low-costhigh-volumelong-context
GPT-5.6 model optimized for cost-sensitive, high-volume workloads.
by OpenAI1.05M context$0.080/M input standard price $0.200$0.480/M output standard price $1.204129ms latency161 t/s
OpenAI API pricing
Oxyy is an independent API gateway, not affiliated with OpenAI.
Paid OpenAI text models run from $0.040 to $5.00 per 1M input tokens and $0.200 to $30.00 per 1M output tokens. GPT-6 Sol costs $0.800 input / $4.00 output per 1M tokens, pay-as-you-go (standard price $2.00 / $10.00). The lowest-priced paid OpenAI text model is GPT-6 Luna at $0.040 input / $0.200 output per 1M tokens.
Prices checked daily · last price change Sep 24, 2026 (discount changed: 70% → 60% off)
OpenAI API pricing per 1M tokens
| Model | Context | Input | Output | Cached input | Saving | Released |
|---|---|---|---|---|---|---|
| GPT-5.5 (long prompts cost more, see note)gpt-5.5 | 1.05M | Standard price $5.00, on Oxyy $2.00 | Standard price $30.00, on Oxyy $12.00 | $0.200 | 60% | Apr 24, 2026 |
| GPT-5.4 minigpt-5.4-mini | 400K | Standard price $0.750, on Oxyy $0.300 | Standard price $4.50, on Oxyy $1.80 | $0.030 | 60% | — |
| GPT-4o minigpt-4o-mini | 128K | Standard price $0.150, on Oxyy $0.060 | Standard price $0.600, on Oxyy $0.240 | $0.030 | 60% | — |
| GPT-6 Sol (long prompts cost more, see note)gpt-6-sol | 1.05M | Standard price $2.00, on Oxyy $0.800 | Standard price $10.00, on Oxyy $4.00 | $0.080 | 60% | — |
| GPT-5.6 Luna (long prompts cost more, see note)gpt-5.6-luna | 1.05M | Standard price $0.200, on Oxyy $0.080 | Standard price $1.20, on Oxyy $0.480 | $0.008 | 60% | — |
| GPT-5.6 Sol (long prompts cost more, see note)gpt-5.6-sol | 1.05M | Standard price $4.00, on Oxyy $1.60 | Standard price $20.00, on Oxyy $8.00 | $0.160 | 60% | — |
| GPT-Image-2.5 Flaregpt-image-2.5-flare | — | Standard price $5.00, on Oxyy $2.00 | Standard price $30.00, on Oxyy $12.00 | $0.500 | 60% | Sep 8, 2026 |
| GPT-Image-2.5 Sunburstgpt-image-2.5-sunburst | — | Standard price $5.00, on Oxyy $2.00 | Standard price $30.00, on Oxyy $12.00 | $0.500 | 60% | Sep 8, 2026 |
| GPT-5.6 Terra (long prompts cost more, see note)gpt-5.6-terra | 1.05M | Standard price $2.00, on Oxyy $0.800 | Standard price $12.00, on Oxyy $4.80 | $0.080 | 60% | — |
| GPT Image 2gpt-image-2 | — | Standard price $2.50, on Oxyy $1.00 | Standard price $15.00, on Oxyy $6.00 | $0.250 | 60% | Apr 21, 2026 |
| GPT-6 Astra (long prompts cost more, see note)gpt-6-astra | 1.05M | Standard price $10.00, on Oxyy $4.00 | Standard price $50.00, on Oxyy $20.00 | $0.400 | 60% | — |
| chat-latestchat-latest | — | Standard price $5.00, on Oxyy $2.00 | Standard price $30.00, on Oxyy $12.00 | $0.200 | 60% | — |
