LLMversus
Together AI

Qwen 2.5 72B (Together)

Complete specs, pricing, and benchmark data for Qwen 2.5 72B (Together) by Together AI. Last verified 2026-09-14.

JSON ModeFunctionsStreaming
Pricing

Input / 1M tokens

$1.20

Output / 1M tokens

$1.20

Context & Output

Context Window

32K

Max Output

4,096

TTFT

150ms

Speed

100 tok/s

Benchmarks

Arena ELO

1230

Coding ELO

1210

Reasoning ELO

1230

HumanEval

89

MMLU

85

MATH

104

GPQA

40

Price History (Input $/M tokens)

Strengths
  • +Good quality
  • +Reliable
  • +Balanced pricing
Limitations
  • -Smaller context window

Best For

CodingGeneral Purpose

Compare Qwen 2.5 72B (Together) with...

vs Claude Opus 4vs Claude Sonnet 4vs Gemini 2.5 Provs Claude Haiku 4vs DeepSeek R1vs Qwen 2.5 Maxvs Gemini 2.0 Flashvs DeepSeek V3vs o3-minivs o3vs o1vs Qwen 3 235B MoE
Official Pricing Page →
Your ad here