jishie

Mistral Medium 3.5

greenpt/mistral-medium-3.5-128b · family mistral-medium · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

$4.10Blended $/1M (3:1)
$2.052Input $/1M
$10.26Output $/1M
$12.311M in + 1M out
Cache read $/1M
#4691 of 5,000Cheapest rank
Provider
GreenPT (greenpt)
Context
262,144 tokens
Max output
16,384 tokens
Capabilities
toolsreasoningtextimage

Same model, other providers

“Mistral Medium 3.5” is offered by 7 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Nvidiafreefree$0.00262k
NanoGPT$1.5$7.5$3.00256k
Pioneer$1.5$7.5$3.00262k
Mistral$1.5$7.5$3.00262k
OpenRouter$1.5$7.5$3.00262k
evroc$1.725$6.9$3.02262k
GreenPT (this)$2.052$10.26$4.10262k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at GreenPT and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"mistral-medium-3.5-128b","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):