The June 2023 snapshot was the first GPT-4 checkpoint to support function calling, introducing structured JSON output for tool use through a dedicated API parameter. Many enterprises pinned to this exact version for reproducibility, making it the de facto stable GPT-4 reference point throughout 2023 with its 8K context window and September 2021 training cutoff.
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 |
|---|---|---|---|---|---|---|---|
| No data available at this time, please try again later. |
Powered by our own GPU infrastructure, select a large language model, add a prompt, and chat away. For unlimited chats, sign up for a free account on our Mission Control Portal here.
GPT-4 0613 is the June 2023 snapshot of OpenAI's GPT-4, notable for introducing function calling support. It is available through Telnyx's inference platform and OpenAI's API.
OpenAI is deprecating older GPT-4 snapshots as newer models like GPT-4o and GPT-4.1 provide better performance at lower cost. The 0613 snapshot will eventually be retired in favor of these successors.
The GPT-4 family is not gone, but individual snapshots like 0613 are being phased out. GPT-4o and GPT-4.1 carry forward GPT-4's capabilities with .
GPT-4 0613 shares the 86.4% MMLU (5-shot) and 8.99 MT-Bench of the GPT-4 family, with function calling as its primary addition over the 0314 snapshot on the same sheet. Its Arena ELO of 1,163 is close to the 0314 (1,186), with the slight difference likely reflecting evaluation timing rather than capability changes. It became the most widely adopted GPT-4 checkpoint for enterprise production systems.
The cost for utilizing this model with Telnyx Inference is $0.0010 per 1,000 tokens. For instance, analyzing 1,000,000 customer chats, assuming each chat is 1,000 tokens long, would cost $1,000.
The 0613 snapshot was the first GPT-4 version to support function calling, enabling structured tool integration. This feature became foundational for agent-based applications and is now standard across all OpenAI models.
GPT-4 0613 has been surpassed by GPT-4o, GPT-4.1, and GPT-5 on all major benchmarks. For new projects, migrating to a newer model is strongly recommended.
GPT-4 0613 is priced at $30 per million input tokens and $60 per million output tokens, making it one of the most expensive options. Newer models offer significantly better value.
