for Voice AI [GET Available Models](https://developers.telnyx.com/docs/inference/models) ### Create an account Sign-up to the Telnyx platform to get access to our suite of intuitive AI tools. ### Choose GPT-3.5 Turbo-0613 In the [AI Playground](https://portal.telnyx.com/#/app/next/ai/ai-playground "Telnyx AI Playground") select GPT-3.5 Turbo-0613 from the dropdown. ### Enter your API key If you’re using a proprietary model, you’ll need your API key before prompting the LLM. Our vast selection of OS models allow you to get started right away. ### Prompt the LLM Get responses from an LLM in minutes, and scale with our [OpenAI-compatible APIs](https://developers.telnyx.com/docs/inference/getting-started "Inference API Quickstart"). Step 1/4 **RESOURCES** ## Get started Check out our helpful tools to help get you started. * ### Test in the portal Easily browse and select your preferred model in the AI Playground. [Test today](https://portal.telnyx.com/#/ai/assistants) ## Sign up and start building [Sign up](https://telnyx.com/sign-up)[Contact sales](https://telnyx.com/contact-us) ## faqs ### Does GPT-3.5 Turbo still exist? GPT-3.5 Turbo 0613 was deprecated by OpenAI in favor of newer snapshots. The [0125 variant](https://telnyx.com/llm-library/gpt-3-5-turbo) is the recommended replacement, and OpenAI suggests migrating to GPT-4o mini for new projects. ### Is GPT-3.5 Turbo a good model? GPT-3.5 Turbo 0613 was the first snapshot to support function calling, making it a foundational model for tool-using applications. While surpassed by newer models, it remains functional for [basic chat and classification tasks](https://telnyx.com/llm-library/gpt-3-5-turbo-0613) at low cost. ### What is the difference between GPT-3 and GPT-3.5 Turbo? GPT-3.5 Turbo added chat optimization, function calling, and significantly lower pricing compared to GPT-3's completion-based API. The was the first to introduce function calling, enabling structured tool integration. (in thousands) 4096 ## Use cases for GPT-3.5 Turbo-0613 1. **Structured API tool use:** As the first GPT-3.5 model with native function calling, the 0613 snapshot converts natural language into structured JSON function calls for reliable API orchestration. 2. **System prompt-driven agents:** Improved system message adherence makes it effective for applications where consistent persona, tone, and behavioral constraints must be maintained across conversations. 3. **Legacy workflow compatibility:** As a pinned snapshot with deterministic behavior, it serves as a stable inference target for production systems that depend on consistent output formatting. ## Quality Arena Elo1117 MMLUN/A MT Bench8.39 GPT-3.5 Turbo 0613 shares the 70.0% MMLU (5-shot) and 7.94 MT-Bench baseline of the GPT-3.5 Turbo family. As the first snapshot to introduce function calling, its quality differentiation from later snapshots (1106, 0125) is in structured output reliability rather than raw benchmark performance. Compared to Mixtral 8x7B (70.6% MMLU, 8.30 MT-Bench) on the sheet, it trails by a narrow margin on both measures. **Llama 3 Instruct 8B** 1152 **Claude-Sonnet-4-20250514** 1138 **GPT-3.5 Turbo-0613** 1117 **Mixtral 8x7B Instruct v0.1** 1114 **GPT-3.5 Turbo-0125** 1106 ## pricing The cost per 1,000 tokens for running the model with Telnyx Inference is $0.0010\. To illustrate, if a marketing ops team were to analyze 1,000,000 customer chats, assuming each chat is 1,000 tokens long, the total cost would be $1,000. ## What's Twitter saying? * Developers report **worse output quality** with GPT-3.5-turbo-0613 compared to 0301, as it ignores system prompts and produces unusable results across inputs. * Users note **poorer performance in non-English languages** and