Skip to main content
AI HQ

Type at least two characters. Try a model (“gpt-5 mini”), a provider (“anthropic”), or a topic (“coding”).

↑↓ navigate · ↵ open · esc closeLive data from OpenRouter

Compare

Compare AI models side by side

Choose up to 4 models. Prices, context windows and declared capabilities are read live from the OpenRouter listing, so the table reflects what the providers publish today.

DeepSeekR1 Distill Llama 70BDeepSeekDeepSeek V4 Flash Vision Exp
Share this comparison with the canonical link below the table.
Side-by-side comparison of DeepSeek: R1 Distill Llama 70B, DeepSeek: DeepSeek V4 Flash Vision Exp
Attribute
DeepSeekR1 Distill Llama 70Bdeepseek/deepseek-r1-distill-llama-70b
DeepSeekDeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp
Input priceUSD per 1M tokens$0.80$0.22 (best)
Output priceUSD per 1M tokens$0.80$0.66 (best)
Blended price75% in / 25% out$0.80$0.33 (best)
Vs. market median0% cheaper59% cheaper
Value rankcheapest = 1#206#113 (best)
Context windowtokens8K1.0M (best)
Max outputtokens7K944K (best)
Input modalitiestexttext, image
Output modalitiestexttext
Tool callingNot declaredDeclared
ReasoningDeclaredDeclared
Structured outputNot declaredDeclared
Listed on OpenRouter2025-01-232026-08-21 (best)

Source: OpenRouter (live)

Permanent link to this comparison

Read-out

What the numbers say

  • DeepSeek: DeepSeek V4 Flash Vision Exp is the cheapest here at $0.33/M blended — 2.4× less than DeepSeek: R1 Distill Llama 70B.
  • DeepSeek: DeepSeek V4 Flash Vision Exp offers the largest context window (1.0M tokens) versus 8K for DeepSeek: R1 Distill Llama 70B.
  • Tool calling is declared for DeepSeek: DeepSeek V4 Flash Vision Exp only.

Generated from the live figures above. Capabilities are what each provider declares on its listing.

Curated

Head-to-heads we keep up to date

Each comparison resolves to the newest models in the named families and carries our own guidance on which to choose.

Newsletter

Stay Ahead of AI

Get the most important developments in artificial intelligence delivered directly to your inbox.

No hype. No spam.

Just trusted insights, major model releases, pricing updates, benchmark changes, product reviews, and practical guidance from across the AI ecosystem.

  • Weekly AI Briefing
  • Major Model Releases
  • Pricing & Benchmark Updates
  • Unsubscribe Anytime

The AI HQ Briefing

One email a week. Read in five minutes.

By subscribing you agree to receive the AI HQ newsletter. Your address is processed by our email delivery provider and never sold. Unsubscribe anytime.