impulse

GPT Realtime 2.1 Mini

Frontier labRealtime
API id gpt-realtime-2.1-miniReleased 7 Jul 2026 (Jul 2026)
Input / 1M
$0.60
at OpenAI
Output / 1M
$2.40
at OpenAI
Context window
128K
tokens
Max output
32K
tokens per reply
Hosts
2
4 listings
Released
Jul 2026
7 Jul 2026

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.60$2.40
Cached input
90% off input
$0.06
Regional endpoints
10% more

What it costs a month

At OpenAI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$311
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$245
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$410
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$2,016
Use your own numbers

Where to run it

2 hosts serve GPT Realtime 2.1 Mini. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-realtime-2.1-mini
$0.60 / $2.40
gpt-realtime-2.1-mini
$0.60 / $2.40
Retires 25 Jun 2027
Show 2 more listings: regions, snapshots and variants
Azure OpenAI
2026-07-07
gpt-realtime-2.1-mini-2026-07-07
$0.60 / $2.40
Retires 25 Jun 2027
us
gpt-realtime-2.1-mini
$0.66 / $2.64
+10% vs headline
Retires 25 Jun 2027

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
AudioImagesText
Produces
AudioText
Features
Audio inputAudio outputParallel tool callsPrompt caching

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than OpenAI.

Smaller OpenAI models

No cheaper OpenAI model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

No cheaper open-weight match.

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-realtime-2.1-mini", input="Hello")
print(response.output_text)

Quick answers

How much does GPT Realtime 2.1 Mini cost?

On OpenAI, GPT Realtime 2.1 Mini costs $0.60 per million input tokens and $2.40 per million output tokens. Cached input costs $0.06 per million tokens.

Which APIs offer GPT Realtime 2.1 Mini?

GPT Realtime 2.1 Mini runs on 2 APIs: OpenAI and Azure OpenAI.

What is GPT Realtime 2.1 Mini's context window?

128K tokens, with up to 32K tokens in one reply.

Is GPT Realtime 2.1 Mini being retired?

Azure OpenAI retires it on 25 Jun 2027. 1 host keeps serving it.

When was GPT Realtime 2.1 Mini released?

OpenAI released it on 7 Jul 2026.

What is GPT Realtime 2.1 Mini's API model id?

Use gpt-realtime-2.1-mini with OpenAI.

Sources

Raw catalog entry for gpt-realtime-2.1-mini on OpenAI
{
  "cache_creation_input_audio_token_cost": 3e-7,
  "cache_read_input_audio_token_cost": 3e-7,
  "cache_read_input_image_token_cost": 8e-8,
  "cache_read_input_token_cost": 6e-8,
  "input_cost_per_audio_token": 0.00001,
  "input_cost_per_image_token": 8e-7,
  "input_cost_per_token": 6e-7,
  "litellm_provider": "openai",
  "max_input_tokens": 128000,
  "max_output_tokens": 32000,
  "mode": "realtime",
  "output_cost_per_audio_token": 0.00002,
  "output_cost_per_token": 0.0000024,
  "regional_processing_uplift_multiplier_eu": 1.1,
  "regional_processing_uplift_multiplier_us": 1.1,
  "source": "https://developers.openai.com/api/docs/pricing",
  "supported_endpoints": [
    "/v1/realtime"
  ],
  "supported_modalities": [
    "text",
    "image",
    "audio"
  ],
  "supported_output_modalities": [
    "text",
    "audio"
  ],
  "supports_audio_input": true,
  "supports_audio_output": true,
  "supports_function_calling": true,
  "supports_parallel_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_system_messages": true,
  "supports_tool_choice": true
}