| GPT-4ogpt-4o | 128K | Standard price $2.50, on Oxyy $1.00 | Standard price $10.00, on Oxyy $4.00 | $0.500 | 60% | — |
| GPT-5.1gpt-5.1 | 400K | Standard price $1.25, on Oxyy $0.500 | Standard price $10.00, on Oxyy $4.00 | $0.050 | 60% | — |
| GPT-5.2gpt-5.2 | 400K | Standard price $1.75, on Oxyy $0.700 | Standard price $14.00, on Oxyy $5.60 | $0.070 | 60% | — |
| GPT-5.3 Codexgpt-5.3-codex | — | Standard price $1.75, on Oxyy $0.700 | Standard price $14.00, on Oxyy $5.60 | $0.070 | 60% | — |
| GPT-5.6 Cyber (Daybreak Red)gpt-5.6-cyber | — | Standard price $12.50, on Oxyy $5.00 | Standard price $75.00, on Oxyy $30.00 | $0.500 | 60% | — |
| GPT-6 Luna (long prompts cost more, see note)gpt-6-luna | 1.05M | Standard price $0.100, on Oxyy $0.040 | Standard price $0.500, on Oxyy $0.200 | $0.004 | 60% | — |
| GPT-Realtime-2.1gpt-realtime-2.1 | — | Standard price $4.00, on Oxyy $1.60 | Standard price $24.00, on Oxyy $9.60 | $0.160 | 60% | — |
| GPT-Realtime-2.1 Minigpt-realtime-2.1-mini | — | Standard price $0.600, on Oxyy $0.240 | Standard price $2.40, on Oxyy $0.960 | $0.024 | 60% | — |
| Text Embedding 3 Largetext-embedding-3-large | 8K | Standard price $0.130, on Oxyy $0.052one rate for input and output | — | 60% | — | |
| Text Embedding 3 Smalltext-embedding-3-small | 8K | Standard price $0.020, on Oxyy $0.008one rate for input and output | — | 60% | — | |
| Text Embedding Ada 002text-embedding-ada-002 | 8K | Standard price $0.100, on Oxyy $0.040one rate for input and output | — | 60% | — | |
| gpt-oss-120bgpt-oss-120b | 131K | Not yet priced | — | Aug 5, 2025 | ||
| gpt-oss-20bgpt-oss-20b | 131K | Not yet priced | — | Aug 5, 2025 | ||
| GPT-Realtime-1.5gpt-realtime-1.5 | — | Not yet priced | — | — | ||
| GPT-Realtime-2gpt-realtime-2 | — | Not yet priced | — | — | ||
- † Long prompts cost more. The whole request is billed at the higher rate:
- GPT-5.5: $4.00 input / $18.00 output per 1M tokens once a prompt goes over 272K tokens.
- GPT-6 Sol: $1.60 input / $6.00 output per 1M tokens once a prompt goes over 272K tokens.
- GPT-5.6 Luna: $0.160 input / $0.720 output per 1M tokens once a prompt goes over 272K tokens.
- GPT-5.6 Sol: $3.20 input / $12.00 output per 1M tokens once a prompt goes over 272K tokens.
- GPT-5.6 Terra: $1.60 input / $7.20 output per 1M tokens once a prompt goes over 272K tokens.
- GPT-6 Astra: $8.00 input / $30.00 output per 1M tokens once a prompt goes over 272K tokens.
- GPT-6 Luna: $0.080 input / $0.300 output per 1M tokens once a prompt goes over 272K tokens.
- The standard price is Oxyy's list price for the model before any discount. OpenAI publishes its own prices on its pricing page.
