This variant extended GPT-4's context window to 32,768 tokens at twice the per-token cost of standard GPT-4, making it the most expensive chat model OpenAI offered. Access remained restricted behind a separate waitlist even after GPT-4 API access was broadly available in July 2023, and it was effectively made obsolete by GPT-4 Turbo's 128K context at a lower price point four months later.
Discover the power and diversity of large language models available with Telnyx. Explore the options below to find the perfect model for your project.
Check out our helpful tools to help get you started.
GPT-4 32K extends the standard 8K context window to 32,768 tokens for processing longer documents. The underlying model is identical, with the larger context being the only difference.
GPT-4 32K on Azure costs $60 per million input tokens and $120 per million output tokens. Inference providers offer alternative access with their own pricing.
OpenAI is retiring older GPT-4 snapshots as newer models offer better performance at lower cost. GPT-4o, GPT-4.1, and GPT-5 have for most applications.
GPT-4 32k shares the same 86.4% MMLU (5-shot) and 8.99 MT-Bench scores as the standard GPT-4 on the sheet, differing only in its 32,768-token context window. The 32k variant was one of the rarest OpenAI models, restricted behind a separate waitlist even after GPT-4 API access opened broadly. It was superseded by GPT-4 Turbo (128K context) within months of its limited release.
Running GPT-4 32k through Telnyx Inference costs $60.00 per million input tokens and $120.00 per million output tokens. Processing 100,000 long documents at 20,000 tokens each would cost approximately $120,000 input plus $240,000 output. GPT-4 Turbo ($10/$30 per million tokens) on the same sheet offers 4x the context window at one-sixth the cost.
| 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 |
| Telnyx | DeepSeek-V4.1-Flash-1017 | text generation | English | 1,048,576 | 552.0B | small | mit |
| 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 |
| minimaxai | MiniMax-M3-MXFP8 | text generation | Multilingual | 1,000,000 | 428.0B | small | minimax-community |
| 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 |
| moonshotai | Kimi-K3.1-Pro | text generation | English | 1,000,000 | 2.8B | large | kimi-k3.1-pro |
| nvidia | NVIDIA-NemotronLabs-VoiceChat-11B | speech to-speech | English | 8,192 | 11.1B | medium | openmdw-1.1 |
| openai | gpt-oss-120b | text generation | Multilingual | 131,072 | 117.0B | small | apache-2.0 |
| poolside | Laguna-S-2.1 | text generation | English | 1,048,576 | 117.6B | small | OpenMDW-1.1 |
| Telnyx | Qwen3.8-27B | text generation | English | 262,144 | 27.0B | small | Apache 2.0 |
| 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-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-5.2 | 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-6-luna | text generation | Multilingual | 1,050,000 | 0 | large | openai |
| openai | gpt-live-1 | speech to-speech | Multilingual | 400,000 | 0 | large | openai |
GPT-4 128K refers to GPT-4 Turbo, which expanded the context window from 32K to 128,000 tokens. It also added JSON mode and reduced pricing compared to GPT-4 32K.
GPT-4 32K has been superseded by GPT-4 Turbo (128K), GPT-4o, and GPT-4.1 (1M context). Unless you have specific version requirements, newer models offer better performance at lower cost.
GPT-4 Turbo offers a 128K context window at roughly one-third the price of GPT-4 32K, with additional features like JSON mode. GPT-4 Turbo is the clear upgrade for applications using GPT-4 32K.
