Sonar Pro Search vs Codestral 2508 compared — price per token, context window, multimodality, openness and which to choose. Full 2026 breakdown.
Sonar Pro Search — full profile › · Codestral 2508 — full profile ›
Prices & specs refreshed from live data · olud.ai
Open-model prices = cheapest provider via OpenRouter; official maker rates may be higher.
| Spec | Sonar Pro Search | Codestral 2508 | Winner |
|---|---|---|---|
| Maker | Perplexity | Mistral AI | – |
| Type | Proprietary | Proprietary | – |
| Context window | 200K tokens | 256K tokens | |
| Input price | $3/M | $0.3/M | |
| Output price | $15/M | $0.9/M | |
| Vision / multimodal | Yes | No | |
| Tool / function calling | No | Yes | |
| Self-hostable | No (API only) | No (API only) | – |
| License | Proprietary | Proprietary | – |
Codestral 2508 is ~17× cheaper than Sonar Pro Search on output tokens ($0.9 vs $15 per M tokens).
| Capability | Sonar Pro Search | Codestral 2508 |
|---|---|---|
| Open weights (downloadable) | ✗ | ✗ |
| Self-hostable | ✗ | ✗ |
| Runs fully offline | ✗ | ✗ |
| Vision / multimodal | ✓ | ✗ |
| Tool / function calling | ✗ | ✓ |
| 1M+ context window | ✗ | ✗ |
| Criterion | Sonar Pro Search | Codestral 2508 |
|---|---|---|
| Cost-efficiency | 3.0 | 5.0 |
| Context window | 4.0 | 4.0 |
| Openness | 1.5 | 1.5 |
| Self-hosting | 1.0 | 1.0 |
| Multimodality | 3.5 | 3.5 |
Scores come from live data — output price (cost), context length, open vs closed weights (openness & self-hosting) and vision/tool support (multimodality). Raw task quality isn't scored here; it depends on your benchmark — see the verdict.
Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/ne
Codestral 2508 is cheaper on output ($0.9/M vs $15/M).
Codestral 2508 offers the larger context window (256K tokens).
Choose Codestral 2508 for the lower output price ($0.9/M vs $15/M). It also gives you the larger 256K context window.
Browse the full open-source model leaderboard, thousands of tools and live benchmarks — all in one place.
Open the leaderboard →