Amazon Bedrock: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Amazon Bedrock for your use-case.
Most Intelligent
Intelligence Index
Total 83 models
Lowest Time per Task
Time per Intelligence Index task (minutes)
Total 83 models
Lowest Price
Blended price (per 1M tokens)
Total 83 models
Amazon offers 83 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on Amazon are Claude Opus 5.5 (max) (59), GPT-6 Astra (max) (57), and Claude Sonnet 5.5 (max) (55).
- For time per task, Claude 4.5 Haiku (2.2 min), Claude Sonnet 5.5 (low) (2.5 min), and Claude Opus 5.5 (low) (3.4 min) finish an Intelligence Index task fastest on Amazon. Time per task varies significantly across models, with the slowest taking 2.5x longer than the quickest.
- For latency, Mistral 7B (0.43s), Llama 3 70B (0.56s), and Mixtral 8x7B (0.76s) offer the lowest time to first answer token.
- For pricing, Nova Micro ($0.03), Gemma 3 4B ($0.04), and Nova Lite ($0.05) offer the lowest blended prices per 1M tokens. Prices vary up to 3.4x across models.
- For context window size, Claude Opus 5.5 (max) (1M), Claude Sonnet 5.5 (max) (1M), and Kimi K3.1 Pro High Speed (1M) support the largest context windows on Amazon.
Intelligence
Artificial Analysis Intelligence Index
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Physics reasoning
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic real-world work tasks, Elo
Agentic interactive 3D experiences, Elo
Product and brand videos designed in code, Elo
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
Intelligence Index vs. Price
Pricing
Cost per Intelligence Index Task
Intelligence Index vs. Price
Speed
Average of the single-request and multi-turn agentic workloads measured
Time per Intelligence Index Task
Quality
Endpoint Accuracy Index
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate
Caching
Cache Hit Rate
Cost per Task vs. Cache Hit Rate
Further Analysis | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Claude Opus 5.5 (max) | 59 | $10.04 | 27.2 | 370.52 | 14.1% | 1M | Proprietary | |||
GPT-6 Astra (max) | 57 | $6.25 | 12.3 | 133.18 | 0.0% | 524k | Proprietary | |||
Claude Sonnet 5.5 (max) | 55 | $8.91 | 30.8 | 272.41 | 3.4% | 1M | Proprietary | |||
Kimi K3.1 Pro High Speed | 46 | $4.37 | 8.2 | 38.28 | 4.4% | 1M | Open | |||
Claude Opus 5 (max) | 44 | $11.82 | 24.2 | 64.61 | 2.6% | 1M | Proprietary | |||
Claude Opus 5.5 (low) | 35 | $0.98 | 3.4 | 7.53 | 3.8% | 1M | Proprietary | |||
GPT-5.6 Terra (max) | 32 | $3.77 | 9.9 | 79.42 | 0.0% | 1M | Proprietary | |||
Claude Sonnet 5.5 (low) | 26 | $0.48 | 2.6 | 2.50 | 0.0% | 1M | Proprietary | |||
GPT-5.6 Luna (max) | 24 | $0.35 | 4.3 | 28.04 | 0.0% | 1M | Proprietary | |||
Claude 4.5 Haiku | 7 | $0.49 | 2.3 | 22.25 | 0.0% | 200k | Proprietary | |||
gpt-oss-120b (high) | 4 | $0.35 | 13.7 | 28.52 | 1.5% | 131k | Open | |||
Qwen3 Coder 480B | -- | -- | -- | 2.22 | 1.9% | 262k | Open | |||
