Qwen models and API pricing
Published Qwen models available through Meldport. Check capabilities before selecting a model for your integration.
Latest catalog evidence: Verified on 2026-11-06.
| Model / publisher | Input | Output | List input / output | Published discount | Capabilities / context | Evidence |
|---|---|---|---|---|---|---|
| Qwen3 Coder Next Qwen | $0.1647 | $0.8235 | $0.3 / $1.5 | Input: 45.1% Output: 45.1% | text, tools, stream 256K tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| Qwen3.7 Max Qwen | $1.3152 | $5.2608 | $2.4 / $9.6 | Input: 45.2% Output: 45.2% | text, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| Qwen3.7 Plus Qwen | $0.66 | $2.64 | $1.2 / $4.8 | Input: 45% Output: 45% | text, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| Qwen3.8 2.4T-A95B Qwen | $0.6 | $1.8 | $2 / $6 | Input: 70% Output: 70% | text, cache, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| Qwen3.8 Max 0902 Qwen | $0.6 | $1.8 | $2 / $6 | Input: 70% Output: 70% | text, vision, cache, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| Qwen 3.8 Max Qwen | $0.6 | $1.8 | $2 / $6 | Input: 70% Output: 70% | text, vision, cache, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| Qwen3.8 Flash Qwen | $0.045 | $0.141 | $0.15 / $0.47 | Input: 70% Output: 70% | text, vision, cache, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| Qwen3.8 27B Qwen | $0.15 | $0.9 | $0.5 / $3 | Input: 70% Output: 70% | text, vision, video, cache, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
| Qwen3.8 Omni Flash Qwen | $0.045 | $0.141 | $0.15 / $0.47 | Input: 70% Output: 70% | text, vision, video, audio, cache, tools, stream 1M tokens | Verified on 2026-11-06 Expires 2026-11-07 |
Select the exact model and variant
Compare the published Flash, Plus, Max and Coder entries against the task you need. Vision, tool support and context limits belong to each model entry, not automatically to the entire Qwen family.
One currently active example is Qwen3.8 Flash, API ID meldport/qwen3.8-flash. Its published context is 1,000,000 tokens; published capabilities: text, vision, cache, tools, stream. Evidence checked 2026-11-06. Review the model detail for its current evidence and limits.
Try a bounded Chat Completions request
Send this JSON to POST https://api.meldport.com/v1/chat/completions, with Content-Type: application/json and your dedicated key in the Authorization: Bearer header.
{
"model": "meldport/qwen3.8-flash",
"messages": [
{
"role": "user",
"content": "Reply with one short sentence."
}
],
"max_tokens": 64,
"stream": false
}Store a dedicated key in your environment and follow the authentication quickstart. Use the exact ID above; a paid model ID and a :free alias have separate funding rules. See the eligible free aliases and shared monthly pool before assuming a free version is available.
Calculate ordinary input, cache and output costs, compare gateway tradeoffs, or read why your token ratio matters. Client-specific streaming and tool behavior must be tested separately; see agent compatibility.