overall "more stupid" behavior, leading to calls not to deprecate older versions. * Benchmarks show **lower labeling accuracy** on 6/8 datasets versus prior models, though it's \~40% faster. | 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 | small | mit | | google | [gemma-2b-it](https://telnyx.com/llm-library/gemma-2b-it) | text generation | English | 8,192 | 2.5B | small | gemma | | google | gemma-4-26B-A4B-it | text to-text | Multilingual | 262,144 | 25.8B | small | apache-2.0 | | google | gemma-4-31B-it | text generation | Multilingual | 131,072 | 30.7B | small | apache-2.0 | | meta-llama | [Llama-3.3-70B-Instruct](https://telnyx.com/llm-library/llama-3.3-70b-instruct) | text generation | Multilingual | 99,000 | 70.6B | large | llama3.3 | | meta-llama | [Meta-Llama-3.1-70B-Instruct](https://telnyx.com/llm-library/meta-llama-3-1-70b-instruct) | text generation | Multilingual | 99,000 | 70.6B | large | llama3.1 | | meta-llama | [Meta-Llama-3.1-8B-Instruct](https://telnyx.com/llm-library/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 | small | minimax-community | | moonshotai | [Kimi-K2.5](https://telnyx.com/llm-library/kimi-k2.5) | text generation | Multilingual | 256,000 | 1.0T | large | modified-mit | | moonshotai | Kimi-K2.6 | text generation | Multilingual | 262,144 | 1.0T | medium | modified-mit | | moonshotai | Kimi-K3 | text generation | English | 1,000,000 | 2.8M | large | MIT Modified | | nvidia | personaplex-7b-v1 | speech to-speech | English | 3,000 | 7.0B | small | nvidia-open-model-license | | poolside | Laguna-S-2.1 | text generation | English | 1,048,576 | 117.6B | unlisted | OpenMDW-1.1 | | Qwen | [Qwen3-235B-A22B](https://telnyx.com/llm-library/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 | small | 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 | medium | MIT | | Telnyx | GLM-5.3 | text generation | English | 1,048,576 | 753.0B | medium | glm-5.3 | | zai-org | GLM-5.3-Flash | text generation | English | 1,048,576 | 320.0B | small | mit | | anthropic | [claude-haiku-4-5](https://telnyx.com/llm-library/claude-haiku-4-5) | text generation | Multilingual | 400,000 | 0 | large | openai | | google | [gemini-2.5-flash](https://telnyx.com/llm-library/gemini-2.5-flash) | text generation | Multilingual | 400,000 | 0 | large | openai | | google | gemini-3.7-flash | text generation | Multilingual | 400,000 | 0 | large | openai | | groq | [gpt-oss-120b](https://telnyx.com/llm-library/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](https://telnyx.com/llm-library/gpt-4-omni) | text generation | Multilingual | 400,000 | 0 | large | openai | | openai | [gpt-4o-mini](https://telnyx.com/llm-library/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](https://telnyx.com/llm-library/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 | * ### Explore the docs Don’t wait to scale, start today with our public API endpoints. [Get started](https://developers.telnyx.com/api-reference/assistants/list-assistants) * ### Stay up to date Keep an eye on our AI changelog so you don't miss a beat. [See updates](https://telnyx.com/release-notes) 0613 snapshot ### What is GPT-4 0613? GPT-4 0613 is a separate model, the June 2023 snapshot of GPT-4 with function calling support. It is not related to GPT-3.5 Turbo 0613 beyond sharing the same release date convention. Both are available through [OpenAI's API](https://telnyx.com/llm-library/gpt-3-5-turbo-0613). ### How much does GPT-3.5 Turbo cost? GPT-3.5 Turbo 0613 is priced at $1.50 per million input tokens and $2.00 per million output tokens. The newer [0125 snapshot](https://telnyx.com/llm-library/gpt-3-5-turbo) offers the same capability at lower pricing. GPT-3.5 Turbo-0613—Performance and quality overview