The feed lists audio in and audio out. OpenRouter describes GPT Audio as OpenAI's generally available audio model, with a decoder aimed at more natural speech. Use it when the product has to talk back, not only transcribe. GPT Audio is listed at $2.50 input and $10.00 output per million tokens, with a 128,000-token context window. In: audio, text. Out: audio, text. Tools: Yes. Open weights: No public weights id listed.
Tools: Yes.
in audio
in text
out audio
out text
tools
Facts
Facts for GPT Audio. OpenRouter models API, checked 20 Nov 2026.
Fact
Value
Source
Release date
19 Jan 2026
OpenRouter field created. This is the listing date the feed publishes. Checked 20 Nov 2026.
Context window
128,000 tokens
OpenRouter field context_length. Checked 20 Nov 2026.
Max output
16,384 tokens
OpenRouter field top_provider.max_completion_tokens. Checked 20 Nov 2026.
Input price
$2.50 per million tokens. Published per-token rate 0.0000025.
OpenRouter field pricing.prompt, USD per token, multiplied by 1,000,000. Checked 20 Nov 2026.
Output price
$10.00 per million tokens. Published per-token rate 0.00001.
OpenRouter field pricing.completion, USD per token, multiplied by 1,000,000. Checked 20 Nov 2026.
Batch input price
No batch route listed
Sibling OpenRouter id ending in :batch, field pricing.prompt. Checked 20 Nov 2026.
Batch output price
No batch route listed
Sibling OpenRouter id ending in :batch, field pricing.completion. Checked 20 Nov 2026.
Input modalities
audio, text
OpenRouter field architecture.input_modalities. Checked 20 Nov 2026.
Output modalities
audio, text
OpenRouter field architecture.output_modalities. Checked 20 Nov 2026.
Tools
Yes
OpenRouter field supported_parameters contains tools. Checked 20 Nov 2026.
Open weights
No public weights id listed
OpenRouter field hugging_face_id. Empty means no public weights id is listed, which is not a legal opinion. Checked 20 Nov 2026.
Knowledge cutoff
Unknown
OpenRouter field knowledge_cutoff. Checked 20 Nov 2026.
Reasoning
Unknown
OpenRouter field reasoning. Missing means unknown, not unsupported. Checked 20 Nov 2026.
Other published prices
audio: 0.000032 USD audio_output: 0.000064 USD
Other OpenRouter pricing fields, shown raw. The documented unit is USD per token, request, or unit — not converted to per million. Checked 20 Nov 2026.
A $0 token price does not mean the model is free to use. Another published price field is non-zero and may be the one you are billed on.
Listing blurb
The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...
No third-party index was included for this model in the feed. The Best Model For does not fill that gap.
Guide note · 19 Nov 2026
The feed lists audio in and audio out. OpenRouter describes GPT Audio as OpenAI's generally available audio model, with a decoder aimed at more natural speech. Use it when the product has to talk back, not only transcribe.
A support line or a language drill that must reply out loud needs audio output. Listen to a sample before you commit. Token rates are not the whole voice bill if a provider also meters audio time.
GPT Audio is listed at $2.50 input and $10.00 output per million tokens, with a 128,000-token context window.
Read a messy voicemail and reply in a steady voice
Audio in plus audio out covers both sides of that job in one model family.
GPT Audio is listed at $2.50 input and $10.00 output per million tokens, with a 128,000-token context window.
The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.
GPT Audio is listed at $2.50 input and $10.00 output per million tokens, with a 128,000-token context window. No batch route is listed. Other price fields, if any, are on this page and are not converted.
Does GPT Audio have open weights?
No public weights id is listed on the OpenRouter row. The Best Model For does not treat that as a legal claim that weights do not exist anywhere.
What is GPT Audio good for?
The feed lists audio in and audio out. OpenRouter describes GPT Audio as OpenAI's generally available audio model, with a decoder aimed at more natural speech. Use it when the product has to talk back, not only transcribe.