Qwen3 235B A22B
jiekou/qwen/qwen3-235b-a22b-fp8 · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: reasoning text.
$0.35
Blended $/1M (3:1)
$0.2
Input $/1M
$0.8
Output $/1M
$1.00
1M in + 1M out
—
Cache read $/1M
#2370 of 7,712
Cheapest rank
- Provider
- Jiekou.AI (
jiekou) - Kind
- text (outputs text)
- Context
- 40,960 tokens
- Max output
- 20,000 tokens
- Capabilities
- reasoning text
Same model, other providers
“Qwen3 235B A22B” is offered by 3 providers — cheapest-effective first. This one (Jiekou.AI) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Jiekou.AI (this) | $0.2 | $0.8 | $0.35 | 41k |
| NovitaAI | $0.2 | $0.8 | $0.35 | 41k |
| Merge Gateway | $0.287 | $1.15 | $0.50 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Jiekou.AI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen/qwen3-235b-a22b-fp8","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):