GeniusRelay
Sign upConsole

Mistral: Mistral Devstral Small 2505

devstral-small-2505

CompareAPIGet an API keyGet an API key

Mistral Devstral Small 2505 costs $0.078 per million input tokens and $0.078 per million output tokens, supports 33K context, and is available through the OpenAI-compatible API.

OpenHands+Devstral is 100% local 100% open, and is SOTA for the category on SWE-Bench Verified: 46.8% accuracy.

Modalities

Text → Text

Input / output price

$0.078 / $0.078 per 1M

Context

33K · max output 8K

Capabilities

CodingOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.078
Output$0.078
Cached input$0.039

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00030
Per day
$0.1482
Per month (30 days)
$4.45

Mistral Devstral Small 2505: input $0.078/M · output $0.078/M · cached input $0.039/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": "devstral-small-2505", "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 devstral-small-2505.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "devstral-small-2505",
    "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 Devstral Small 2505 billed?
Input is $0.078 and output is $0.078 per million tokens; cached input is $0.039. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
33K 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.
Mistral Devstral Small 2505 API pricing · GeniusRelay