Models

Pick the right LLM
for every step.

18 models across 7 providers organized into 6 routing tiers. Ranked by real execution data with quality, speed, and value scores. No API key needed.

Models

Providers

Tiers

219

Outcomes

FrontierTop-of-the-line models for the hardest tasks. Maximum quality, highest cost.

Model	Context	Input $/1M	Output $/1M	Quality	Speed	Value Score	Badges
A Claude Opus 4 anthropic	200k	$15.00	$75.00	9.5	Slow	8.3	ToolsJSONVision
G Gemini 2.0 Pro google	2000k	$1.25	$5.00	9.5	Slow	9.6	ToolsJSONVision
O GPT-4.5 Preview openai	128k	$75.00	$150.00	9.5	Slow	7.4	ToolsJSONVision

Reasoning ProDeep reasoning and complex analysis. Extended thinking for multi-step problems.

Model	Context	Input $/1M	Output $/1M	Quality	Speed	Value Score	Badges
A Claude Sonnet 4.6 anthropic	200k	$3.00	$15.00	8.5	Slow	8.5	ToolsJSONVision
D DeepSeek R1 deepseek	128k	$0.55	$2.19	9.5	Slow	10.0
O O3 Mini openai	200k	$1.10	$4.40	9.5	Slow	9.6	ToolsJSON
O GPT-4o openai	128k	$2.50	$10.00	8.5	Slow	8.6	ToolsJSONVision

Tool AgentOptimized for tool calling and agentic workflows. Reliable structured output.

Model	Context	Input $/1M	Output $/1M	Quality	Speed	Value Score	Badges
G Gemini 2.0 Flash google	1049k	$0.10	$0.40	7.0	Slow	9.4	ToolsJSONVision
M Mistral Large mistral	128k	$2.00	$6.00	8.5	Slow	8.7	ToolsJSONVision

Fast CodeRapid code generation with solid quality. Best balance of speed and accuracy.

Model	Context	Input $/1M	Output $/1M	Quality	Speed	Value Score	Badges
D DeepSeek V3 deepseek	128k	$0.14	$0.28	8.5	Slow	10.0	ToolsJSON
M Codestral mistral	256k	$0.30	$0.90	7.0	Slow	8.8	JSON

EfficientCost-effective JSON and structured output. Reliable for high-volume pipelines.

Model	Context	Input $/1M	Output $/1M	Quality	Speed	Value Score	Badges
M Mistral Small mistral	128k	$0.20	$0.60	7.0	Slow	9.0	ToolsJSON
O GPT-4o Mini openai	128k	$0.15	$0.60	7.0	Slow	9.2	ToolsJSONVision

BudgetLowest cost for simple conversational tasks. High throughput, minimal spend.

Model	Context	Input $/1M	Output $/1M	Quality	Speed	Value Score	Badges
A Claude 3.5 Haiku anthropic	200k	$0.80	$4.00	7.0	Slow	8.3	ToolsJSONVision
A Claude 3.5 Sonnet anthropic	200k	$3.00	$15.00	8.5	Slow	8.5	ToolsJSONVision

Use the ToolRoute API or SDK to get optimal model recommendations for any task — with cost, quality, and speed scoring built in.

Pick the right LLMfor every step.