OpenAI speech, transcription and realtime voice pricing
| Model | Type | Price | Saving | Released |
|---|---|---|---|---|
| TTS-1tts-1 | Text to speech | Standard price $0.015, on Oxyy $0.006per 1K characters | 60% | Nov 6, 2023 |
| TTS-1 HDtts-1-hd | Text to speech | Standard price $0.030, on Oxyy $0.012per 1K characters | 60% | Nov 6, 2023 |
| GPT-Live 1gpt-live-1 | Realtime voice | Standard price $0.050, on Oxyy $0.020per minute of input | 60% | — |
| GPT-Live-Transcribegpt-live-transcribe | Speech to text | Standard price $0.017, on Oxyy $0.0068per minute of audio | 60% | — |
| GPT-Realtime-Translategpt-realtime-translate | Speech to text | Standard price $0.034, on Oxyy $0.014per minute of audio | 60% | — |
| GPT-Realtime-Whispergpt-realtime-whisper | Speech to text | Standard price $0.017, on Oxyy $0.0068per minute of audio | 60% | — |
| GPT-Transcribegpt-transcribe | Speech to text | Standard price $0.0045, on Oxyy $0.0018per minute of audio | 60% | — |
| GPT-4o Mini TTSgpt-4o-mini-tts | Text to speech | Not yet priced | — | — |
| Whisper large-v3whisper-large-v3 | Speech to text | Not yet priced | — | — |
| Whisper large-v3-turbowhisper-large-v3-turbo | Speech to text | Not yet priced | — | — |
Recent OpenAI price changes
| Date | Model | Change |
|---|---|---|
| Sep 24, 2026 | 16 models | Discount changed: 70% → 60% off |
| Sep 22, 2026 | 10 models | Discount started: 70% off |
OpenAI API cost calculator
Estimate a month of OpenAI API usage: set your input and output volume and how much of your input is a repeated prompt prefix served from cache, or start from a preset.
Estimated monthly cost for 10M input and 2M output tokens, with 0% of input served from cache.
| OpenAI model | At standard price | On Oxyy | You save |
|---|---|---|---|
| GPT-6 Sol (estimate is a lower bound, see note) | $40.00 | $16.00 | $24.00 (60%) |
| GPT-5.6 Luna (estimate is a lower bound, see note) | $4.40 | $1.76 | $2.64 (60%) |
| GPT-5.6 Sol (estimate is a lower bound, see note) | $80.00 | $32.00 | $48.00 (60%) |
| GPT-5.6 Terra (estimate is a lower bound, see note) | $44.00 | $17.60 | $26.40 (60%) |
| GPT-6 Astra (estimate is a lower bound, see note) | $200.00 | $80.00 | $120.00 (60%) |
| chat-latest | $110.00 | $44.00 | $66.00 (60%) |
| GPT-5.2 | $45.50 | $18.20 | $27.30 (60%) |
| GPT-5.3 Codex | $45.50 | $18.20 | $27.30 (60%) |
- † A lower bound: prompts past the model's long-context threshold are billed at a higher rate (see the table above).
Which OpenAI model should you use?
For each kind of work, the lowest-priced paid OpenAI model tagged for it and the one developers use most on Oxyy.
| Need | Lowest price | Most used on Oxyy |
|---|---|---|
| Coding | GPT-6 Luna$0.040 / $0.200 per 1M tokens | GPT-5.6 Sol |
| Reasoning | GPT-6 Luna$0.040 / $0.200 per 1M tokens | GPT-5.6 Sol |
| Agents and tool use | GPT-6 Luna$0.040 / $0.200 per 1M tokens | GPT-5.6 Sol |
| Long documents | GPT-6 Luna$0.040 / $0.200 per 1M tokens | GPT-5.6 Luna |
| Lowest cost | GPT-6 Luna$0.040 / $0.200 per 1M tokens | GPT-5.6 Luna |
OpenAI API pricing FAQ
How much does the OpenAI API cost?
On Oxyy, GPT-6 Sol costs $0.800 input / $4.00 output per 1M tokens at the pay-as-you-go price (standard price $2.00 / $10.00). Across paid OpenAI text models, input runs from $0.040 to $5.00 per 1M tokens and output from $0.200 to $30.00. Speech to text starts at $0.0018 per minute of audio, text to speech starts at $0.006 per 1K characters and realtime voice starts at $0.020 per minute of input. There is no subscription: you pay only for what you use.
What is the cheapest OpenAI model?
GPT-6 Luna is the lowest-priced paid OpenAI text model on Oxyy, at $0.040 input / $0.200 output per 1M tokens.
How much does cached input cost on OpenAI models?