Claude 3.5 Sonnet (Oct) | -- | -- | -- | -- | -- | 200k | Proprietary | |||
Nova 2.0 Pro Preview (medium) | -- | -- | -- | 16.97 | 0.7% | 256k | Proprietary | |||
DeepSeek R1 (Jan) | -- | -- | -- | 13.85 | 0.0% | 128k | Open | |||
Claude Opus 5 (xhigh) | -- | -- | -- | -- | -- | 1M | Proprietary | |||
gpt-oss-20b (low) | -- | -- | -- | 8.81 | 4.0% | 131k | Open | |||
DeepSeek V3.1 | -- | -- | -- | 9.93 | 0.0% | 128k | Open | |||
Mistral Large 2 (Jul) | -- | -- | -- | -- | -- | 128k | Open | |||
GPT-5.5 (xhigh) | -- | -- | -- | 31.58 | 2.0% | 272k | Proprietary | |||
Claude 3 Haiku | -- | -- | -- | -- | -- | 200k | Proprietary | |||
Claude Opus 5 (low) | -- | -- | -- | 2.94 | 0.0% | 1M | Proprietary | |||
Mistral 7B | -- | -- | -- | 0.43 | 0.0% | 8k | Open | |||
Gemma 3 4B | -- | -- | -- | 1.47 | 0.0% | 128k | Open | |||
Claude Sonnet 5 (max) | -- | -- | -- | 149.22 | 0.0% | 1M | Proprietary | |||
Claude Opus 4.5 | -- | -- | -- | 18.44 | 0.0% | 200k | Proprietary | |||
Gemma 3 27B | -- | -- | -- | 3.17 | 0.0% | 128k | Open | |||
GLM-4.7-Flash | -- | -- | -- | 18.07 | 2.2% | 200k | Open | |||
Claude Sonnet 4.6 (non-reasoning, high) | -- | -- | -- | 1.59 | 0.0% | 200k | Proprietary | |||
Gemma 3 12B | -- | -- | -- | 2.25 | 0.0% | 128k | Open | |||
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | -- | -- | -- | 1.66 | 2.7% | 131k | Open | |||
Claude Opus 4.7 (non-reasoning, high) | -- | -- | -- | 1.74 | 0.0% | 1M | Proprietary | |||
Qwen3 235B 2507 | -- | -- | -- | 1.79 | 0.0% | 256k | Open | |||
Nova Micro | -- | -- | -- | 1.36 | 0.6% | 130k | Proprietary | |||
gpt-oss-20b (high) | -- | -- | -- | 31.43 | 2.0% | 131k | Open | |||
Mixtral 8x7B | -- | -- | -- | 0.71 | 0.0% | 33k | Open | |||
Claude Opus 4.5 (non-reasoning) | -- | -- | -- | 2.46 | 0.0% | 200k | Proprietary | |||
Claude Opus 4.6 (non-reasoning, high) | -- | -- | -- | 1.82 | 0.0% | 1M | Proprietary | |||
Llama 3.1 70B Standard | -- | -- | -- | -- | -- | 128k | Open | |||
Llama 3.1 70B Latency Optimized | -- | -- | -- | -- | -- | 128k | Open | |||
Mistral Large 3 | -- | -- | -- | 2.10 | 1.9% | 256k | Open | |||
GPT-5.4 (non-reasoning) | -- | -- | -- | 1.44 | 0.0% | 272k | Proprietary | |||
GPT-5.4 (low) | -- | -- | -- | -- | -- | 272k | Proprietary | |||
Claude Opus 4.6 (max) | -- | -- | -- | 24.26 | 0.0% | 1M | Proprietary | |||
Jamba 1.5 Mini | -- | -- | -- | -- | -- | 256k | Open | |||
Nova Pro | -- | -- | -- | 2.61 | 0.0% | 300k | Proprietary | |||
Nova Lite | -- | -- | -- | 1.60 | 0.0% | 300k | Proprietary | |||
Mistral Large (Feb) | -- | -- | -- | -- | -- | 33k | Proprietary | |||
Grok 4.3 (medium) | -- | -- | -- | -- | -- | 524k | Proprietary | |||
Nova 2.0 Lite (high) | -- | -- | -- | 19.26 | 0.7% | 1M | Proprietary | |||
Ministral 3 3B | -- | -- | -- | 1.47 | 0.7% | 256k | Open | |||
GPT-5.5 (medium) | -- | -- | -- | -- | -- | 272k | Proprietary | |||
