Model comparison
Llama 4 Scout 17B vs Mistral Medium 3.1
Llama 4 Scout 17B (Meta) and Mistral Medium 3.1 (Mistral) side by side: what each costs per million tokens through Rapid Router, how much context each takes, what each supports, and where independent benchmarks place them. Same API, same key; switching is a one-string change.
| Llama 4 Scout 17B | Mistral Medium 3.1 | |
|---|---|---|
| Input price per 1M | $0.100 | $0.400 |
| Output price per 1M | $0.300 | $2.00 |
| Context window | 328K tokens | 262K tokens |
| Max output | 16K tokens | 262K tokens |
| Input types | text, image | text, image |
| Capabilities | tools, JSON, vision | tools, vision |
| Author | Meta | Mistral |
| LMArena Overall | 1279 | 1424 |
| LMArena Coding | 1286 | 1433 |
| LMArena Math | 1287 | 1409 |
| LMArena Creative writing | 1249 | 1391 |
| LMArena Instruction following | 1248 | 1398 |
| LMArena Hard prompts | 1266 | 1426 |
| LMArena Vision | 1118 | 1172 |
| GPQA Diamond | 51.8% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath | 0.0% | — |
| OTIS Mock AIME | 7.8% | — |
Scores from LMArena and Epoch AI, as published; a blank cell means not measured there.
What a month costs on each
| Workload | Llama 4 Scout 17B | Mistral Medium 3.1 |
|---|---|---|
| Chatbot month (15M in, 4M out) | $2.70 | $14.00 |
| RAG month (40M in, 3M out) | $4.90 | $22.00 |
| Coding month (60M in, 10M out) | $9.00 | $44.00 |
On a typical 75/25 input-output mix, Llama 4 Scout 17B costs less (about 81% less than Mistral Medium 3.1). Llama 4 Scout 17B takes the longer prompt at 328K tokens. Try your own numbers in the cost calculator.
Call either one
curl https://rapidrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $RAPIDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "meta-llama/llama-4-scout-17b-16e-instruct", "messages": [{"role": "user", "content": "Hello"}]}'
# the other one: change the model string
-d '{"model": "mistralai/mistral-medium-2508", ...}'Common questions
Which is cheaper, Llama 4 Scout 17B or Mistral Medium 3.1?
Llama 4 Scout 17B is cheaper on a typical mix of 75% input and 25% output tokens, by about 81%. Through Rapid Router both are billed at the provider list price per million tokens.
Which has the larger context window?
Llama 4 Scout 17B, at 328K tokens. Mistral Medium 3.1 offers 262K tokens.
Can I switch between Llama 4 Scout 17B and Mistral Medium 3.1 without changing code?
Yes. Both are callable at https://rapidrouter.ai/api/v1 with the same OpenAI-compatible request; only the model string changes (meta-llama/llama-4-scout-17b-16e-instruct or mistralai/mistral-medium-2508).
How do I pay for Llama 4 Scout 17B or Mistral Medium 3.1?
Top up a Rapid Router balance by card in US dollars, and both models debit that balance per request.
More Llama models: Meta API pricing · More Mistral: Mistral API pricing