ML
Llama 3.1 405B
Meta
$0.01
per request
CheapestAN
Claude 3.5 Haiku
Anthropic
$0.03
per request
OA
GPT-5.4 Mini
OpenAI
$0.03
per request
10,000
5,000
Cost per Request
Context Window
Pricing Breakdown
| Metric | Llama 3.1 405B | Claude 3.5 Haiku | GPT-5.4 Mini |
|---|---|---|---|
| Input Price | $0.80/MTok | $0.80/MTok | $0.75/MTok |
| Output Price | $0.80/MTok | $4.00/MTok | $4.50/MTok |
| Cached Input | — | $0.08/MTok | $0.07/MTok |
| Cost / Request | $0.01 | $0.03 | $0.03 |
| Daily (100 req) | $1.20 | $2.80 | $3.00 |
| Monthly (100 req/day) | $36.00 | $84.00 | $90.00 |
Features & Capabilities
| Feature | Llama 3.1 405B | Claude 3.5 Haiku | GPT-5.4 Mini |
|---|---|---|---|
| Context Window | 128K | 200K | 1.1M |
| Max Output | 8K | 8K | 32K |
| Caching | No | Yes | Yes |
| Batch API | No | Yes | Yes |
| Vision | No | Yes | Yes |
| Tool Use | Yes | Yes | Yes |
| Best For | reasoningcodingcomplex tasks | chatfast tasksbudget | generalfast tasks |