AI Model Intelligence

gpt-realtime-2

vercel/gpt-realtime-2

By vercel · family: gpt · released 2026-05-07

⚠ This is a community fine-tune or derivative — not an official vendor release.

$4.00
Input / 1M tokens
$24.00
Output / 1M tokens
Unknown
Context window
Unknown
Max output

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Capabilities

✗ Tool calling✗ Reasoning? Structured output✗ Attachments✗ Open weights✓ Temperature control
Modalities: input text, audio · output text, audio

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding1
  • Tool calling0/40
  • Structured output0/20
  • Reasoning0/10
  • Context window (100K → 1M)0/20
  • Provider availability1/10
Agents1
  • Tool calling0/35
  • Structured output0/25
  • Reasoning0/15
  • Output token limit0/15
  • Provider availability1/10
JSON / structured output10
  • Structured output / JSON mode0/50
  • Tool calling0/20
  • Temperature control10/10
  • Price-friendly for high-volume0/20
Cost efficiency31
  • Headline price (log-scaled)26/95
  • Has prompt-cache pricing5/5
Long context0
  • Context ≥ 100K0/100
Production-readiness35
  • Number of independent providers5/40
  • Has published per-token price20/20
  • Context window ≥ 8K0/15
  • No data inconsistencies across providers10/10
  • Official model (not derivative)0/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

ScenarioCostAssumption
RAG answer
per 1,000 RAG answers
$32.00
$0.03 per request
5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot.
Support ticket triage
per 10,000 tickets
$64.00
< $0.01 per request
1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support.
Data extraction
per 1,000 documents
$20.00
$0.02 per request
2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines.
Code review
per 1,000 PRs
$56.00
$0.06 per request
8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads.
Agent step
per 1,000 steps
$62.40
$0.06 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

Pricing detail

Recommended pricing from vercel · openai/gpt-realtime-2

$4.00
Input
$24.00
Output
$0.400
Cache read

Available on 1 providers

ProviderProvider model idInput / 1MOutput / 1MContextReleased
Vercel AI Gateway
vercel
openai/gpt-realtime-2$4.00$24.00Unknown2026-05-07

Frequently asked questions

How much does gpt-realtime-2 cost?

gpt-realtime-2 costs $4.00 per 1M input tokens and $24.00 per 1M output tokens, sourced from vercel. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.

Does gpt-realtime-2 support tool calling?

No. gpt-realtime-2 does not support tool calling (function calling). If your workflow requires it, look at the /capabilities/tool-calling list for alternatives.

Does gpt-realtime-2 support structured output / JSON mode?

Support for structured output / JSON-schema-constrained decoding is not reported for gpt-realtime-2 in our data source. Verify with vercel's official documentation before relying on it in production.

Can gpt-realtime-2 accept image input?

No. gpt-realtime-2 only accepts text, audio as input. If you need image input, see our /capabilities/vision list for current vision-capable models.

Is gpt-realtime-2 open-weight?

No. gpt-realtime-2 is a proprietary model — only vercel (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.

What are the best alternatives to gpt-realtime-2?

If gpt-realtime-2 doesn't fit, consider Kling v3.0 Motion Control, Kling v2.6 Image-to-Video, Kling v2.5 Turbo Text-to-Video. Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

Explore more

More vercel models

See also

Last updated:

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.