Mistral Large 3
Mistral · released 2026-02-01
Quality (AA Index)82
Input price$2.00
Output price$6.00
Context128K
Throughput140 tok/s
P50 latency0.9s
Side-by-side pricing, capabilities, real-world cost across common scenarios, and our editorial pick.
Mistral · released 2026-02-01
OpenAI · released 2026-01-15
链接通过我们的 OpenRouter 推荐链接在新标签页打开。 查看推广披露
| Metric | Mistral Large 3 | GPT-5 | Verdict |
|---|---|---|---|
Input price /百万 tokens | $2.00 | $1.25 | GPT-5 −38% |
Output price /百万 tokens | $6.00 | $10.00 | Mistral Large 3 −40% |
Context window max input length | 128K | 400K | GPT-5 +3.1× |
AA Quality AA Intelligence Index (0–100) | 82 | 91 | GPT-5 +9pt |
Arena Elo LMArena human-pref Elo (800–2000) | — | — | Tied |
Throughput tokens per second | 140 | 120 | Mistral Large 3 +17% |
P50 latency first token | 0.9s | 0.7s | GPT-5 −22% |
Vision multimodal | — | ||
Function calling tool use | Tied | ||
Reasoning mode chain-of-thought | — |
| Scenario | Mistral Large 3 | GPT-5 |
|---|---|---|
customer support 1000K req · 600/180 tok | $2.3K | $2.5K |
chat with docs 300K req · 4000/300 tok | $2.9K | $2.4K |
code generation 500K req · 2000/500 tok | $3.5K | $3.8K |
voice assistant 600K req · 800/200 tok | $1.7K | $1.8K |
Best across-the-board quality but the most expensive token rate in the table; pick GPT-5 when reasoning depth or function-calling reliability outranks per-million-token spend.
Set GPT-5 as primary, Mistral Large 3 as fallback. One key, one bill, automatic failover when GPT-5 errors.
$ curl https://api.aipricly.com/v1/chat/completions \
-H "Authorization: Bearer $AIPC_KEY" \
-d '{
"routing": {
"primary": "openai/gpt-5",
"fallback": ["mistral/mistral-large-3"]
},
"messages": [{"role": "user", "content": "..."}]
}'