Inference provider

Amazon Bedrock

30 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.

Models served

Median output speed

74 t/s

Median latency

889ms

Median price / 1M

$3.13

Catalogue

Strongest and fastest on this provider

What the catalogue looks like at the top end, on the two axes that usually decide the choice.

Highest Intelligence Index

Among models this provider serves

Claude Opus 5Anthropic
63.1
Claude Fable 5Anthropic
62.1
GPT-5.6 SolOpenAI
60.9
Claude Opus 4.8Anthropic
57.3
GPT-5.6 TerraOpenAI
56.6
GPT-5.5OpenAI
56.3
Claude Sonnet 5Anthropic
55.3
Claude Opus 4.7Anthropic
55.0
GPT-5.4OpenAI
53.1
GPT-5.6 LunaOpenAI
52.3

View as table

Model	Intelligence
Claude Opus 5 (Anthropic)	63.1
Claude Fable 5 (Anthropic)	62.1
GPT-5.6 Sol (OpenAI)	60.9
Claude Opus 4.8 (Anthropic)	57.3
GPT-5.6 Terra (OpenAI)	56.6
GPT-5.5 (OpenAI)	56.3
Claude Sonnet 5 (Anthropic)	55.3
Claude Opus 4.7 (Anthropic)	55.0
GPT-5.4 (OpenAI)	53.1
GPT-5.6 Luna (OpenAI)	52.3

Fastest output

Median tokens per second

gpt-oss-120bOpenAI
773 t/s
gpt-oss-20bOpenAI
252 t/s
Nova Micro 1.0Amazon
177 t/s
Nova Lite 1.0Amazon
155 t/s
GPT-5.4OpenAI
120 t/s
Claude Haiku 4.5Anthropic
111 t/s
Claude Sonnet 5Anthropic
102 t/s
Nova Pro 1.0Amazon
98 t/s
GPT-5.6 LunaOpenAI
88 t/s
Claude Opus 5Anthropic
87 t/s

View as table

Model	Tokens/s
gpt-oss-120b (OpenAI)	773
gpt-oss-20b (OpenAI)	252
Nova Micro 1.0 (Amazon)	177
Nova Lite 1.0 (Amazon)	155
GPT-5.4 (OpenAI)	120
Claude Haiku 4.5 (Anthropic)	111
Claude Sonnet 5 (Anthropic)	102
Nova Pro 1.0 (Amazon)	98
GPT-5.6 Luna (OpenAI)	88
Claude Opus 5 (Anthropic)	87

Full catalogue

All 30 models on Amazon Bedrock

30 of 30 models


Claude Opus 5 Anthropic	63.1	78.0	59.2	87 t/s	1.12s	$10	$2.25	1M
Claude Fable 5 Anthropic	62.1	76.5	56.6	54 t/s	3.84s	$20	$4.50	1M
GPT-5.6 Sol OpenAI	60.9	77.4	57.8	46 t/s	2.38s	$11.25	$2.65	1.05M
Claude Opus 4.8 Anthropic	57.3	74.3	49.4	64 t/s	902ms	$10	$2.25	1M
GPT-5.6 Terra OpenAI	56.6	76.7	50.2	56 t/s	1.5s	$2.25	$0.53	1.05M
GPT-5.5 OpenAI	56.3	74.9	47.4	85 t/s	2.19s	$11.25	$2.65	1.05M
Claude Sonnet 5 Anthropic	55.3	71.5	49.7	102 t/s	1.39s	$4	$0.90	1M
Claude Opus 4.7 Anthropic	55.0	73.6	46.3	77 t/s	1.05s	$10	$2.25	1M
GPT-5.4 OpenAI	53.1	71.1	44.2	120 t/s	1.07s	$5.63	$1.32	1.05M
GPT-5.6 Luna OpenAI	52.3	71.4	46.9	88 t/s	1.16s	$0.225	$0.05	1.05M
GLM 5 Z.aiopen	40.6	—	—	48 t/s	937ms	$1.35	$0.25	205K
Claude Opus 4.6 Anthropic	38.8	—	—	44 t/s	1.85s	$10	$2.25	1M
Claude Sonnet 4.6 Anthropic	36.8	—	42.1	52 t/s	843ms	$6	$1.35	1M
Kimi K2.5 Moonshot AIopen	36.0	46.8	21.7	73 t/s	849ms	$1.14	$0.26	262K
Claude Opus 4.5 Anthropic	35.6	—	—	53 t/s	1.1s	$10	$2.25	200K
Claude Sonnet 4.5 Anthropic	29.9	—	26.4	54 t/s	1.1s	$6	$1.35	1M
Claude Opus 4.1 Anthropic	28.8	—	—	16 t/s	2.46s	$30	$6.75	200K
Claude Sonnet 4 Anthropic	26.0	—	17.6	41 t/s	863ms	$6	$1.35	1M
Claude Haiku 4.5 Anthropic	24.1	—	16.5	111 t/s	487ms	$2	$0.45	200K
gpt-oss-120b OpenAIopen	24.1	30.4	13.4	773 t/s	205ms	$0.07	$0.02	131K
gpt-oss-20b OpenAIopen	15.2	20.7	3.1	252 t/s	259ms	$0.055	$0.01	131K
Qwen3 Coder 30B A3B Instruct Qwenopen	13.6	—	—	76 t/s	876ms	$0.12	$0.01	262K
Claude 3 Haiku Anthropic	3.5	—	—	79 t/s	423ms	$0.5	$0.04	200K
Palmyra X5 Writer	—	—	—	78 t/s	320ms	$1.95	$0.18	1.04M
Nova 2 Lite Amazon	—	—	—	48 t/s	440ms	$0.85	$0.22	1M
Nova Premier 1.0 Amazon	—	—	—	36 t/s	416ms	$5	$0.44	1M
Nova Lite 1.0 Amazon	—	—	—	155 t/s	313ms	$0.105	$0.009	300K
Nova Micro 1.0 Amazon	—	—	—	177 t/s	397ms	$0.061	$0.005	128K
Nova Pro 1.0 Amazon	—	—	—	98 t/s	667ms	$1.4	$0.12	300K
Llama 3.1 70B Instruct Metaopen	—	—	—	23 t/s	365ms	$0.4	$0.03	131K