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.
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 It was superseded by GPT-4 Turbo (128K context) within months of its limited release.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.
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 | NVIDIA-NemotronLabs-VoiceChat-11B | speech to-speech | English | 8,192 | 11.1B | medium | openmdw-1.1 |
| 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 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 superseded the original GPT-4 for most applications.
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.
