91Fit score
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, m…
Model details →Best AI reasoning models
Reasoning models (o-series, Claude thinking, DeepSeek R1, Gemini Thinking) trade latency for quality on hard problems. Pricing reflects extra reasoning tokens.
91Fit score
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, m…
Model details →91Fit score
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide…
Model details →Top 25 models for step-by-step reasoning
| # | Model | Provider | Context | Input price / 1M | Tier |
|---|---|---|---|---|---|
| 1 | Anthropic: Claude Sonnet 5 | Anthropic | 1M Ultra context (1M+) | $2.00 | Standard |
| 2 | Anthropic: Claude Sonnet 5 (batch) | Anthropic | 1M Ultra context (1M+) | $1.00 | Standard |
| 3 | Google: Gemini 2.5 Flash | 1.0M Ultra context (1M+) | $0.30 | Budget | |
| 4 | Google: Gemini 2.5 Flash (batch) | 1.0M Ultra context (1M+) | $0.15 | Budget | |
| 5 | Google: Gemini 2.5 Flash Lite Preview 09-2025 | 1.0M Ultra context (1M+) | $0.10 | Budget | |
| 6 | Google: Gemini 2.5 Pro | 1.0M Ultra context (1M+) | $1.25 | Standard | |
| 7 | Google: Gemini 2.5 Pro (batch) | 1.0M Ultra context (1M+) | $0.63 | Budget | |
| 8 | Google: Gemini 2.5 Pro Preview 05-06 | 1.0M Ultra context (1M+) | $1.25 | Standard | |
| 9 | Google: Gemini 2.5 Pro Preview 06-05 | 1.0M Ultra context (1M+) | $1.25 | Standard | |
| 10 | Google: Gemini 3 Flash Preview | 1.0M Ultra context (1M+) | $0.50 | Budget | |
| 11 | Google: Gemini 3 Flash Preview (batch) | 1.0M Ultra context (1M+) | $0.25 | Budget | |
| 12 | Qwen: Qwen Plus 0728 (thinking) | Qwen | 1M Ultra context (1M+) | $0.26 | Budget |
| 13 | Qwen: Qwen3.8 27B | Qwen | 1M Ultra context (1M+) | $0.04 | Budget |
| 14 | Thinking Machines: Inkling (free) | Thinkingmachines | 1.0M Ultra context (1M+) | $0.00 | Budget |
| 15 | Thinking Machines: Inkling Small (free) | Thinkingmachines | 1.0M Ultra context (1M+) | $0.00 | Budget |
| 16 | Anthropic: Claude 3.7 Sonnet (thinking) | Anthropic | 200K Long context (128K+) | $3.00 | Standard |
| 17 | Arcee AI: Trinity Large Thinking | Arcee Ai | 262K Long context (128K+) | $0.25 | Budget |
| 18 | ByteDance Seed: Seed 1.6 | Bytedance Seed | 262K Long context (128K+) | $0.25 | Budget |
| 19 | ByteDance Seed: Seed 1.6 Flash | Bytedance Seed | 262K Long context (128K+) | $0.07 | Budget |
| 20 | Google: Gemma 4 31B | 262K Long context (128K+) | $0.09 | Budget | |
| 21 | Google: Gemma 4 31B (batch) | 262K Long context (128K+) | $0.39 | Budget | |
| 22 | Google: Gemma 4 31B (free) | 262K Long context (128K+) | $0.00 | Budget | |
| 23 | inclusionAI: Ring-2.6-1T | Inclusionai | 262K Long context (128K+) | $0.07 | Budget |
| 24 | MoonshotAI: Kimi K2 Thinking | Moonshotai | 262K Long context (128K+) | $0.60 | Budget |
| 25 | OpenAI: o1 | OpenAI | 200K Long context (128K+) | $15.00 | Premium |
Frequently asked questions
What is a reasoning model?
A model that produces internal reasoning tokens before its final answer. Useful for hard math, scientific problems, code planning, and agentic workflows where step-by-step logic matters.
Are reasoning models more expensive?
Usually yes — you pay for the hidden reasoning tokens too. The trade-off is much higher accuracy on hard problems.
Related use cases
AI models for codingAI vision modelslong-context AI models (128K+)AI models for function callingAI models for structured / JSON outputsAI models for agentsfree AI modelsCheapest AI models per tokenmultilingual AI modelsembedding modelssmall / on-device AI modelsAI image generation modelsAI voice / audio modelsAI models for mathAI models for writingopen-source AI modelsAI models for RAGAI models for summarizationAI models for translationAI models for enterprise