Padma
← All models

Mistral Large

Mistral · mistral/mistral-large

Available

European-hosted general model with strong function calling and multilingual coverage across Latin scripts.

Input / 1M tokens

৳240

Output / 1M tokens

৳720

Context length

128K

Max output

16K

Placeholder rates. Final pricing is published per model before launch.

Suitable for

  • Reasoning
  • Coding
  • Agents

Example request

cURL
curl https://padmarouter.com/v1/chat/completions \
  -H "Authorization: Bearer $PADMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/mistral-large",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Performance

Throughput82 tok/s
Time to first token1.0s
StreamingSupported
Tool callingSupported

Measured from Dhaka over the last 24h of prototype traffic.

Routing

Primary routeMistral direct
FallbackSecondary region
Prompt retentionNot retained