Model Capabilities Comparison

Compare vision, tools, reasoning and caching support.

Result

Model capabilities compared

43 models

Model	Provider	Vision	Tools	Reasoning	Caching
GPT-5.4	openai	Yes	Yes	Yes	Yes
GPT-5	openai	Yes	Yes	Yes	Yes
GPT-5 Mini	openai	Yes	Yes	Yes	Yes
GPT-4.1	openai	Yes	Yes	No	Yes
GPT-4.1 Mini	openai	Yes	Yes	No	Yes
GPT-4.1 Nano	openai	No	Yes	No	Yes
GPT-4o	openai	Yes	Yes	No	Yes
GPT-4o mini	openai	Yes	Yes	No	Yes
o3	openai	Yes	Yes	Yes	Yes
o4-mini	openai	Yes	Yes	Yes	Yes
Claude Opus 4.8	anthropic	Yes	Yes	Yes	Yes
Claude Opus 4.6	anthropic	Yes	Yes	Yes	Yes
Claude Sonnet 4.6	anthropic	Yes	Yes	Yes	Yes
Claude Sonnet 5	anthropic	Yes	Yes	Yes	Yes
Claude Haiku 4.5	anthropic	No	Yes	No	Yes
Claude Fable 5	anthropic	No	Yes	Yes	Yes
Gemini 2.5 Pro	google	Yes	Yes	Yes	Yes
Gemini 2.5 Flash	google	Yes	Yes	Yes	Yes
Gemini 2.5 Flash-Lite	google	Yes	Yes	No	Yes
Amazon Nova Premier	aws-bedrock	Yes	Yes	Yes	No
Amazon Nova Pro	aws-bedrock	Yes	Yes	No	No
Amazon Nova Lite	aws-bedrock	Yes	Yes	No	No
Amazon Nova Micro	aws-bedrock	No	Yes	No	No
Llama 4 Maverick	meta	Yes	Yes	No	No
Llama 4 Scout	meta	Yes	Yes	No	No
Llama 3.3 70B	meta	No	Yes	No	No
Mistral Large 3	mistral	Yes	Yes	No	No
Mistral Medium 3.1	mistral	Yes	Yes	No	No
Mistral Small 4	mistral	No	Yes	No	No
Devstral 2	mistral	No	Yes	No	No
DeepSeek V4 Flash	deepseek	No	Yes	No	Yes
DeepSeek V4 Pro	deepseek	No	Yes	Yes	Yes
DeepSeek V3.2	deepseek	No	Yes	No	Yes
Command A	cohere	No	Yes	Yes	No
Command R+	cohere	No	Yes	No	No
Command R	cohere	No	Yes	No	No
Command R7B	cohere	No	Yes	No	No
Grok 4.5	xai	Yes	Yes	Yes	Yes
Grok 4.3	xai	Yes	Yes	Yes	Yes
Sonar	perplexity	No	No	No	No
Sonar Pro	perplexity	No	No	No	No
Sonar Reasoning Pro	perplexity	No	No	Yes	No
Sonar Deep Research	perplexity	No	No	Yes	No

Compare which models support vision, tool use, reasoning and prompt caching in one table, so you can shortlist by capability, not just price.

How this is calculated

This calculator uses the comparisons formulas described in our methodology. All figures are estimates for planning; verify current pricing with each provider before relying on them.

Worked example (defaults)

With the default inputs above, here is the result:

Result

Model capabilities compared

43 models

Model	Provider	Vision	Tools	Reasoning	Caching
GPT-5.4	openai	Yes	Yes	Yes	Yes
GPT-5	openai	Yes	Yes	Yes	Yes
GPT-5 Mini	openai	Yes	Yes	Yes	Yes
GPT-4.1	openai	Yes	Yes	No	Yes
GPT-4.1 Mini	openai	Yes	Yes	No	Yes
GPT-4.1 Nano	openai	No	Yes	No	Yes
GPT-4o	openai	Yes	Yes	No	Yes
GPT-4o mini	openai	Yes	Yes	No	Yes
o3	openai	Yes	Yes	Yes	Yes
o4-mini	openai	Yes	Yes	Yes	Yes
Claude Opus 4.8	anthropic	Yes	Yes	Yes	Yes
Claude Opus 4.6	anthropic	Yes	Yes	Yes	Yes
Claude Sonnet 4.6	anthropic	Yes	Yes	Yes	Yes
Claude Sonnet 5	anthropic	Yes	Yes	Yes	Yes
Claude Haiku 4.5	anthropic	No	Yes	No	Yes
Claude Fable 5	anthropic	No	Yes	Yes	Yes
Gemini 2.5 Pro	google	Yes	Yes	Yes	Yes
Gemini 2.5 Flash	google	Yes	Yes	Yes	Yes
Gemini 2.5 Flash-Lite	google	Yes	Yes	No	Yes
Amazon Nova Premier	aws-bedrock	Yes	Yes	Yes	No
Amazon Nova Pro	aws-bedrock	Yes	Yes	No	No
Amazon Nova Lite	aws-bedrock	Yes	Yes	No	No
Amazon Nova Micro	aws-bedrock	No	Yes	No	No
Llama 4 Maverick	meta	Yes	Yes	No	No
Llama 4 Scout	meta	Yes	Yes	No	No
Llama 3.3 70B	meta	No	Yes	No	No
Mistral Large 3	mistral	Yes	Yes	No	No
Mistral Medium 3.1	mistral	Yes	Yes	No	No
Mistral Small 4	mistral	No	Yes	No	No
Devstral 2	mistral	No	Yes	No	No
DeepSeek V4 Flash	deepseek	No	Yes	No	Yes
DeepSeek V4 Pro	deepseek	No	Yes	Yes	Yes
DeepSeek V3.2	deepseek	No	Yes	No	Yes
Command A	cohere	No	Yes	Yes	No
Command R+	cohere	No	Yes	No	No
Command R	cohere	No	Yes	No	No
Command R7B	cohere	No	Yes	No	No
Grok 4.5	xai	Yes	Yes	Yes	Yes
Grok 4.3	xai	Yes	Yes	Yes	Yes
Sonar	perplexity	No	No	No	No
Sonar Pro	perplexity	No	No	No	No
Sonar Reasoning Pro	perplexity	No	No	Yes	No
Sonar Deep Research	perplexity	No	No	Yes	No

Frequently asked questions

Do all models support tool use?+

Most current flagships do, but support for vision, reasoning and prompt caching varies. Use this table to filter models by the features you need.

Related calculators

Comparisons

Model Context Window Comparison

Compare context windows across all models.

Comparisons

LLM Pricing Comparison

Compare input, output and cached prices across models.

Comparisons

LLM Model Cost Comparison

Compare the cost of every model for the same workload.