← All models

gpt-5.2

github_copilot · chat model

gpt-5.2 is listed here as a chat model from github_copilot. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.

Input
N/A
Output
N/A
Cached input
N/A
Context
64.0K

Quick read

Best for

Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.

Things to verify

Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.

Pricing

Item Price

Token limits

Context window
64.0K
Max input tokens
128.0K
Max output tokens
64.0K
Max tokens
64.0K

Capabilities

Capability Supported
Vision
Function calling
Parallel function calling
Tool choice
Prompt caching
Reasoning
Response schema
System messages
Audio input
Audio output
Web search
PDF input
Video input

Benchmarks

Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer

Benchmark Score Metric Scope Checked Source
GDPval 70.9% wins or ties (%) Base model: gpt-5.2 (GPT-5.2 Thinking) 2026-05-31 Link
SWE-bench Pro 55.6% accuracy (%) Base model: gpt-5.2 (GPT-5.2 Thinking) 2026-05-31 Link
AIME 2025 100.0% accuracy (%) Base model: gpt-5.2 (GPT-5.2 Thinking) 2026-05-31 Link

Sources

Source links
Pricing data LiteLLM model cost map
Synced at 2026-05-28

Docs

Official docs

Similar models

This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.

Comparing from
Model Cost Input shape Features Context Why it is close
gpt-5.2
github_copilot
In N/A
Out N/A
imagetext
Output: text
VisionFunction callingParallel function callingResponse schema
64.0K
Current model
Reference row

Overall blends cost, modality overlap, capabilities, and context.

Model Cost Input shape Features Context Why it is close
gpt-5-mini
github_copilot
In N/A
Out N/A
imagetext
Output: text
VisionFunction callingParallel function callingResponse schema
64.0K
Same provider
Overall 80%
gpt-5.1
github_copilot
In N/A
Out N/A
imagetext
Output: text
VisionFunction callingParallel function callingResponse schema
64.0K
Same provider
Overall 80%
gpt-5
github_copilot
In N/A
Out N/A
imagetext
Output: text
VisionFunction callingParallel function callingResponse schema
128.0K
Same provider
Overall 73%
gpt-4.1
github_copilot
In N/A
Out N/A
imagetext
Output: text
VisionFunction callingParallel function callingResponse schema
16.4K
Same provider
Overall 69%
gpt-4.1-2025-04-14
github_copilot
In N/A
Out N/A
imagetext
Output: text
VisionFunction callingParallel function callingResponse schema
16.4K
Same provider
Overall 69%
magistral-medium
vercel_ai_gateway
In $2.0000 / 1M tokens
Out $5.0000 / 1M tokens
imagetext
Output: text
Function callingResponse schema
64.0K
Text + image covered
Overall 65%
gpt-4o-2024-11-20
Azure
In $2.7500 / 1M tokens
Out $11.0000 / 1M tokens
imagetext
Output: text
VisionFunction callingParallel function callingResponse schema
16.4K
Text + image covered
Overall 64%
gpt-4o-2024-11-20
github_copilot
In N/A
Out N/A
imagetext
Output: text
VisionFunction callingParallel function calling
16.4K
Same provider
Overall 63%
paddleocr-vl
novita
In $0.0200 / 1M tokens
Out $0.0200 / 1M tokens
imagetext
Output: text
Vision
16.4K
Text + image covered
Overall 49%
Llama-3.2-3B-Instruct
deepinfra
In $0.0200 / 1M tokens
Out $0.0200 / 1M tokens
imagetext
Output: text
Function calling
131.1K
Partial I/O overlap
Overall 40%
Missing image
llama3.2-11b-vision-instruct
lambda_ai
In $0.0150 / 1M tokens
Out $0.0250 / 1M tokens
imagetext
Output: unknown
VisionFunction callingParallel function calling
131.1K
Partial I/O overlap
Overall 20%
Missing text, image
llama3.2-3b-instruct
lambda_ai
In $0.0150 / 1M tokens
Out $0.0250 / 1M tokens
imagetext
Output: unknown
Function callingParallel function calling
131.1K
Partial I/O overlap
Overall 16%
Missing text, image
titan-embed-text-v2
vercel_ai_gateway
In $0.0200 / 1M tokens
Out N/A
imagetext
Output: embedding
Low overlap
0
Partial I/O overlap
Overall 12%
Missing image
Qwen2.5-Coder-3B-Instruct
nscale
In $0.0100 / 1M tokens
Out $0.0300 / 1M tokens
imagetext
Output: unknown
Low overlap
N/A
Partial I/O overlap
Overall 0%
Missing text, image