Cached input on GPT-6 Sol costs $0.080 per 1M tokens on Oxyy, against $0.800 for regular input. Writing to the cache costs $1.00 per 1M tokens. The price table on this page lists the cache rate of every model that has one.
Can I call OpenAI models with the OpenAI SDK?
Yes. Oxyy's API is OpenAI-compatible: set the base URL to https://api.oxyy.ai/v1, use your Oxyy API key and pass the model id, for example "gpt-6-sol", to /v1/chat/completions. Image models use /v1/images/generations, text-to-speech models use /v1/audio/speech, transcription models use /v1/audio/transcriptions and embedding models use /v1/embeddings.
Do long prompts cost more on OpenAI models?
For some models, yes. GPT-6 Sol costs $1.60 input / $6.00 output per 1M tokens once a prompt goes over 272K tokens, instead of $0.800 / $4.00; the whole request is priced at the higher rate.
Is Oxyy affiliated with OpenAI?
No. Oxyy is an independent API gateway, not affiliated with or endorsed by OpenAI. It gives you one API key and one bill for models from many AI labs, OpenAI among them.
OpenAI tokens processed on Oxyy· daily, UTC
All OpenAI models 37
reasoningcodingagenticlong-context
Flagship model for complex professional work.
by OpenAI1.05M context$1.60/M input standard price $4.00$8.00/M output standard price $20.004414ms latency1636 t/s
image-generationimage-editinginpaintingtransparency4k+1 more
Fast, high-quality everyday image generation and editing.
by OpenAISep 8, 2026$2.00/M input standard price $5.00$12.00/M output standard price $30.0020.0s latency
image-generationimage-editinginpaintingtransparency4k+1 more
OpenAI's most capable image generation and editing model, for premium workflows needing tight control across detailed, iterative edits.
by OpenAISep 8, 2026$2.00/M input standard price $5.00$12.00/M output standard price $30.0023.0s latency
reasoningcodingbalancedlong-context
GPT-5.6 model that balances intelligence and cost.
by OpenAI1.05M context$0.800/M input standard price $2.00$4.80/M output standard price $12.004704ms latency192 t/s
image-generationimage-editinginpainting4ktext-rendering
OpenAI's image generation and editing model with flexible, near-arbitrary output resolutions up to 4K and automatic high-fidelity handling of reference images.
by OpenAIApr 21, 2026$1.00/M input standard price $2.50$6.00/M output standard price $15.0015.5s latency
reasoningcodingagenticlong-context
OpenAI's most capable model, built for the hardest end-to-end work.
by OpenAI1.05M context$4.00/M input standard price $10.00$20.00/M output standard price $50.001882ms latency
text-to-speechsteerable
Text-to-speech model powered by GPT-4o Mini, with an instructions parameter for tone and style steering.
by OpenAINot yet priced4180ms latency
Text-to-speech model optimized for realtime, low-latency use.
by OpenAINov 6, 2023$0.006 per 1K characters standard price $0.0151819ms latency
Text-to-speech model optimized for audio quality. Double the price of tts-1.
by OpenAINov 6, 2023$0.012 per 1K characters standard price $0.0302957ms latency
Flagship model for the most complex professional work, coding and reasoning.
by OpenAIApr 24, 20261.05M context$2.00/M input standard price $5.00$12.00/M output standard price $30.00
open-weightsreasoningagenticlocal-inferenceapache-2.0
OpenAI's most powerful open-weight model, for production, general-purpose, high-reasoning use. Achieves near-parity with OpenAI o4-mini on core reasoning benchmarks.
by OpenAIAug 5, 2025131K contextNot yet priced
open-weightsreasoningagenticlocal-inferenceapache-2.0
Smaller open-weight model for lower latency, local and specialized use. Delivers results similar to OpenAI o3-mini on common benchmarks.
by OpenAIAug 5, 2025131K contextNot yet priced
chatrolling-alias
The model currently powering ChatGPT, exposed through the API. A rolling alias whose underlying snapshot changes over time.
