Claude Haiku 4.5 (2025-10-01) vs Claude Sonnet 4.6

Claude Haiku 4.5 (2025-10-01) vs Claude Sonnet 4.6: Claude Haiku 4.5 (2025-10-01) is cheaper by 67% on average. Claude Haiku 4.5 (2025-10-01) from Anthropic (200,000-token context, reasoning, tool calls) vs. Claude Sonnet 4.6 from Azure AI Foundry (1,000,000-token context, reasoning, tool calls). Use Agent Command Center to A/B both in shadow mode and pick the winner per workload.

Side-by-side cost

Live workload comparison

Same workload run through both models. The cheaper one is highlighted.

3,000
01,000,000
400
064,000
5,000
01,000,000
Anthropic
$761/mo
Input $1.00/M · Output $5.00/M
Azure AI Foundry
$2,283/mo
Input $3.00/M · Output $15.00/M
At this workload, Claude Haiku 4.5 (2025-10-01) is 67% cheaper than Claude Sonnet 4.6 — a savings of $1,522/month ($18,263/year).
Production recipe — Agent Command Center
strategy: cost-optimized
primary:
  model: claude-haiku-4-5-20251001
  provider: anthropic
fallback:
  model: claude-sonnet-4-6
  provider: azure-ai-foundry
shadow: { sample_rate: 0.05 }   # mirror 5% of traffic to compare quality live
Claude Haiku 4.5 (2025-10-01) Claude Sonnet 4.6
Input price $1.00/M $3.00/M
Output price $5.00/M $15.00/M
Context window 200,000 1,000,000
Max output 64,000 64,000
Function calling
Vision
Audio input
Reasoning
Prompt caching
Structured output
Pricing verified May 12, 2026 May 12, 2026
Cheaper option
~67% cheaper than Claude Sonnet 4.6
Larger context
1,000,000 tokens
More capabilities
5 of 6 capability flags advertised

Benchmark comparison

Side-by-side public benchmark scores. Greener bar = winner.

Chatbot Arena ELOgeneral
Claude Haiku 4.5 (2025-10-01)
1,310
Claude Sonnet 4.6
1,466
τ-bench (retail)agent
Claude Haiku 4.5 (2025-10-01)
Claude Sonnet 4.6
91.7%
GPQA Diamondreasoning
Claude Haiku 4.5 (2025-10-01)
55.2%
Claude Sonnet 4.6
89.9%
HumanEvalcode
Claude Haiku 4.5 (2025-10-01)
89.5%
Claude Sonnet 4.6
MMLUgeneral
Claude Haiku 4.5 (2025-10-01)
Claude Sonnet 4.6
89.3%
SWE-bench Verifiedagent
Claude Haiku 4.5 (2025-10-01)
52.0%
Claude Sonnet 4.6
79.6%
BFCL v3agent
Claude Haiku 4.5 (2025-10-01)
79.3%
Claude Sonnet 4.6
MMMU-Promultimodal
Claude Haiku 4.5 (2025-10-01)
Claude Sonnet 4.6
74.5%
MMLU-Proreasoning
Claude Haiku 4.5 (2025-10-01)
72.4%
Claude Sonnet 4.6
ARC-AGI-2reasoning
Claude Haiku 4.5 (2025-10-01)
Claude Sonnet 4.6
58.3%
Humanity's Last Examreasoning
Claude Haiku 4.5 (2025-10-01)
Claude Sonnet 4.6
33.2%