o4-mini vs Claude Sonnet 4.6
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by OpenAI
|
by Anthropic
|
|---|---|---|
| Overview | ||
| Status | Deprecated reasoning | Current mid tier |
| Released | Apr 17, 2025 | Jan 15, 2026 |
| Pricing per million tokens | ||
| Input | $1.10/Mtok | $3.00/Mtok |
| Output | $4.40/Mtok | $15.00/Mtok |
| Blended avg | $1.93/Mtok | $6.00/Mtok |
| Cached input | $0.275/Mtok | $0.300/Mtok |
| Specifications | ||
| Context window | 200K tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
textimage
|
| Benchmarks source: Vellum LLM Leaderboard | ||
| Avg benchmark score | 69.2 | 70.4 |
| Perf / dollar | 35.9 | 11.7 |
| GPQA Diamond | 81.4 | 89.9 |
| Humanity's Last Exam | 14.28 | 19.1 |
| ARC-AGI 2 | 40 | 58.3 |
| AIME 2025 | 92.7 | 83 |
| MMMLU | 86 | 89.3 |
| HumanEval | 68.1 | 79.6 |
| SWE-Bench Verified | 68 | — |
| Terminal-Bench 2.1 | — | 59.1 |
| LiveCodeBench | — | 72.4 |
| MCP Atlas | — | 69.5 |
| BrowseComp | — | 76.2 |
| OSWorld-Verified | — | 78.5 |
| BFCL | 82 | — |
| MATH 500 | 90 | — |
| AutoBench | — | 5.3 |
| Independent composite scores each on its own scale — not part of the average above | ||
| LMSYS Chatbot Arena | 1389.8 ELO | 1472 ELO |
| AA Intelligence Index | — | 48.4 |
| AA Agentic Index | — | 42.1 |
| AA-Omniscience Index (−100–100) | — | 12.2 |
| Providers | ||
| Available from |
OpenAI — $1.10/$4.40/Mtok
|
Anthropic — $3.00/$15.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | o4-mini | Claude Sonnet 4.6 | Savings |
|---|---|---|---|
| 1M tokens | $1.93 | $6 | $4.07 (67.8%) |
| 10M tokens | $19.25 | $60 | $40.75 (67.9%) |
| 100M tokens | $192.5 | $600 | $407.5 (67.9%) |
| 1000M tokens | $1925 | $6000 | $4075 (67.9%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $1.93/Mtok blended vs $6.00 — 67.9% less on the same 50/50 token mix
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.300/Mtok — 90% off its list input price
- you need the longer context: 1M tokens vs 200K (5×)
- raw capability matters more than price: 70.4 vs 69.2 average benchmark score
The cheaper option here — o4-mini costs $1.93/Mtok blended on OpenAI.
Summary
o4-mini by OpenAI costs $1.10/Mtok input and $4.40/Mtok output, with a 200K-token context window. It supports text, image input.
Claude Sonnet 4.6 by Anthropic costs $3.00/Mtok input and $15.00/Mtok output, with a 1M-token context window. It supports text, image input.
On a blended cost basis, o4-mini is 67.9% cheaper than Claude Sonnet 4.6.
On benchmarks, Claude Sonnet 4.6 scores higher (70.4 vs 69.2) on average. In terms of value, o4-mini has better performance per dollar (35.9 vs 11.7).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.