Amazon Bedrock — pricing & performance
Models served
32
of 1,111 tracked models
Mean output speed
71
tokens per second, averaged over
31 measured endpoints
31 measured endpoints
Mean latency
8.2s
time to first token, averaged over
31 measured endpoints
31 measured endpoints
Cheapest blended
$0.061
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Amazon Bedrock
Output tokens per second for the 31 of 32 models on Amazon Bedrock with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 32, measured or not. Higher is better. We do not run these measurements ourselves.
The Known Good
32 models on Amazon Bedrock
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
| Az Amazon: Nova 2 Lite | Amazon | $0.30 | $2.50 | $0.85 | 103 | 0.9s | 1.00M |
| Az Amazon: Nova Lite 1.0 | Amazon | $0.060 | $0.24 | $0.10 | 77 | 0.5s | 300k |
| Az Amazon: Nova Micro 1.0 | Amazon | $0.035 | $0.14 | $0.061 | 143 | 0.3s | 128k |
| Az Amazon: Nova Premier 1.0 | Amazon | $2.50 | $12.50 | $5.00 | 32 | 0.5s | 1.00M |
| Az Amazon: Nova Pro 1.0 | Amazon | $0.80 | $3.20 | $1.40 | 72 | 0.5s | 300k |
Anthropic: Claude 3 Haiku
|
Anthropic | $0.25 | $1.25 | $0.50 | 66 | 0.3s | 200k |
|
Anthropic: Claude Fable 5
|
Anthropic | $10.00 | $50.00 | $20.00 | 35 | 5.7s | 1.00M |
|
Anthropic: Claude Fable 5.1
|
Anthropic | $10.00 | $50.00 | $20.00 | 32 | 5.4s | 1.00M |
|
Anthropic: Claude Haiku 4.5
|
Anthropic | $1.00 | $5.00 | $2.00 | 111 | 0.6s | 200k |
|
Anthropic: Claude Opus 4.1
|
Anthropic | $15.00 | $75.00 | $30.00 | 12 | 3.3s | 200k |
|
Anthropic: Claude Opus 4.5
|
Anthropic | $5.00 | $25.00 | $10.00 | 45 | 2.1s | 200k |
|
Anthropic: Claude Opus 4.6
|
Anthropic | $5.00 | $25.00 | $10.00 | 39 | 1.9s | 1.00M |
|
Anthropic: Claude Opus 4.7
|
Anthropic | $5.00 | $25.00 | $10.00 | 54 | 1.9s | 1.00M |
|
Anthropic: Claude Opus 4.8
|
Anthropic | $5.00 | $25.00 | $10.00 | 61 | 2.8s | 1.00M |
|
Anthropic: Claude Sonnet 4
|
Anthropic | $3.00 | $15.00 | $6.00 | 44 | 1.1s | 200k |
|
Anthropic: Claude Sonnet 4.5
|
Anthropic | $3.00 | $15.00 | $6.00 | 44 | 2.2s | 1.00M |
|
Anthropic: Claude Sonnet 4.6
|
Anthropic | $3.00 | $15.00 | $6.00 | 63 | 0.9s | 1.00M |
|
Anthropic: Claude Sonnet 5
|
Anthropic | $2.00 | $10.00 | $4.00 | 56 | 3.9s | 1.00M |
|
Claude Opus 5
|
Anthropic | $5.00 | $25.00 | $10.00 | 64 | 3.8s | 1.00M |
Meta: Llama 3.1 70B Instruct
|
Meta | $0.72 | $0.72 | $0.72 | 18 | 0.4s | 131k |
MoonshotAI: Kimi K2.5
|
Moonshot AI | $0.60 | $3.00 | $1.20 | 44 | 1.2s | 262k |
OpenAI: GPT-5.4
|
OpenAI | $2.75 | $16.50 | $6.19 | 5 | 1.3s | 1.05M |
|
OpenAI: GPT-5.5
|
OpenAI | $5.50 | $33.00 | $12.38 | 150 | 1.6s | 1.05M |
|
OpenAI: GPT-5.6 Luna
|
OpenAI | $0.22 | $1.32 | $0.49 | 96 | 0.9s | 1.05M |
|
OpenAI: GPT-5.6 Sol
|
OpenAI | $4.40 | $22.00 | $8.80 | 9 | 3.8s | 1.05M |
|
OpenAI: GPT-5.6 Terra
|
OpenAI | $2.20 | $13.20 | $4.95 | 42 | 1.7s | 1.05M |
|
OpenAI: gpt-oss-120b
|
OpenAI | $0.15 | $0.60 | $0.26 | 293 | 0.4s | 131k |
|
OpenAI: gpt-oss-20b
|
OpenAI | $0.070 | $0.15 | $0.090 | 296 | 0.4s | 131k |
Qwen: Qwen3 Coder 30B A3B Instruct
|
Alibaba | $0.15 | $0.60 | $0.26 | — | — | — |
SpaceXAI: Grok 4.6
|
xAI | $2.20 | $6.60 | $3.30 | 24 | 202.0s | 500k |
| Wr Writer: Palmyra X5 | writer | $0.60 | $6.00 | $1.95 | 22 | 0.3s | 1.04M |
Z.ai: GLM 5
|
Z.ai | $1.00 | $3.20 | $1.55 | 54 | 1.9s | 203k |
The Known Good
Source. Prices, endpoint availability and throughput for Amazon Bedrock are ingested from OpenRouter;
model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint —
it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this
site; see methodology. Quality scores are not provider-specific:
a model scores the same wherever it is hosted, so quality lives on the
model pages.