Models

Claude Opus 4.8 vs GPT 5 Mini

Compare Claude Opus 4.8 from Anthropic and GPT 5 Mini from OpenAI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.

AnthropicClaude Opus 4.8OpenAIGPT 5 Mini
Anthropic logo
Claude Opus 4.8
Anthropic · text, image, pdf → text

Claude Opus 4.8 is Anthropic’s newest and most powerful publicly available model. It is suitable for the most complex tasks. It is Anthropic’s strongest model for complex reasoning, long-horizon agent programming, and highly autonomous work.claude-opus-4-8 does not display thought content by default; you need to set the additional parameter "display": "summarized" to enable it

Input$5 /M
Output$25 /M
Cache read$0.5 /M
OpenAI logo
GPT 5 Mini
OpenAI · text, image → text

GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.

Input$0.25 /M
Output$2 /M
Cache read$0.025 /M

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

Claude Opus 4.8
GPT 5 Mini
Input /M
$5
$0.25
Output /M
$25
$2
Cache read /M
$0.5
$0.025
Context length
1,000,000
400,000
Max output
128,000
128,000
Time to First Token
1.1 s
2.6 s
Throughput
82.6 tok/s
84.7 tok/s
Modalities
textimagepdf
textimage
Supported Parameters
thinkingtoolsfunction callingstructured outputs
thinkingtoolsfunction callingstructured outputs
API Formats
chat_completions · claude_api
Released
May 28, 2026
August 7, 2025

Promotional prices show the discounted rate; see each model page for promotion windows.

Activity Past 30 Days

Daily traffic served through AIHubMix — how demand for each model is trending.

claude-opus-4-8gpt-5-mini

Tokens / day

-

Requests / day

-

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

claude-opus-4-8gpt-5-mini

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.

Text
claude-opus-4-8gpt-5-mini
1300138014601540
Overall
13901473
Coding
14301527
Math
14061474
Hard prompts
14031503
Instruction following
13741477
Multi-turn
13721495
Creative writing
13261465
Longer query
13701499
Chinese
14091523
English
13981480
Vision
claude-opus-4-8gpt-5-mini
1160122012801340
Overall
11811279
OCR
11951294
Diagram
12121309
Homework
12311320

Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.

Cost calculator

Estimate your monthly bill for the same workload on each model.

GPT 5 Mini
$45.00 /mo
Claude Opus 4.8
$675 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

Which is cheaper: Claude Opus 4.8, GPT 5 Mini?

GPT 5 Mini: $2/M output tokens; Claude Opus 4.8: $25/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

Claude Opus 4.8: 1527; GPT 5 Mini: 1430 (LMArena coding leaderboard).

Which responds faster?

Claude Opus 4.8: 1.1s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.

How large is each context window?

Claude Opus 4.8 accepts 1,000,000 and GPT 5 Mini accepts 400,000 input tokens. Maximum output per request is 128,000 tokens on Claude Opus 4.8 and 128,000 tokens on GPT 5 Mini.

Which one generates tokens faster?

GPT 5 Mini at 84.7 tok/s and Claude Opus 4.8 at 82.6 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

Claude Opus 4.8 accepts text, image and PDF input and supports thinking, tool calling, function calling and structured outputs; GPT 5 Mini accepts text and image input and supports thinking, tool calling, function calling and structured outputs.

Can I call Claude Opus 4.8 and GPT 5 Mini with the same API key?

Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.

Popular comparisons

Related model match-ups readers also look at.