GeniusRelay
EN中文Sign upConsole

Mistral: Mistral Medium 3.5

mistralai-medium-3.5

CompareAPIGet an API keyGet an API key

Mistral Medium 3.5 is a 128B dense open-weights flagship model for instruction-following, reasoning, coding, long-horizon agentic work, tool use, structured output, and multimodal prompts. It supports a 256k context window and configurable reasoning effort.

Modalities

Text + Image → Text

Input / output price

$1.95 / $9.75 per 1M

Context

256K · max output 33K

Capabilities

ReasoningVisionTool callingLong contextOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$1.95
Output$9.75
Cached input$0.975

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.0137
Per day
$6.83
Per month (30 days)
$204.75

Mistral Medium 3.5: input $1.95/M · output $9.75/M · cached input $0.975/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mistralai-medium-3.5", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to mistralai-medium-3.5.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai-medium-3.5",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Mistral Medium 3.5 billed?
Input is $1.95 and output is $9.75 per million tokens; cached input is $0.975. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
256K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.