API Market



MistralFastest
Codestral 3 API
Low-latency code completion
Fill-in-the-middle completion tuned for editor integrations, where every 100ms is visible to the user.
ChatTool useStreaming256K context
Quickstart
Authenticate with a bearer token from your dashboard, then POST the request below.
curl -X POST https://api.viddly.io/v1/chat/completions \
-H "Authorization: Bearer $VIDDLY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "codestral-3",
"messages": [
{
"role": "user",
"content": "Explain retrieval augmented generation in two sentences."
}
],
"max_tokens": 512
}'Parameters
| Name | Type | Default | Description |
|---|---|---|---|
| messages* | text | — | Chat messages array, OpenAI-compatible. |
| max_tokens | number | 1024 | Upper bound on generated tokens. |
| temperature | number | 0.7 | Sampling temperature, 0–2. |
| stream | boolean | false | Stream tokens as server-sent events. |
Similar models
OpenAIPopular
OpenAI
GPT-5.2
ChatReasoning
OpenAI's frontier model for general reasoning and tool use
Try it$3.39 / 1M input tokens~3s
OpenAIBest price
OpenAI
GPT-5.2 Mini
ChatReasoning
Most of the capability at a fraction of the price
Try it$0.455 / 1M input tokens~1s
OpenAI
OpenAI
o5 Reasoning
ReasoningCoding
Extended deliberation for maths, proofs and planning
Try it$9.60 / 1M input tokens~22s


