Qwen3 235B A22b Thinking 2507
novita-ai/qwen/qwen3-235b-a22b-thinking-2507 · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.97
Blended $/1M (3:1)
$0.3
Input $/1M
$3
Output $/1M
$3.30
1M in + 1M out
—
Cache read $/1M
#3988 of 7,708
Cheapest rank
- Provider
- NovitaAI (
novita-ai) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Qwen3 235B A22b Thinking 2507” is offered by 5 providers — cheapest-effective first. submodel is the cheapest at $0.30 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| submodel | $0.2 | $0.6 | $0.30 | 262k |
| OpenRouter | $0.23 | $2.3 | $0.75 | 131k |
| NovitaAI (this) | $0.3 | $3 | $0.97 | 131k |
| Jiekou.AI | $0.3 | $3 | $0.97 | 131k |
| Vercel AI Gateway | $0.4 | $4 | $1.30 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NovitaAI 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-thinking-2507","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):