DeepSeek V3.2 (non-reasoning) | -- | -- | -- | 2.70 | 0.0% | 128k | Open | |||
GPT-5.5 (non-reasoning) | -- | -- | -- | 1.31 | 0.0% | 272k | Proprietary | |||
GLM-4.7 | -- | -- | -- | 33.39 | 0.0% | 200k | Open | |||
Nova 2.0 Lite (low) | -- | -- | -- | 9.34 | 0.0% | 1M | Proprietary | |||
Magistral Small 1.2 | -- | -- | -- | 3.26 | 0.0% | 128k | Open | |||
Claude Opus 5 (high) | -- | -- | -- | -- | -- | 1M | Proprietary | |||
Ministral 3 14B | -- | -- | -- | 1.34 | 0.8% | 256k | Open | |||
Llama 3.1 8B | -- | -- | -- | -- | -- | 128k | Open | |||
Nova 2.0 Lite (non-reasoning) | -- | -- | -- | 1.76 | 0.0% | 1M | Proprietary | |||
GPT-5.6 Sol (non-reasoning) | -- | -- | -- | 1.07 | 0.0% | 1M | Proprietary | |||
GLM-4.7 (non-reasoning) | -- | -- | -- | 3.69 | 0.0% | 200k | Open | |||
Llama 3 8B | -- | -- | -- | -- | -- | 8k | Open | |||
Grok 4.3 (non-reasoning) | -- | -- | -- | 3.37 | 0.0% | 524k | Proprietary | |||
Claude 4.5 Sonnet | -- | -- | -- | 13.58 | 0.0% | 1M | Proprietary | |||
Claude 4.5 Sonnet (non-reasoning) | -- | -- | -- | 2.92 | 0.0% | 1M | Proprietary | |||
Llama 4 Maverick | -- | -- | -- | 1.08 | 0.0% | 128k | Open | |||
Grok 4.3 (high) | -- | -- | -- | 8.79 | 0.0% | 524k | Proprietary | |||
Ministral 3 8B | -- | -- | -- | 1.60 | 0.0% | 256k | Open | |||
Llama 3.3 70B | -- | -- | -- | 2.56 | 0.0% | 128k | Open | |||
Claude Opus 4.8 (max) | -- | -- | -- | 41.20 | 0.0% | 1M | Proprietary | |||
GPT-5.6 Terra (non-reasoning) | -- | -- | -- | 1.18 | 0.0% | 1M | Proprietary | |||
Nova 2.0 Pro Preview (non-reasoning) | -- | -- | -- | 1.36 | 0.0% | 256k | Proprietary | |||
Kimi K2.5 | -- | -- | -- | 36.35 | 0.0% | 256k | Open | |||
GPT-5.4 (xhigh) | -- | -- | -- | 63.71 | 2.1% | 272k | Proprietary | |||
Llama 3 70B | -- | -- | -- | 0.53 | 0.0% | 8k | Open | |||
NVIDIA Nemotron Nano 12B v2 VL (non-reasoning) | -- | -- | -- | 1.55 | 0.0% | 128k | Open | |||
Claude 3.5 Sonnet (June) | -- | -- | -- | -- | -- | 200k | Proprietary | |||
Llama 4 Scout | -- | -- | -- | 1.12 | 0.0% | 128k | Open | |||
GPT-5.5 (high) | -- | -- | -- | -- | -- | 272k | Proprietary | |||
Jamba 1.5 Large | -- | -- | -- | -- | -- | 256k | Open | |||
Kimi K2 Thinking | -- | -- | -- | 21.81 | 0.0% | 256k | Open | |||
Qwen3 32B (non-reasoning) | -- | -- | -- | 0.85 | 0.0% | 33k | Open | |||
Claude 4.5 Haiku (non-reasoning) | -- | -- | -- | 1.14 | 0.0% | 200k | Proprietary | |||
GPT-5.5 (low) | -- | -- | -- | -- | -- | 272k | Proprietary | |||
GLM-4.7-Flash (non-reasoning) | -- | -- | -- | 2.22 | 1.8% | 200k | Open | |||
gpt-oss-120b (low) | -- | -- | -- | 2.44 | 3.0% | 131k | Open | |||
Claude 4.1 Opus | -- | -- | -- | -- | -- | 200k | Proprietary | |||
Claude Sonnet 5 (non-reasoning) | -- | -- | -- | 1.37 | 0.0% | 1M | Proprietary | |||
DeepSeek V3.2 | -- | -- | -- | 17.61 | 4.9% | 128k | Open | |||
GPT-5.6 Sol (max) | -- | -- | -- | 78.80 | 0.0% | 1M | Proprietary | |||
