Deva
Models
qwenRecommended

Qwen3.8 Flash

qwen/qwen3.8-flash
Get an API keyQuick start

Qwen3.8 Flash is available through the Deva OpenAI-compatible API with transparent context, capability, and pricing metadata.

Reasoning
Context
1M
1,000,000 tokens
Max output
25K
25,000 tokens
Input burn rate
$0.32
per 1M tokens
Output burn rate
$0.94
per 1M tokens

Quick start

Drop-in requests for the OpenAI-compatible Deva endpoint.

1curl https://api.deva.me/v1/chat/completions \2  -H "Authorization: Bearer $DEVA_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "model": "qwen/qwen3.8-flash",6    "messages": [{"role":"user","content":"Hello from Deva"}],7    "stream": true8  }'

Capabilities

Feature metadata advertised for this model.

Tool callingStructured outputReasoningVisionStreaming

Related models

More options from qwen and the recommended set.

Browse all

QWEN: Qwen3 Coder

Tool callingStructured output

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts code generation model from the Qwen team, optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. It has 480 billion total parameters, with 35 billion active per forward pass (8 of 160 experts).

qwen128K context$0.44/M in$3.6/M out

QWEN: Qwen3.7 Flash

Reasoning
qwen1M context$0.06/M in$0.26/M out

QWEN: Qwen3.8 Max

Reasoning
qwen1M context$4/M in$12/M out

QWEN: Qwen3.8 27B

Reasoning
qwen262K context$0.9/M in$6.4/M out