Compare
Gpt 4o Audio Preview 2025 06 03 vs GPT-4o-mini Search 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 2025 06 03
Context window
128K
128,000 tokens · ~96K words
Model
GPT-4o-mini Search 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 2025 06 03 and GPT-4o-mini Search Preview have identical context windows (128K tokens). GPT-4o-mini Search Preview is 94% cheaper on input.
Quick verdicts
Short takeaways — validate with your own workloads.
RAG / high-volume retrieval
Use GPT-4o-mini Search 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 2025 06 03 | GPT-4o-mini Search 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 | Yes |
| Function calling | Yes | Yes |
| Extended thinking | No | No |
| Prompt caching | No | Yes |
| Batch API | Yes | Yes |
| Release date | N/A | Mar 2025 |
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 2025 06 03 in | Gpt 4o Audio Preview 2025 06 03 out | GPT-4o-mini Search Preview in | GPT-4o-mini Search Preview out |
|---|---|---|---|---|
| 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