Side by side
Llama 3.3 70B Instruct vs Voxtral Small 24B 2507
Source: OpenRouter (live)
Live figures
The numbers
Best value in each row is highlighted. "Not declared" means the provider does not advertise the feature on its listing.
| Attribute | ||
|---|---|---|
| Input priceUSD per 1M tokens | $0.10 | $0.10 |
| Output priceUSD per 1M tokens | $0.32 | $0.30 (best) |
| Blended price75% in / 25% out | $0.15 | $0.15 (best) |
| Vs. market median | 83% cheaper | 83% cheaper |
| Value rankcheapest = 1 | #73 | #68 (best) |
| Context windowtokens | 131K (best) | 33K |
| Max outputtokens | 16K | 26K (best) |
| Input modalities | text | text, audio, file |
| Output modalities | text | text |
| Tool calling | Declared | Declared |
| Reasoning | Not declared | Not declared |
| Structured output | Declared | Declared |
| Listed on OpenRouter | 2024-12-06 | 2025-10-30 (best) |
Blended price assumes a 3:1 input-to-output token mix. Median is across all 429 priced models.
Add or swap modelsCost calculator
At your volume
Estimate the monthly bill for these models at your own token volumes.
| Model | Input | Output | Monthly | Yearly | vs cheapest | |
|---|---|---|---|---|---|---|
| Mistral: Voxtral Small 24B 2507 Mistral · $0.100 in / $0.300 out per M | $5.00 | $4.50 | $9.50 | $114 | Cheapest | |
| Meta: Llama 3.3 70B Instruct Meta · $0.100 in / $0.320 out per M | $5.00 | $4.80 | $9.80 | $118 | +$0.300 (1.0×) |
Estimates use list prices per million tokens from live provider listings. Cached-input, batch and volume discounts are not included, so real bills are often lower.
Read-out
What the numbers say
- Mistral: Voxtral Small 24B 2507 is the cheapest here at $0.15/M blended; Meta: Llama 3.3 70B Instruct costs 3% more.
- Meta: Llama 3.3 70B Instruct offers the largest context window (131K tokens) versus 33K for Mistral: Voxtral Small 24B 2507.
Models
Model pages
Full pricing history, capabilities and alternatives for each model in this comparison.
$0.155
/M blended
$0.150
/M blended
More comparisons
Other head-to-heads
- Claude vs GPT-5: which frontier model should you pay for?
Anthropic's flagship Claude against OpenAI's GPT-5 line on price, context and declared capabilities, with live figures.
- Claude Sonnet vs GPT-5 Mini: the mid-tier workhorses
The two models most production apps actually run. How the price gap compares to the capability gap.
- Gemini vs GPT-5: Google's flagship against OpenAI's
Gemini's very long context and multimodal input against GPT-5's ecosystem and pricing.
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.