Qwen3.5-35B-A3B
novita-ai/qwen/qwen3.5-35b-a3b · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.
$0.69
Blended $/1M (3:1)
$0.25
Input $/1M
$2
Output $/1M
$2.25
1M in + 1M out
—
Cache read $/1M
#3428 of 7,708
Cheapest rank
- Provider
- NovitaAI (
novita-ai) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools reasoning text image video
Same model, other providers
“Qwen3.5-35B-A3B” is offered by 2 providers — cheapest-effective first. CoreWeave is the cheapest at $0.50 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| CoreWeave | $0.25 | $1.25 | $0.50 | 262k |
| NovitaAI (this) | $0.25 | $2 | $0.69 | 262k |
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/qwen3.5-35b-a3b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):