Best LLM APIs for Reasoning Tasks
LLM APIs specialized for reasoning and complex problem solving. Compare pricing for models optimized for math, logic, and multi-step inference.
Cost calculator for this use case
🥇 DeepSeek V4 Flash
$—
🥈 DeepSeek V4 Pro
$—
🥉 NVIDIA Nemotron 3 Ultra
$—
Full ranking — top 15 models
| # | Model | Provider | Input $/Mtok | Output $/Mtok | Blended | Context | |
|---|---|---|---|---|---|---|---|
| 1 | DeepSeek V4 Flash | DeepSeek | $0.140 | $0.280 | $0.210 | 1M | → |
| 2 | DeepSeek V4 Pro | DeepSeek | $0.435 | $0.870 | $0.652 | 1M | → |
| 3 | NVIDIA Nemotron 3 Ultra | Fireworks | $0.600 | $2.40 | $1.50 | 128K | → |
| 4 | QwQ-Plus | Alibaba | $0.800 | $2.40 | $1.60 | 131K | → |
| 5 | Llama Nemotron Ultra 253B | NVIDIA | $0.600 | $3.60 | $2.10 | 128K | → |
| 6 | Nemotron 3 Ultra | NVIDIA | $0.600 | $3.60 | $2.10 | 128K | → |
| 7 | NVIDIA Nemotron 3 Ultra | Together | $0.600 | $3.60 | $2.10 | 128K | → |
| 8 | DeepSeek V4 Pro | Fireworks | $1.74 | $3.48 | $2.61 | 1M | → |
| 9 | DeepSeek V4 Pro | Together | $1.74 | $3.48 | $2.61 | 1M | → |
| 10 | o3-mini | OpenAI | $1.10 | $4.40 | $2.75 | 200K | → |
| 11 | o4-mini | OpenAI | $1.10 | $4.40 | $2.75 | 200K | → |
| 12 | Magistral Medium | Mistral | $2.00 | $5.00 | $3.50 | 128K | → |
| 13 | Sonar Deep Research | Perplexity | $2.00 | $8.00 | $5.00 | 200K | → |
| 14 | Sonar Reasoning Pro | Perplexity | $2.00 | $8.00 | $5.00 | 200K | → |
| 15 | Gemini 2.5 Pro | $1.25 | $10.00 | $5.63 | 2M | → |
How models are selected
Models tagged for reasoning, sorted by blended cost.
Prices are per million tokens (Mtok), sourced directly from official provider pricing pages and verified by our automated scraper pipeline that runs 3x daily. "Blended cost" is the average of input and output pricing — a quick proxy for typical 50/50 usage patterns.