All times Eastern (ET)Provider pages checked daily at
ProSign inRSS

Migrating from qwen3.6-flash to qwen3.7-flash

What changes when you move from qwen3.6-flash to qwen3.7-flash: input price −88%, output price −91.3%.

Status
Active
Shutdown
none announced
Time left
—
Status
Active
Shutdown
none announced
Time left
—

Prices

USD per 1M tokens, standard tier
Typeqwen3.6-flashqwen3.7-flashChange
Input$0.25first seen October 5, 2026 · source$0.03first seen October 5, 2026 · source−88%
Cached inputNot published$0.006first seen October 5, 2026 · source—
Output$1.50first seen October 5, 2026 · source$0.13first seen October 5, 2026 · source−91.3%

At 1M input and 250K output tokens a month: $0.625 on qwen3.6-flash, $0.0625 on qwen3.7-flash (−90%).

Other tiers, prompt-size bands and modalities are on each model's page.

Limits

Tokens
Limitqwen3.6-flashqwen3.7-flashChange
Context window1,000,000 tokensin place when tracking began (October 6, 2026) · source1,000,000 tokensin place when tracking began (October 6, 2026) · source0%
Max output tokens65,536 tokensin place when tracking began (October 6, 2026) · source131,072 tokensin place when tracking began (October 6, 2026) · source+100%

Benchmarks

Same benchmark, source and setting on both sides
Benchmarkqwen3.6-flashqwen3.7-flashChange
FrontierMath Tiers 1-3Epoch AI, no reasoning.
Other settings
  • 17.2% → 19.3%
22.5%19.3%−3.2 pts
GPQA DiamondEpoch AI.
Other settings
  • not run → 80.8% no reasoning
83.3%82.3%−1.0 pts
OTIS Mock AIME 2024-2025Epoch AI.
Other settings
  • not run → 77.8% no reasoning
84.4%86.7%+2.3 pts

A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features and parameters

Compare models

Same on both

  • