modelsdev/gpt35instruct

modelsdev· 4K ctx

API only quant: unknown

spread (output)

1.1×

$1.80 – $2.00 · 5 providers

5 providers priced

Provider	Input	Output	Cache rd	Blended
Poe relay router	$1.40	$1.80	—	$1.44^*
Azure hyperscaler	$1.50	$2.00	—	$1.55^*
Azure Cognitive Services unknown	$1.50	$2.00	—	$1.55^*
Kilo Gateway relay router	$1.50	$2.00	—	$1.55^*
OpenRouter unknown	$1.50	$2.00	—	$1.55^*

Cheapest (output)

Poe

$1.80 /M

opencode.json

{
  "provider": {
    "poe": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.poe.com/v1"
      },
      "models": {
        "openai/gpt-3.5-turbo-instruct": {}
      }
    }
  }
}

Set POE_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time7-day preview

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Full price history & dynamics

This is a 7-day preview. Sign in for 30 days free; the full series and export are the API subscription.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.