jishie

Qwen3 30B A3b fp8

cloudflare-workers-ai/@cf/qwen/qwen3-30b-a3b-fp8 · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.12Blended $/1M (3:1)
$0.0509Input $/1M
$0.335Output $/1M
$0.391M in + 1M out
—Cache read $/1M
#843 of 5,000Cheapest rank
Provider
Cloudflare Workers AI (cloudflare-workers-ai)
Context
32,768 tokens
Max output
32,768 tokens
Capabilities
toolsreasoningtext

Same model, other providers

“Qwen3 30B A3b fp8” is offered by 2 providers — cheapest-effective first. This one (Cloudflare Workers AI) is the cheapest.

ProviderInputOutputBlendedContext
Cloudflare Workers AI (this)$0.0509$0.335$0.1233k
Cloudflare AI Gateway$0.051$0.34$0.12128k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Cloudflare Workers AI and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"@cf/qwen/qwen3-30b-a3b-fp8","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):