The Orchestrator › Models › Qwen
Qwen: Qwen3.7 Flash
Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...
Specifications
| Provider | Qwen |
| Model ID | qwen/qwen3.7-flash |
| Context window | 1M tokens (1,000,000) |
| Modalities | text + image + video → text |
| Tokenizer | Qwen |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2026-07-27 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | On by default |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | qwen/qwen3.7-flash | $0.03 | $0.13 | 1M |
| standard | TrustedRouter | qwen/qwen3.7-flash | $0.032 | $0.137 | 1.0M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.032 | $0.137 | 1.0M |
| 2026-11-14 | $0.03 | $0.13 | 1M |
Capabilities
Vision (image input)Video inputAgentic tool useStructured outputsReasoning mode1M+ context windowControllable reasoningNo content storage (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, response_format, seed, temperature, tool_choice, tools, top_logprobs, top_p