Ember-1

ember-1

ember-1· 2026-09-22· 1.0M ctx

API onlytool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

— too few providers

$15.00 – $15.00 · 1 providers · max÷min 1.0×

1 provider priced · 1 offering

Including routers & resellers

Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.

Provider classes in the stats:

Blended $/M assumptionsInput : output: 1Cache-hit share of input%

blended = 90.9% input × [(1 − 70% cache) × input + 70% cache × cache-read] + 9.1% × output + cache writes (30% of uncached input) where a write price is published

A provider that publishes no cache price is blended with cache share 0 (all input at the input price) and labelled “no cache price published” — never penalised against identical in/out prices.

Provider	Input	Output	Cache rd	Blended
Cloudflare AI Gateway router / aggregator	$3.00	$15.00	$0.30	$2.37
Fireworks AI inference host	$3.00	$15.00	$0.30	$2.37
Kilo Gateway router / aggregator	$3.00	$15.00	$0.30	$2.37
NanoGPT router / aggregator	$3.00	$15.00	$0.30	$2.37
OpenRouter router / aggregator	$3.00	$15.00	$0.30	$2.37
Vercel AI Gateway router / aggregator	$3.00	$15.00	$0.30	$2.37

Connect

Provider (default: cheapest output among direct providers)

$15.00 /M · inference host

opencode.json

{
  "provider": {
    "fireworks-ai": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.fireworks.ai/inference/v1/"
      },
      "models": {
        "accounts/fireworks/models/ember-1": {}
      }
    }
  }
}

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

Not enough history yet — the min/median/max sparkline fills in as the daily snapshot accumulates.

Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.