GPT-5.2

GitHub Copilot chat

GPT-5.2 is a GitHub Copilot chat model.It supports a 128,000-token context windowwith up to 64,000 output tokens. Capabilities include function calling, vision. Route GPT-5.2 via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.

Pricing source: unknown Last verified: Aug 6, 2026 View source ↗
Pricing not yet public

We don't have verified per-token pricing for GPT-5.2 yet. If you have a source from GitHub Copilot's documentation, help us add it — your submission gets reviewed within 48 hours.

Pricing

Per-token rates, expressed in USD per 1M tokens. Verified Aug 6, 2026.

Input —
Output —

Context & limits

Context window
128,000 tokens
Max input
128,000 tokens
Max output
64,000 tokens
Modalities
vision, text

Capabilities

  • Function calling ✓ supported
  • Parallel tool calls ✓ supported
  • Vision input ✓ supported
  • Audio input — not advertised
  • Audio output — not advertised
  • PDF input — not advertised
  • Streaming ✓ supported
  • Structured output ✓ supported
  • Prompt caching — not advertised
  • Reasoning — not advertised

Strengths & caveats — when to pick GPT-5.2

Data-driven from GPT-5.2's percentile within chat peers.

Where it's strong

  • +parallel tool calls — only 18% of chat models on Future AGI advertise this

Watch out for

  • No major caveats flagged from public spec.

Benchmark scores

Reported public benchmark numbers. Each row links to the source. Faded bar shows 6-peer average for context.

AIME 2025math· no tools
Captured Aug 8, 2026
τ-benchagent· Tau2-bench Telecom
Captured Jun 2, 2026
Arena ELO (coding)code· style control↑3% vs peers
Captured Oct 20, 2026
GPQA Diamondreasoning· no tools↑16% vs peers
Captured Aug 8, 2026
Chatbot Arena ELOgeneral· style control↑4% vs peers
Captured Oct 20, 2026
MMLUgeneral
Captured Aug 8, 2026
Captured Oct 19, 2026
ARC-AGIreasoning· Verified
Captured Aug 8, 2026
τ-bench (retail)agent· Tau2-bench Retail
Captured Jun 2, 2026
SWE-bench Verifiedagent↑7% vs peers
Captured Aug 8, 2026
MMMU-Promultimodal· no tools
Captured Aug 8, 2026
Captured Oct 19, 2026
SWE-benchagent· Public
Captured Aug 8, 2026
ARC-AGI-2reasoning· Verified
Captured Aug 8, 2026
FrontierMathmath· Tier 1-3; w/ Python
Captured Aug 8, 2026
Humanity's Last Examreasoning· no tools
Captured Aug 8, 2026
Try it

Call GPT-5.2 via Agent Command Center

One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.

SDK
Native Future AGI client (agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.
# GPT-5.2 via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC

client = AgentCC(
    api_key=os.environ["AGENTCC_API_KEY"],   # from app.futureagi.com → Settings → API Keys
    base_url="https://gateway.futureagi.com/v1",
)

resp = client.chat.completions.create(
    model="github-copilot/gpt-5-2",
    messages=[{"role": "user", "content": "Hello, GPT-5.2!"}],
)

print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")

# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
    model="github-copilot/gpt-5-2",
    messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost:   ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache:  ", raw.headers.get("x-agentcc-cache"))
Set AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗
Advanced: fallback + cache config (YAML) ▸
strategy: cost-optimized
targets:
  - model: gpt-5-2
    provider: github-copilot
    weight: 80
fallbacks:
  - model: claude-opus-4-7
    provider: azure-ai-foundry
  - model: claude-opus-4-7-20260416
    provider: anthropic
guardrails: [pii, prompt-injection, secrets]
cache: { exact: true, semantic: true }

Same model on other providers

gpt-5-2 is also available via 2 other routes. Pricing, regions, and capabilities can differ — compare before routing production traffic.

ProviderInput / 1MOutput / 1MVerified
Azure OpenAI$1.75/M$14.00/MOct 22, 2026
OpenAI$1.75/M$14.00/MOct 22, 2026

Explore similar models

Grouped by Chatbot Arena tier (GPT-5.2 sits at 1435 ELO). Side-by-side links appear where a comparison page exists; otherwise, open the model profile.

FAQ

How much does GPT-5.2 cost?

Public per-token pricing for GPT-5.2 is not yet published. Submit a source on this page to help us add it.

What is the context window of GPT-5.2?

GPT-5.2 supports a 128,000-token context window with up to 64,000 output tokens.

Does GPT-5.2 support function calling?

Yes — GPT-5.2 supports function (tool) calling, including parallel tool calls.

Is GPT-5.2 good for production?

GPT-5.2 is well-suited for parallel tool calls — only 18% of chat models on Future AGI advertise this.

How can I route to GPT-5.2 with fallback?

Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.

Useful links for GPT-5.2

Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.