Get API key

Mistral: Mistral Medium 3.5

1 provider live
mistralai/mistral-medium-3-5
→
  • 1 live provider
  • 100% uptime
  • 0.58 s first token
  • 65 tok/s output

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.

Context
180K
tokens
Max output
16K
tokens
Input
$1.7286
per million tokens
Output
$8.6428
per million tokens

Providers

Ranked by price and speed. Requests go to the best healthy provider, then fail over down the list.
#ProviderInputOutputCache readLatencyThroughputUptime (3d)
1
Data policy not declared
$1.7286$8.6428n/a0.58 s65 tok/s100%
Want to serve this model?Become a provider

Price history

Input price since Oct 21, 2026, in USD per million tokens.

Data table
ProviderFromInputOutput
ScalewayOct 21, 2026$1.7328$8.6636
ScalewayOct 22, 2026$1.7357$8.6783
ScalewayOct 22, 2026$1.7312$8.6559
ScalewayOct 23, 2026$1.7294$8.6466
ScalewayOct 26, 2026$1.7286$8.6428

Performance

Last 24 hours, from llm.buzz's test requests

Throughput (tok/s)

  • Scaleway65 tok/s
Data table
ProviderFrom (UTC)p50p90p99
ScalewayOct 26, 08:0054 tok/s54 tok/s54 tok/s
ScalewayOct 26, 12:0065 tok/s65 tok/s65 tok/s
ScalewayOct 26, 17:0065 tok/s65 tok/s65 tok/s
ScalewayOct 26, 22:0065 tok/s65 tok/s65 tok/s
ScalewayOct 27, 02:0065 tok/s65 tok/s65 tok/s
ScalewayLast 24 hours65 tok/s54 tok/s54 tok/s

Latency (time to first token)

  • Scaleway0.58 s
Data table
ProviderFrom (UTC)p50p90p99
ScalewayOct 26, 08:000.69 s0.69 s0.69 s
ScalewayOct 26, 12:000.33 s0.33 s0.33 s
ScalewayOct 26, 17:000.28 s0.28 s0.28 s
ScalewayOct 26, 22:000.69 s0.69 s0.69 s
ScalewayOct 27, 02:000.58 s0.58 s0.58 s
ScalewayLast 24 hours0.58 s0.69 s0.69 s

Uptime

Last 72 hours, by hour
Best provider 100%
This model
Scaleway
  • Up: 95% or more served
  • Degraded: 85% to 95%
  • Down: below 85%
  • No data
  • From llm.buzz's test requests

Questions

How much does Mistral: Mistral Medium 3.5 cost?

Mistral: Mistral Medium 3.5 costs $1.7286 per million input tokens and $8.6428 per million output tokens at Scaleway, the provider requests go to first.

Do providers train on my prompts?

Each provider declares it, and the table above shows every declaration. You can limit a request to providers that keep nothing, or to providers in the EU.

Can I serve Mistral: Mistral Medium 3.5 myself?

Yes. Apply as a provider, add your endpoint and list this model at your price. It goes live once the automated check passes.

Similar models

Call Mistral: Mistral Medium 3.5 with one keyEach request pays the price of the provider that answered it.