Qwq 32B
cloudflare-workers-ai/@cf/qwen/qwq-32b · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: reasoning text.
$0.74
Blended $/1M (3:1)
$0.66
Input $/1M
$1
Output $/1M
$1.66
1M in + 1M out
—
Cache read $/1M
#3563 of 7,708
Cheapest rank
- Provider
- Cloudflare Workers AI (
cloudflare-workers-ai) - Kind
- text (outputs text)
- Context
- 24,000 tokens
- Max output
- 24,000 tokens
- Capabilities
- reasoning text
Same model, other providers
“Qwq 32B” is offered by 3 providers — cheapest-effective first. Abacus is the cheapest at $0.40 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Abacus | $0.4 | $0.4 | $0.40 | 33k |
| Alibaba (China) | $0.287 | $0.861 | $0.43 | 131k |
| Cloudflare Workers AI (this) | $0.66 | $1 | $0.74 | 24k |
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/qwq-32b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):