Claude Haiku 4.5 vs Gemini 3.8 Flash: API cost
Standard, cached and batch API prices for Claude Haiku 4.5 (Anthropic) and Gemini 3.8 Flash (Google), and what each costs for your usage.
Gemini 3.8 Flash is cheaper than Claude Haiku 4.5 at standard rates, with 25% cheaper input and 25% cheaper output.
- Input $30.00
- Cached input $3.00
- Output $45.00
- Input $22.50
- Cached input $2.25
- Output $33.75
Show as a table
| Output tokens | Claude Haiku 4.5 | Gemini 3.8 Flash |
|---|---|---|
| 0 | $1.00 | $0.75 |
| 250 | $2.25 | $1.69 |
| 500 | $3.50 | $2.63 |
| 750 | $4.75 | $3.56 |
| 1,000 | $6.00 | $4.50 |
| Token type | Claude Haiku 4.5 | Gemini 3.8 Flash | |
|---|---|---|---|
| Input | $1 | $0.75 | Gemini 3.8 Flash is 25% cheaper |
| Cached input | $0.10 | $0.075 | Gemini 3.8 Flash is 25% cheaper |
| Output | $5 | $3.75 | Gemini 3.8 Flash is 25% cheaper |
| Batch input | $0.50 | $0.375 | Gemini 3.8 Flash is 25% cheaper |
| Batch cached input | $0.05 | $0.0375 | Gemini 3.8 Flash is 25% cheaper |
| Batch output | $2.50 | $1.875 | Gemini 3.8 Flash is 25% cheaper |
Gemini 3.8 Flash: promotional price until 31 Dec 2026.
| Workload | Claude Haiku 4.5 | Gemini 3.8 Flash |
|---|---|---|
Support chatbot 2,000 in / 300 out tokens,
1,000 requests a day, 50% cached | $78.00 | $58.50 |
Document summaries 10,000 in / 800 out tokens,
200 requests a day | $84.00 | $63.00 |
Tagging / classifying 400 in / 20 out tokens,
20,000 requests a day | $300.00 | $225.00 |
More comparisons
- GPT-6 Sol vs Claude Haiku 4.5
- GPT-6 Sol vs Gemini 3.8 Flash
- GPT-6 Luna vs Claude Haiku 4.5
- Claude Sonnet 5 vs Claude Haiku 4.5
- Claude Haiku 4.5 vs Gemini 3.5 Flash-Lite
- Claude Haiku 4.5 vs Gemini 3.1 Flash-Lite
- Claude Haiku 4.5 vs Gemini 3 Flash Preview
- Claude Haiku 4.5 vs Gemini 2.5 Flash
Or see Claude Haiku 4.5 pricing, Gemini 3.8 Flash pricing, or compare any two models.
FAQ
Frequently asked questions
Is Claude Haiku 4.5 cheaper than Gemini 3.8 Flash?
Gemini 3.8 Flash is cheaper than Claude Haiku 4.5 at standard rates, with 25% cheaper input and 25% cheaper output. Based on standard API rates last checked on 30 Sept 2026.
How much do Claude Haiku 4.5 and Gemini 3.8 Flash cost per million tokens?
Claude Haiku 4.5: $1 per million input tokens and $5 per million output tokens. Gemini 3.8 Flash: $0.75 input and $3.75 output. These are standard rates in USD, before tax, from each provider’s own pricing page.
Which is cheaper with the Batch API?
Claude Haiku 4.5’s batch rates are $0.50 input and $2.50 output per million tokens (50% off); Gemini 3.8 Flash’s batch rates are $0.375 input and $1.875 output per million tokens (50% off).
Does prompt caching change the comparison?
Claude Haiku 4.5 charges $0.10 per million cached input tokens, against $1 for normal input; Gemini 3.8 Flash charges $0.075 per million cached input tokens, against $0.75 for normal input. Cache write and storage charges are extra and aren’t included here.