Qwen3.8 27B
liquid/qwen3.8-27b · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.
$0.19
Blended $/1M (3:1)
$0.08
Input $/1M
$0.525
Output $/1M
$0.60
1M in + 1M out
$0.0525 −34%
Cache read $/1M
#1786 of 9,563
Cheapest rank
- Provider
- Liquid Inference (
liquid) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools reasoning text image video
Same model, other providers
“Qwen3.8 27B” is offered by 65 providers — cheapest-effective first. AMD is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| AMD | free | free | $0.00 | 262k |
| IteraCompute | free | free | $0.00 | 131k |
| engy | $0.045 | $0.32 | $0.11 | 1M |
| DevPass (LLM Gateway) | $0.08 | $0.35 | $0.15 | 1M |
| Entrim | $0.1 | $0.4 | $0.18 | 262k |
| RunInfra | $0.1 | $0.4 | $0.18 | 262k |
| Cortecs | $0.1 | $0.4 | $0.18 | 1M |
| Powerspring | $0.1044 | $0.4166 | $0.18 | 1M |
| Liquid Inference (this) | $0.08 | $0.525 | $0.19 | 262k |
| EmpirioLabs AI | $0.17 | $0.5 | $0.25 | 262k |
| NanoGPT | $0.15 | $0.7 | $0.29 | 1M |
| AKI.IO | $0.1675 | $0.7257 | $0.31 | 262k |
| CedarLLM | $0.03 | $1.15 | $0.31 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Liquid Inference and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen3.8-27b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):