DevBolt
Processed in your browser. Your data never leaves your device.
← Back to tools

AI Model Comparison

Compare pricing, context windows, and capabilities of 21 models from 7 providers. Updated March 2026.

CompareModelInput $/1MOutput $/1MContext
GPT-4.1 nano
OpenAI
budget
$0.10$0.401M
Gemini 2.0 Flash
Google
budget
$0.10$0.401M
GPT-4o mini
OpenAI
budget
$0.15$0.60128K
Gemini 2.5 Flash
Google
mid
$0.15$0.601M
Llama 4 Scout
Meta
mid
$0.20$0.20524K
DeepSeek V3
DeepSeek
mid
$0.27$1.10131K
Codestral
Mistral
mid
$0.30$0.90256K
Grok 3 mini
xAI
mid
$0.30$0.50131K
GPT-4.1 mini
OpenAI
mid
$0.40$1.601M
Llama 4 Maverick
Meta
flagship
$0.50$0.501M
DeepSeek R1
DeepSeek
flagship
$0.55$2.19131K
Claude 3.5 Haiku
Anthropic
budget
$0.80$4.00200K
o4-mini
OpenAI
mid
$1.10$4.40200K
Gemini 2.5 Pro
Google
flagship
$1.25$10.001M
GPT-4.1
OpenAI
flagship
$2.00$8.001M
o3
OpenAI
flagship
$2.00$8.00200K
Mistral Large
Mistral
flagship
$2.00$6.00128K
GPT-4o
OpenAI
flagship
$2.50$10.00128K
Claude Sonnet 4
Anthropic
mid
$3.00$15.00200K
Grok 3
xAI
flagship
$3.00$15.00131K
Claude Opus 4
Anthropic
flagship
$15.00$75.00200K
21
Models
$0.10
Cheapest Input /1M
1M
Largest Context
9
Reasoning Models

About This Comparison

Pricing reflects publicly listed API prices as of March 2026. Actual costs may vary with batch pricing, prompt caching, or volume discounts. Meta/Llama prices are based on common API providers (Together, Fireworks).

Tiers: Flagship = most capable model in the family, Mid = balanced cost/performance, Budget = cheapest option.

Capabilities: Vision = image/document input, Reasoning = built-in chain-of-thought or thinking, Tools = function calling / tool use, OSS = open-source weights available.

Related Inspect Tools