A streaming speech-to-text model that emits low-latency transcript deltas from live audio.
Technical Specifications
- Provider
- OpenAI
- Category
- lightweight
- Release Date
- 2026-05
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- $20 / month
- Reasoning Effort Control
- Fixed
- Structured Outputs
- No
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- gpt-realtime-whisper
- Supported SDK & API Protocol
- OpenAI Responses API & Chat Completions v1
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2028+)
- Production Rate Limits (RPM & TPM)
- 10,000 – 30,000 RPM (Tier 5 Enterprise) · 800,000 – 2,000,000 TPM
- Long-Context Pricing Tier (>128K / >200K)
- Flat rate ($0.006/1M in) across full 0K window
- Prompt Cache Write & TTL Policy
- Automatic prefix caching at $0/1M (no extra cache-write fee)
- Computer Use & Browser GUI Agent
- Text-only completion (No GUI action loop)
- MCP & Parallel Tool Calling
- Prompt-based JSON extraction only
- Web Search Grounding & Code Sandbox
- Native Web Search tool + Hosted Code Interpreter & File Search RAG
- Fine-Tuning & Distillation Support
- Supervised Fine-Tuning (SFT), Direct Preference (DPO) & Reinforcement Fine-Tuning (RFT)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token) · Audio (~25–32 tokens/sec)
- Weights Precision & Quantization
- Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster)
- Minimum GPU VRAM Requirement
- Zero Local VRAM Required (100% Serverless Cloud API)
- Supported Inference Engines
- Managed OpenAI Cloud API
- System Card & Safety Framework
- OpenAI Preparedness Framework Audited & System Card Published
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier
GPT Realtime Whisper Cost, Context, Hardware & API Integration
Pay-as-you-go API is cheaper for this volume (saves $19.82/mo vs $20 flat plan).
Break-even point: ~55,556 requests/day equals $20/month.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to GPT Realtime Whisper:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 36%
- GPQA Diamond
- 46%
- MMLU-Pro
- 66%
- HumanEval
- 82.5%
- Humanity's Last Exam
- 5.5%
- Terminal-Bench
- 23%
- SciCode
- 24.5%
- LiveCodeBench
- 39%
- AIME
- 46%
- Long-Context Reasoning
- 61%
- Chatbot Arena Elo
- 1255pts
Strengths
- Streaming transcription with very low latency
- Ideal for live captions and real-time agent input
- Priced per minute of audio rather than per token
- Emits transcript deltas with very low latency
Limitations & Trade-offs
- Speech-to-text only — no generation or reasoning
- Accuracy drops in very noisy environments
Editorial Assessment
The streaming counterpart to the batch Whisper models.
Best for: Live captions and real-time voice-agent transcription
Compare GPT Realtime Whisper
Frequently Asked Questions about GPT Realtime Whisper
How much does the GPT Realtime Whisper API cost per 1M tokens?+
GPT Realtime Whisper by OpenAI is priced at $0.006 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the GPT Realtime Whisper pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in GPT Realtime Whisper's context window?+
GPT Realtime Whisper features a 0K tokens context window, which equals approximately 336 English words or ~1 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 448 tokens.
Can I run GPT Realtime Whisper locally on my own GPU (Open Weights)?+
No, GPT Realtime Whisper is a proprietary closed-weights model hosted by OpenAI. It cannot be downloaded for local GPU execution and must be accessed via OpenAI's official API or cloud platform.
Does OpenAI train on data sent to the GPT Realtime Whisper API, and is commercial use allowed?+
API payloads are excluded from model training by default. License tier: Proprietary Commercial API (OpenAI Terms). Full commercial ownership of generated outputs. Supported deployment channels include: OpenAI Platform API, Microsoft Azure OpenAI Foundry.
How does GPT Realtime Whisper perform on coding and reasoning benchmarks?+
GPT Realtime Whisper achieves a composite Intelligence Index of 44/100, scoring 36% on SWE-bench Verified, 46% on GPQA Diamond, 66% on MMLU-Pro, and 1255 pts on Chatbot Arena Elo.
What is GPT Realtime Whisper best used for?+
GPT Realtime Whisper is best suited for: Live captions and real-time voice-agent transcription. Assessment: The streaming counterpart to the batch Whisper models.
OpenAI Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to OpenAI's flagship reasoning tier:
GPT-6 Astra
GPT-6.1 Sol
GPT-6 Sol
GPT-6 Luna
GPT-5.6 Sol
GPT-5.6 Terra
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to GPT Realtime Whisper:
The basic unit of text that a language model processes, typically representing about 3 to 4 English characters or roughly 0.75 words. For example, the sentence "Artificial intelligence is fast" breaks down into about 5 tokens.
A standardized evaluation suite used to objectively measure and rank an AI model's capabilities across specific tasks — such as SWE-bench Verified for software engineering, AIME for competitive math, or MMLU for general knowledge.
The maximum number of tokens a model can consider at once — both the input it reads and the output it writes. A 1,000,000-token context window can hold roughly 750,000 English words in a single request.
The neural network architecture introduced in 2017 that powers modern LLMs, using self-attention mechanisms to process all tokens in a sequence concurrently rather than sequentially.
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.
Sources: OpenAI Official Pricing & Technical Reports (Late 2026)↗