The Known Good Updated 8 Oct 2026 Subscribe
Providers· First-party endpoint· 40 tracked models

Amazon Bedrock — pricing & performance

Compare models All providers Data sources
Models served
40
of 1,191 tracked models
Mean output speed
89
tokens per second, averaged over
37 measured endpoints
Mean latency
4.2s
time to first token, averaged over
37 measured endpoints
Cheapest blended
$0.061
per 1M tokens at a 3:1
input:output blend
Output speed on Amazon Bedrock

Output tokens per second for the 37 of 40 models on Amazon Bedrock with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 40, measured or not. Higher is better. We do not run these measurements ourselves.

⇩
290
277
159
137
136
135
134
121
121
114
111
97
The Known Good
40 models on Amazon Bedrock
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Amazon: Nova 2 Lite Amazon $0.30 $2.50 $0.85 121 0.5s 1.00M
Amazon: Nova Lite 1.0 Amazon $0.060 $0.24 $0.10 134 0.7s 300k
Amazon: Nova Micro 1.0 Amazon $0.035 $0.14 $0.061 159 0.4s 128k
Amazon: Nova Premier 1.0 Amazon $2.50 $12.50 $5.00 — — 1.00M
Amazon: Nova Pro 1.0 Amazon $0.80 $3.20 $1.40 135 0.6s 300k
Anthropic: Claude 3 Haiku Anthropic $0.25 $1.25 $0.50 36 0.4s 200k
Anthropic: Claude Fable 5 Anthropic $10.00 $50.00 $20.00 — — 1.00M
Anthropic: Claude Fable 5.1 Anthropic $10.00 $50.00 $20.00 42 15.5s 1.00M
Anthropic: Claude Haiku 4.5 Anthropic $1.00 $5.00 $2.00 114 0.8s 200k
Anthropic: Claude Haiku 5.5 Anthropic $0.10 $0.50 $0.20 136 2.6s 1.00M
Anthropic: Claude Opus 4.1 Anthropic $15.00 $75.00 $30.00 13 3.8s 200k
Anthropic: Claude Opus 4.5 Anthropic $5.00 $25.00 $10.00 44 1.4s 200k
Anthropic: Claude Opus 4.6 Anthropic $5.00 $25.00 $10.00 39 2.1s 1.00M
Anthropic: Claude Opus 4.7 Anthropic $5.00 $25.00 $10.00 60 1.3s 1.00M
Anthropic: Claude Opus 4.8 Anthropic $5.00 $25.00 $10.00 81 2.3s 1.00M
Anthropic: Claude Opus 5 Anthropic $5.00 $25.00 $10.00 56 1.0s 1.00M
Anthropic: Claude Opus 5.5 Anthropic $4.00 $20.00 $8.00 70 4.5s 1.00M
Anthropic: Claude Sonnet 4 Anthropic $3.00 $15.00 $6.00 59 0.9s 200k
Anthropic: Claude Sonnet 4.5 Anthropic $3.00 $15.00 $6.00 38 1.7s 1.00M
Anthropic: Claude Sonnet 4.6 Anthropic $3.00 $15.00 $6.00 57 2.0s 1.00M
Anthropic: Claude Sonnet 5 Anthropic $2.00 $10.00 $4.00 82 3.6s 1.00M
Anthropic: Claude Sonnet 5.5 Anthropic $2.00 $10.00 $4.00 81 1.3s 1.00M
Meta: Llama 3.1 70B Instruct Meta $0.72 $0.72 $0.72 62 0.4s 131k
MoonshotAI: Kimi K2.5 Moonshot AI $0.60 $3.00 $1.20 75 0.8s 262k
MoonshotAI: Kimi K3 Moonshot AI $3.00 $15.00 $6.00 65 2.2s 1.05M
OpenAI: GPT-5.4 OpenAI $2.75 $16.50 $6.19 121 1.6s 1.05M
OpenAI: GPT-5.5 OpenAI $5.50 $33.00 $12.38 92 5.8s 1.05M
OpenAI: GPT-5.6 Luna OpenAI $0.22 $1.32 $0.49 97 0.3s 1.05M
OpenAI: GPT-5.6 Sol OpenAI $4.40 $22.00 $8.80 80 3.1s 1.05M
OpenAI: GPT-5.6 Terra OpenAI $2.20 $13.20 $4.95 94 0.9s 1.05M
OpenAI: GPT-6 Astra OpenAI $11.00 $55.00 $22.00 30 5.1s 1.05M
OpenAI: GPT-6 Luna OpenAI $0.11 $0.55 $0.22 137 0.5s 1.05M
OpenAI: GPT-6 Sol OpenAI $2.20 $11.00 $4.40 90 2.5s 1.05M
OpenAI: GPT-6.1 Sol OpenAI $2.20 $11.00 $4.40 47 1.5s 1.05M
OpenAI: gpt-oss-120b OpenAI $0.15 $0.60 $0.26 290 0.4s 131k
OpenAI: gpt-oss-20b OpenAI $0.070 $0.15 $0.090 277 0.6s 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 18 80.4s 500k
Writer: Palmyra X5 writer $0.60 $6.00 $1.95 52 0.4s 1.04M
Z.ai: GLM 5 Z.ai $1.00 $3.20 $1.55 111 0.7s 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.