Qwen3 Coder 30B A3B | -- | -- | -- | 1.88 | 0.0% | 262k | Open | |||
GPT-5.6 Luna (non-reasoning) | -- | -- | -- | 0.74 | 0.0% | 1M | Proprietary | |||
Claude Sonnet 4.6 (max) | -- | -- | -- | 67.97 | 0.0% | 200k | Proprietary | |||
Claude Opus 4.7 (max) | -- | -- | -- | 12.32 | 0.0% | 1M | Proprietary | |||
Claude 4.1 Opus (non-reasoning) | -- | -- | -- | -- | -- | 200k | Proprietary | |||
Nova 2.0 Pro Preview (low) | -- | -- | -- | 7.80 | 0.0% | 256k | Proprietary | |||
MiniMax-M2 | -- | -- | -- | 7.42 | 0.0% | 205k | Open | |||
Kimi K3 (max) | -- | -- | -- | 17.61 | 0.0% | 1M | Open | |||
DeepSeek V3.1 (non-reasoning) | -- | -- | -- | 2.55 | 2.6% | 128k | Open | |||
Nova 2.0 Lite (medium) | -- | -- | -- | 17.10 | 2.5% | 1M | Proprietary | |||
Qwen3 Coder Next | -- | -- | -- | 2.09 | 0.0% | 128k | Open | |||
Grok 4.3 (low) | -- | -- | -- | -- | -- | 524k | Proprietary | |||
Claude Opus 5 (medium) | -- | -- | -- | -- | -- | 1M | Proprietary | |||
Key definitions
Frequently Asked Questions
Common questions about Amazon Bedrock
Amazon Bedrock offers 83 models that we track: Claude Opus 5.5 (max), GPT-6 Astra (max), Claude Sonnet 5.5 (max), Kimi K3.1 Pro High Speed, Claude Opus 5 (max), Claude Opus 5.5 (low), GPT-5.6 Terra (max), Claude Sonnet 5.5 (low), GPT-5.6 Luna (max), Claude 4.5 Haiku, gpt-oss-120b (high), Qwen3 Coder 480B, Nova 2.0 Pro Preview (medium), DeepSeek R1 (Jan), gpt-oss-20b (low), DeepSeek V3.1, GPT-5.5 (xhigh), Claude Opus 5 (low), Mistral 7B, Gemma 3 4B, Claude Sonnet 5 (max), Claude Opus 4.5, Gemma 3 27B, GLM-4.7-Flash, Claude Sonnet 4.6 (non-reasoning, high), Gemma 3 12B, NVIDIA Nemotron Nano 9B V2 (non-reasoning), Claude Opus 4.7 (non-reasoning, high), Qwen3 235B 2507, Nova Micro, gpt-oss-20b (high), Mixtral 8x7B, Claude Opus 4.5 (non-reasoning), Claude Opus 4.6 (non-reasoning, high), Mistral Large 3, GPT-5.4 (non-reasoning), Claude Opus 4.6 (max), Nova Pro, Nova Lite, Nova 2.0 Lite (high), Ministral 3 3B, DeepSeek V3.2 (non-reasoning), GPT-5.5 (non-reasoning), GLM-4.7, Nova 2.0 Lite (low), Magistral Small 1.2, Ministral 3 14B, Nova 2.0 Lite (non-reasoning), GPT-5.6 Sol (non-reasoning), GLM-4.7 (non-reasoning), Grok 4.3 (non-reasoning), Claude 4.5 Sonnet, Claude 4.5 Sonnet (non-reasoning), Llama 4 Maverick, Grok 4.3 (high), Ministral 3 8B, Llama 3.3 70B, Claude Opus 4.8 (max), GPT-5.6 Terra (non-reasoning), Nova 2.0 Pro Preview (non-reasoning), Kimi K2.5, GPT-5.4 (xhigh), Llama 3 70B, NVIDIA Nemotron Nano 12B v2 VL (non-reasoning), Llama 4 Scout, Kimi K2 Thinking, Qwen3 32B (non-reasoning), Claude 4.5 Haiku (non-reasoning), GLM-4.7-Flash (non-reasoning), gpt-oss-120b (low), Claude Sonnet 5 (non-reasoning), DeepSeek V3.2, GPT-5.6 Sol (max), Qwen3 Coder 30B A3B, GPT-5.6 Luna (non-reasoning), Claude Sonnet 4.6 (max), Claude Opus 4.7 (max), Nova 2.0 Pro Preview (low), MiniMax-M2, Kimi K3 (max), DeepSeek V3.1 (non-reasoning), Nova 2.0 Lite (medium), and Qwen3 Coder Next.