by OpenAI$2.00/M input standard price $5.00$12.00/M output standard price $30.00
Versatile, high-intelligence GPT model. Accepts text and image input and produces text, including Structured Outputs.
by OpenAI128K context$1.00/M input standard price $2.50$4.00/M output standard price $10.00
Fast, affordable small model for focused tasks. Text and image input, text output.
by OpenAI128K context$0.060/M input standard price $0.150$0.240/M output standard price $0.600
GPT-5.1 reasoning model with a no-reasoning default for fast responses.
by OpenAI400K context$0.500/M input standard price $1.25$4.00/M output standard price $10.00
Previous flagship model for complex professional work.
by OpenAI400K context$0.700/M input standard price $1.75$5.60/M output standard price $14.00
codingagentic
OpenAI's Codex model, optimized for agentic coding workflows.
by OpenAI$0.700/M input standard price $1.75$5.60/M output standard price $14.00
OpenAI's strongest mini model for coding, computer use and subagents.
by OpenAI400K context$0.300/M input standard price $0.750$1.80/M output standard price $4.50
cybersecurityvulnerability-researchrestricted-access
OpenAI's most advanced cybersecurity model, for authorized vulnerability research and security testing.
by OpenAI$5.00/M input standard price $12.50$30.00/M output standard price $75.00
reasoningcodingagenticlong-context
OpenAI's most efficient model for focused, high-volume tasks.
by OpenAI1.05M context$0.040/M input standard price $0.100$0.200/M output standard price $0.500
reasoningcodingagenticlong-context
Built for complex coding and agentic workflows.
by OpenAI1.05M context$0.800/M input standard price $2.00$4.00/M output standard price $10.00
voicerealtimespeech-to-speech
OpenAI's premier model for natural, expressive voice conversations with smooth interruption handling.
by OpenAI$0.020 per minute of input standard price $0.050
speech-to-textrealtimelow-latency
Low-latency speech-to-text model for realtime transcription. The recommended replacement for whisper-1 in live transcription.
by OpenAI$0.0068 per minute of audio standard price $0.017
realtimevoice
Voice model for audio in, audio out.
by OpenAINot yet priced
realtimevoice
Realtime reasoning model with tool use. Previous generation to GPT-Realtime-2.1.
by OpenAINot yet priced
realtimevoicespeech-to-speech
Realtime reasoning model with tool use for speech-to-speech agents.
by OpenAI$1.60/M input standard price $4.00$9.60/M output standard price $24.00
realtimevoicelow-cost
Cost-efficient realtime reasoning model with tool use.
by OpenAI$0.240/M input standard price $0.600$0.960/M output standard price $2.40
translationrealtimespeech-to-speech
Streaming speech-to-speech translation model.
by OpenAI$0.014 per minute of audio standard price $0.034
speech-to-textrealtimestreaming
Streaming speech-to-text model for realtime transcription.
by OpenAI$0.0068 per minute of audio standard price $0.017
speech-to-texttranscription
High-accuracy speech-to-text model for file and Realtime input transcription. The recommended replacement for whisper-1 file transcription.
by OpenAI$0.0018 per minute of audio standard price $0.0045
embeddingragsemantic-search
OpenAI's best performing embedding model, with up to 3072 dimensions.
by OpenAI8K context$0.052 per 1M tokens standard price $0.130
embeddingragsemantic-search
Improved, more performant replacement for the ada embedding model.
by OpenAI8K context$0.008 per 1M tokens standard price $0.020
embeddingragsemantic-search
Previous-generation embedding model. Superseded but explicitly NOT deprecated.
by OpenAI8K context$0.040 per 1M tokens standard price $0.100
speech-to-textopen-weightstranscriptionmultilinguallocal-inference
Third-generation large Whisper model for multilingual speech recognition and translation.
by OpenAINot yet priced
speech-to-textopen-weightstranscriptionmultilinguallocal-inference
Fine-tuned, pruned version of large-v3 with the decoder cut from 32 layers to 4, for much faster inference at a small quality cost.
by OpenAINot yet priced