Mistral Large 4 (Preview)
NEWMistral · mistral/mistral-large-4
Mistral's open-weight 1.05T-total, 52B-active multimodal MoE with reasoning and a 1M-token context, in public preview.
Not callable yet: Padma has not connected Mistral on this server. The price is real; requests answer 503 model_unavailable, and are not charged, until it is.
Input / 1M tokens
৳167.29
Output / 1M tokens
৳514.18
Cached input / 1M
৳17.22
Context length
1M
Max output
262.144K
Provider list price: $1.36 in · $4.18 out per 1M tokens (Mistral), × ৳123.01 per dollar. No markup.
Suitable for
- Reasoning
- Coding
- Vision
- Agents
- Long context
Example request
curl https://padmarouter.com/v1/chat/completions \
-H "Authorization: Bearer $PADMA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral/mistral-large-4",
"messages": [{"role": "user", "content": "Hello from Dhaka!"}]
}'Performance
Throughput60 tok/s
Time to first token1.4s
StreamingSupported
Tool callingSupported
Typical figures for this model, which the auto/* routers score on — not a guarantee for any one request.
Routing
Primary routeMistral direct
Fallback hostsNone — one host
Prompt retentionPadma keeps none unless you turn on payload logging; the provider's own API terms apply