Widely reported as a mixture-of-experts architecture with roughly 1.8 trillion total parameters across 16 experts, GPT-4 scored in the 86th percentile on the Uniform Bar Exam compared to the 10th percentile for GPT-3.5. It launched at 60x the cost of GPT-3.5 Turbo and shipped without vision or function calling, both of which were added in later snapshots.
GPT-4 scores 86.4% on MMLU (5-shot) and 8.99 on MT-Bench, a 16-point MMLU improvement over GPT-3.5 Turbo (70.0%) on the same sheet. It passes the Uniform Bar Exam in the 90th percentile and scores in the 99th percentile on the Biology Olympiad. These benchmark results established the quality baseline that subsequent models on the sheet are measured against.
The cost of running the model with Telnyx Inference is $1.00 per 1,000 tokens. For instance, analyzing 1,000,000 customer chats, assuming each chat is 10 tokens long, would require 10,000,000 tokens. Therefore, the total cost would be $10,000.
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 | small | 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 | small | 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 | small | 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 | 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 | 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 | 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.
GPT-4 is available with usage limits in ChatGPT's free tier. API access requires a paid OpenAI account, though inference platforms offer alternative access with usage-based pricing.
GPT-4 stands for Generative Pre-trained Transformer 4, the fourth generation of OpenAI's foundational language model series. The architecture was first described in OpenAI's research publication in March 2023.
OpenAI is gradually deprecating older GPT-4 snapshots (0314, 0613) as newer models supersede them. The GPT-4 family has been largely replaced by GPT-4o, GPT-4.1, and GPT-5 for new projects.
ChatGPT is the consumer product interface, while GPT-4 is the underlying language model. ChatGPT can use various models including GPT-4, GPT-4o, and GPT-5, and adds features like web browsing and tool use on top of the base model capabilities.
GPT stands for Generative Pre-trained Transformer, a neural network architecture that generates text by predicting the next token in a sequence. The "pre-trained" component refers to training on large text corpora before fine-tuning for specific tasks.
GPT-4 is accessible in ChatGPT's free tier with usage caps. For production workloads, the API is paid, and inference providers offer hosted access with their own pricing models.
