Gemini 2.5 Flash vs Claude Haiku 4.5
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
|
by Google
|
by Anthropic
|
|
|---|---|---|
| Overview | ||
| Status | Current budget | Current budget |
| Released | Jun 17, 2025 | Oct 15, 2025 |
| Pricing per million tokens | ||
| Input | $0.075/Mtok | $1.00/Mtok |
| Output | $0.300/Mtok | $5.00/Mtok |
| Blended avg | $0.188/Mtok | $3.00/Mtok |
| Cached input | — | $0.100/Mtok |
| Specifications | ||
| Context window | 1M tokens | 200K tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
textimageaudiovideo
|
textimage
|
| Benchmarks from Vellum LLM Leaderboard | ||
| Avg benchmark score | 53.7 | 82.9 |
| Perf / dollar | 286.4 | 27.6 |
| GPQA Diamond | 55 | — |
| SWE-Bench | 38 | — |
| HumanEval | 82 | 87.8 |
| MATH 500 | 72 | 78 |
| Providers | ||
| Available from |
Google — $0.075/$0.300/Mtok
|
Anthropic — $1.00/$5.00/Mtok
|
Cost at scale — 1M tokens (50/50 input/output)
| Volume | Gemini 2.5 Flash | Claude Haiku 4.5 | Savings |
|---|---|---|---|
| 1M tokens | $0.19 | $3 | $2.81 (93.7%) |
| 10M tokens | $1.88 | $30 | $28.13 (93.8%) |
| 100M tokens | $18.75 | $300 | $281.25 (93.8%) |
| 1000M tokens | $187.5 | $3000 | $2812.5 (93.8%) |
Summary
Gemini 2.5 Flash by Google costs $0.075/Mtok input and $0.300/Mtok output, with a 1M-token context window. It supports text, image, audio, video 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, Gemini 2.5 Flash is 1500% cheaper than Claude Haiku 4.5. It also has a larger context window.
On benchmarks, Claude Haiku 4.5 scores higher (82.9 vs 53.7) on average. In terms of value, Gemini 2.5 Flash has better performance per dollar (286.4 vs 27.6).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.