GPT-4.1 mini vs Claude Haiku 4.5
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by OpenAI
|
by Anthropic
|
|---|---|---|
| Overview | ||
| Status | Current budget | Current budget |
| Released | Apr 14, 2025 | Oct 15, 2025 |
| Pricing per million tokens | ||
| Input | $0.400/Mtok | $1.00/Mtok |
| Output | $1.60/Mtok | $5.00/Mtok |
| Blended avg | $0.700/Mtok | $2.00/Mtok |
| Cached input | $0.100/Mtok | $0.100/Mtok |
| Specifications | ||
| Context window | 1M tokens | 200K tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimage
|
textimage
|
| Benchmarks source: Vellum LLM Leaderboard | ||
| Avg benchmark score | 55.7 | 65.5 |
| Perf / dollar | 79.6 | 32.8 |
| GPQA Diamond | 65 | 73 |
| AIME 2025 | 40 vendor | 96.3 |
| MMMLU | 78.5 | 83 |
| HumanEval | 23.6 | 73.3 |
| MATH 500 | 70 vendor | 78 vendor |
| SWE-Bench Verified | 30 vendor | — |
| Terminal-Bench 2.1 | — | 27.5 |
| MCP Atlas | — | 40.2 |
| Humanity's Last Exam | 12 vendor | — |
| ARC-AGI 2 | 15 vendor | — |
| BFCL | 70 vendor | — |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 14.8 | 29.9 |
| AA Agentic Index | 1.8 | 16.5 |
| AA-Omniscience Index (−100–100) | -53.6 | -4.4 |
| LMSYS Chatbot Arena | 1382.8 ELO | 1412.5 ELO |
| Providers | ||
| Available from |
OpenAI — $0.400/$1.60/Mtok
|
Anthropic — $1.00/$5.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | GPT-4.1 mini | Claude Haiku 4.5 | Savings |
|---|---|---|---|
| 1M tokens | $0.7 | $2 | $1.3 (65%) |
| 10M tokens | $7 | $20 | $13 (65%) |
| 100M tokens | $70 | $200 | $130 (65%) |
| 1000M tokens | $700 | $2000 | $1300 (65%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.700/Mtok blended vs $2.00 — 65% less on the same 50/50 token mix
- you need the longer context: 1M tokens vs 200K (5×)
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.100/Mtok — 90% off its list input price
- raw capability matters more than price: 65.5 vs 55.7 average benchmark score
The cheaper option here — GPT-4.1 mini costs $0.700/Mtok blended on OpenAI.
Summary
GPT-4.1 mini by OpenAI costs $0.400/Mtok input and $1.60/Mtok output, with a 1M-token context window. It supports text, image input.
Claude Haiku 4.5 by Anthropic costs $1.00/Mtok input and $5.00/Mtok output, with a 200K-token context window. It supports text, image input.
On a blended cost basis, GPT-4.1 mini is 65% cheaper than Claude Haiku 4.5.It also has a larger context window.
On benchmarks, Claude Haiku 4.5 scores higher (65.5 vs 55.7) on average. In terms of value, GPT-4.1 mini has better performance per dollar (79.6 vs 32.8).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.