The most intelligent model available on Amazon Bedrock is Claude Opus 5.5 (max) with an Intelligence Index score of 59.
The model with the lowest time per task on Amazon Bedrock is Claude 4.5 Haiku at 2.2 minutes per Intelligence Index task. Time per task is the output tokens per task divided by end-to-end output speed, so lower means a task finishes sooner.
The model with the lowest time to first answer token on Amazon Bedrock is Mistral 7B at 0.43s. Lower latency means faster initial response time.
The most affordable model on Amazon Bedrock by blended price is Nova Micro at $0.0271 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Amazon Bedrock vary up to 284.1x across models, from $0.0271 per 1M tokens for Nova Micro to $7.70 per 1M tokens for GPT-6 Astra (max).
19 of 83 models on Amazon Bedrock support JSON mode for structured output.
79 of 83 models on Amazon Bedrock support function calling (tool use).
Yes, Amazon Bedrock offers 41 reasoning models: Claude Opus 5.5 (max), GPT-6 Astra (max), Claude Sonnet 5.5 (max), Kimi K3.1 Pro High Speed, Claude Opus 5 (max), Claude Opus 5.5 (low), GPT-5.6 Terra (max), Claude Sonnet 5.5 (low), GPT-5.6 Luna (max), Claude 4.5 Haiku, gpt-oss-120b (high), Nova 2.0 Pro Preview (medium), DeepSeek R1 (Jan), gpt-oss-20b (low), DeepSeek V3.1, GPT-5.5 (xhigh), Claude Opus 5 (low), Claude Sonnet 5 (max), Claude Opus 4.5, GLM-4.7-Flash, gpt-oss-20b (high), Claude Opus 4.6 (max), Nova 2.0 Lite (high), GLM-4.7, Nova 2.0 Lite (low), Magistral Small 1.2, Claude 4.5 Sonnet, Grok 4.3 (high), Claude Opus 4.8 (max), Kimi K2.5, GPT-5.4 (xhigh), Kimi K2 Thinking, gpt-oss-120b (low), DeepSeek V3.2, GPT-5.6 Sol (max), Claude Sonnet 4.6 (max), Claude Opus 4.7 (max), Nova 2.0 Pro Preview (low), MiniMax-M2, Kimi K3 (max), and Nova 2.0 Lite (medium). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, 39 of 83 models on Amazon Bedrock are open weight models: Kimi K3.1 Pro High Speed, gpt-oss-120b (high), Qwen3 Coder 480B, DeepSeek R1 (Jan), gpt-oss-20b (low), DeepSeek V3.1, Mistral 7B, Gemma 3 4B, Gemma 3 27B, GLM-4.7-Flash, Gemma 3 12B, NVIDIA Nemotron Nano 9B V2 (non-reasoning), Qwen3 235B 2507, gpt-oss-20b (high), Mixtral 8x7B, Mistral Large 3, Ministral 3 3B, DeepSeek V3.2 (non-reasoning), GLM-4.7, Magistral Small 1.2, Ministral 3 14B, GLM-4.7 (non-reasoning), Llama 4 Maverick, Ministral 3 8B, Llama 3.3 70B, Kimi K2.5, Llama 3 70B, NVIDIA Nemotron Nano 12B v2 VL (non-reasoning), Llama 4 Scout, Kimi K2 Thinking, Qwen3 32B (non-reasoning), GLM-4.7-Flash (non-reasoning), gpt-oss-120b (low), DeepSeek V3.2, Qwen3 Coder 30B A3B, MiniMax-M2, Kimi K3 (max), DeepSeek V3.1 (non-reasoning), and Qwen3 Coder Next.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Amazon Bedrock, consider: intelligence (for quality-sensitive tasks), time per task (how quickly the model completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.