Compare
Gpt 4o Audio Preview 2024 12 17 vs Gpt 4o Mini Audio Preview
This page is context-first: how much text each model can take in one request. Full specs adds capabilities and limits; the pricing matrix below is only about $/million tokens from hosts that list both models.
Model
Gpt 4o Audio Preview 2024 12 17
Context window
128K
128,000 tokens · ~96K words
Model
Gpt 4o Mini Audio Preview
Context window
128K
128,000 tokens · ~96K words
Context window · side by side
Bar length is relative to the larger of the two windows (100% = max of this pair). This is not pricing.
Same context window size for both models.
Gpt 4o Audio Preview 2024 12 17 and Gpt 4o Mini Audio Preview have identical context windows (128K tokens). Gpt 4o Mini Audio Preview is 94% cheaper on input.
Quick verdicts
Short takeaways — validate with your own workloads.
RAG / high-volume retrieval
Use Gpt 4o Mini Audio Preview. Input tokens are 94% cheaper — critical when sending large retrieved contexts.
Full specs
Context, output, capabilities, and dates. Green highlights the favorable value where we compute a winner.
| Spec | Gpt 4o Audio Preview 2024 12 17 | Gpt 4o Mini Audio Preview |
|---|---|---|
| Context window | 128,000 tokens (128K) | 128,000 tokens (128K) |
| Max output tokens | 16,384 tokens (16K) | 16,384 tokens (16K) |
| Speed tier | Balanced | Fast |
| Vision | No | No |
| Function calling | Yes | Yes |
| Extended thinking | No | No |
| Prompt caching | No | No |
| Batch API | Yes | Yes |
| Release date | N/A | N/A |
Pricing matrix
Dollar rates only: hosts that list both models, per 1M tokens. For how much text fits, use the context section above — not this table.
| Provider | Gpt 4o Audio Preview 2024 12 17 in | Gpt 4o Audio Preview 2024 12 17 out | Gpt 4o Mini Audio Preview in | Gpt 4o Mini Audio Preview out |
|---|---|---|---|---|
| Azure | $2.50/M | $10.00/M | — | — |
| Openai | $2.50/M | $10.00/M | $0.150/M | $0.600/M |
Frequently asked questions
Powered by Mem0
Use a smaller model.
Get better results.
Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.
Example: a multi-turn chat session
80% less to send — works with any model