Qwen3.5 Flash
merge-gateway/qwen/qwen3.5-flash · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.09
Blended $/1M (3:1)
$0.029
Input $/1M
$0.287
Output $/1M
$0.32
1M in + 1M out
$0.0058 −80%
Cache read $/1M
#851 of 8,504
Cheapest rank
- Provider
- Merge Gateway (
merge-gateway) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 250,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Qwen3.5 Flash” is offered by 9 providers — cheapest-effective first. AIHubMix is the cheapest at $0.09 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| AIHubMix | $0.0282 | $0.282 | $0.09 | 1M |
| Merge Gateway (this) | $0.029 | $0.287 | $0.09 | 1M |
| Alibaba (China) | $0.029 | $0.287 | $0.09 | 1M |
| EmpirioLabs AI | $0.09 | $0.368 | $0.16 | 996k |
| Ofox | $0.1 | $0.4 | $0.18 | 1M |
| ZenMux | $0.1 | $0.4 | $0.18 | 1M |
| Alibaba | $0.1 | $0.4 | $0.18 | 1M |
| OrcaRouter | $0.1 | $0.4 | $0.18 | 1M |
| NanoGPT | $0.1 | $0.4 | $0.18 | 992k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Merge Gateway 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-flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):