Skip to content
Dashboard

GPT 5.2 Chat

GPT 5.2 Chat is the conversation-optimized variant of GPT-5.2, tuned for natural multi-turn dialogue with GPT-5.2 generation improvements in reasoning and instruction following.

File InputImplicit CachingTool UseVision (Image)Web Search
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'openai/gpt-5.2-chat',
prompt: 'Why is the sky blue?'
})

Playground

Try out GPT 5.2 Chat by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

openai logo
openai logo

GPT 5.2 Chat

Providers

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider
Context
Max Output
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
ZDR
No Training
Release Date
Azure
Legal:Terms
Privacy
128K16K
1.5s
62tps
$1.75/M
$14/M
Read:$0.17/M
Write:
$14/K
+ input costs
+2
12/11/2025
OpenAI
Legal:Terms
Privacy
128K16K
0.6s
83tps
$1.75/M
$14/M
Read:$0.17/M
Write:
$10/K
+ input costs
+2
12/11/2025
Throughput

P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.

Latency

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.

Uptime

Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.

More models by OpenAI

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
1.1M
1.5s
66tps
$5/M
$30/M
Read:
$0.5/M
Write:
$6.25/M
$10/K
+ input costs
+3
azure logo
bedrock logo
openai logo
07/09/2026
1.1M
1.3s
142tps
$1/M
$6/M
Read:
$0.1/M
Write:
$1.25/M
$10/K
+ input costs
+3
azure logo
bedrock logo
openai logo
07/09/2026
1M
0.5s
90tps
$5/M
$30/M
Read:
$0.5/M
Write:
$10/K
+ input costs
+3
azure logo
bedrock logo
openai logo
04/24/2026
1.1M
1.8s
72tps
$2.50/M
$15/M
Read:
$0.25/M
Write:
$10/K
+ input costs
+3
azure logo
openai logo
03/05/2026
400K
6.0s
144tps
$0.05/M
$0.40/M
Read:$0.01/M
Write:
$14/K
+ input costs
+3
azure logo
openai logo
08/07/2025
400K
5.3s
119tps
$0.25/M
$2/M
Read:$0.03/M
Write:
$14/K
+ input costs
+3
azure logo
openai logo
08/07/2025

About GPT 5.2 Chat

GPT 5.2 Chat was released on December 11, 2025 on AI Gateway as the conversational variant of the GPT-5.2 model family. It brings GPT-5.2 generational improvements to dialogue-optimized inference, producing more natural, coherent, and contextually aware conversations than previous chat-focused models.

The model excels at maintaining context across extended conversations, adapting tone and detail level to the conversation flow, and handling complex multi-turn interactions where previous statements inform later responses. It supports the context window of 128K tokens, function calling, and multimodal input, providing the full feature set needed for sophisticated chat applications.

If you're building premium conversational products, GPT 5.2 Chat combines the GPT-5.2 generation's broad improvements with specific optimization for chat workloads.

What To Consider When Choosing a Provider

  • Configuration: GPT 5.2 Chat combines GPT-5.2 generation improvements with optimization for multi-turn dialogue.
  • Configuration: While base GPT-5.2 is general-purpose, this variant specifically optimizes for conversational coherence, natural turn-taking, and tone adaptation.
  • Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
  • Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

When to Use GPT 5.2 Chat

Best for

  • Premium chat products: Consumer-facing conversational interfaces that demand the best available quality
  • Advanced virtual assistants: Multi-turn interactions with complex context tracking
  • Conversational commerce: Sales and support conversations that require nuanced understanding
  • Educational dialogue: Tutoring and learning experiences with sophisticated conversation management
  • Interactive storytelling: Narrative-driven conversational experiences with rich character and tone control

Consider alternatives when

  • Non-conversational tasks: Base GPT-5.2 for single-shot generation and structured processing
  • Cost-sensitive chat: GPT-5 mini or GPT-5 chat for more affordable conversational experiences
  • Coding conversations: GPT-5.2 codex for code-focused dialogue
  • Speed-critical chat: GPT-5.1 instant when response time outweighs quality ceiling

Conclusion

GPT 5.2 Chat brings GPT-5.2 generation quality to multi-turn dialogue on AI Gateway. For premium chat products where conversation quality is a differentiator, it is the dialogue-optimized variant of the GPT-5.2 family.