A
Amazon Bedrock
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-03-232026-04-21
Inference Latency
Amazon: Nova Micro 1.0294ms TTFT · 94 TPS
Amazon: Nova Lite 1.0470ms TTFT · 81 TPS
OpenAI: gpt-oss-20b826ms TTFT · 199 TPS
OpenAI: gpt-oss-120b1476ms TTFT · 138 TPS
Anthropic: Claude 3 Haiku736ms TTFT · 71 TPS
Amazon: Nova 2 Lite886ms TTFT · 113 TPS
Writer: Palmyra X5435ms TTFT · 77 TPS
Meta: Llama 3.1 70B Instruct514ms TTFT · 14 TPS
Anthropic: Claude 3.5 Haiku929ms TTFT · 41 TPS
Amazon: Nova Pro 1.0448ms TTFT · 47 TPS
Anthropic: Claude Haiku 4.51101ms TTFT · 46 TPS
Z.ai: GLM 51211ms TTFT · 57 TPS
Amazon: Nova Premier 1.0462ms TTFT · 32 TPS
Anthropic: Claude Sonnet 41453ms TTFT · 44 TPS
Anthropic: Claude 3.7 Sonnet1384ms TTFT · 48 TPS
Anthropic: Claude Sonnet 4.52034ms TTFT · 41 TPS
Anthropic: Claude Sonnet 4.61916ms TTFT · 35 TPS
Anthropic: Claude Opus 4.71343ms TTFT · 78 TPS
Anthropic: Claude Opus 4.62179ms TTFT · 36 TPS
Anthropic: Claude Opus 4.51694ms TTFT · 34 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Amazon: Nova Micro 1.0 | $0.04 | $0.14 | 294ms | 94 |
| Amazon: Nova Lite 1.0 | $0.06 | $0.24 | 470ms | 81 |
| OpenAI: gpt-oss-20b | $0.07 | $0.15 | 826ms | 199 |
| OpenAI: gpt-oss-120b | $0.15 | $0.60 | 1476ms | 138 |
| Qwen: Qwen3 Coder 30B A3B Instruct | $0.15 | $0.60 | — | — |
| Anthropic: Claude 3 Haiku | $0.25 | $1.25 | 736ms | 71 |
| Amazon: Nova 2 Lite | $0.30 | $2.50 | 886ms | 113 |
| Writer: Palmyra X5 | $0.60 | $6.00 | 435ms | 77 |
| Meta: Llama 3.1 70B Instruct | $0.72 | $0.72 | 514ms | 14 |
| Anthropic: Claude 3.5 Haiku | $0.80 | $4.00 | 929ms | 41 |
| Amazon: Nova Pro 1.0 | $0.80 | $3.20 | 448ms | 47 |
| Anthropic: Claude Haiku 4.5 | $1.00 | $5.00 | 1101ms | 46 |
| Z.ai: GLM 5 | $1.00 | $3.20 | 1211ms | 57 |
| Amazon: Nova Premier 1.0 | $2.50 | $12.50 | 462ms | 32 |
| Anthropic: Claude Sonnet 4 | $3.00 | $15.00 | 1453ms | 44 |
| Anthropic: Claude 3.7 Sonnet | $3.00 | $15.00 | 1384ms | 48 |
| Anthropic: Claude Sonnet 4.5 | $3.00 | $15.00 | 2034ms | 41 |
| Anthropic: Claude Sonnet 4.6 | $3.00 | $15.00 | 1916ms | 35 |
| Anthropic: Claude Opus 4.7 | $5.00 | $25.00 | 1343ms | 78 |
| Anthropic: Claude Opus 4.6 | $5.00 | $25.00 | 2179ms | 36 |
| Anthropic: Claude Opus 4.5 | $5.00 | $25.00 | 1694ms | 34 |
| Anthropic: Claude 3.5 Sonnet | $6.00 | $30.00 | — | — |
| Anthropic: Claude Opus 4 | $15.00 | $75.00 | 3550ms | 14 |
| Anthropic: Claude Opus 4.1 | $15.00 | $75.00 | 3413ms | 11 |
Community Reviews
4.5★★★★★(2 reviews)
clouduser42
★★★★★2025-06-15
Reliable service, great API documentation.
mlresearcher
★★★★☆2025-06-10
Good performance but support could be faster.