Qwen3.5 4B
thinkingmachines/Qwen/Qwen3.5-4B:peft:262144 · family qwen · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.50
Blended $/1M (3:1)
$0.33
Input $/1M
$1.01
Output $/1M
$1.33
1M in + 1M out
$0.066 −80%
Cache read $/1M
#3193 of 8,682
Cheapest rank
- Provider
- Thinking Machines (
thinkingmachines) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Qwen3.5 4B” is offered by 4 providers — cheapest-effective first. QVAC is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| QVAC | free | free | $0.00 | 33k |
| Merge Gateway | $0.04 | $0.07 | $0.05 | 262k |
| EmpirioLabs AI | $0.04 | $0.07 | $0.05 | 262k |
| Thinking Machines (this) | $0.33 | $1.01 | $0.50 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Thinking Machines and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"Qwen/Qwen3.5-4B:peft:262144","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):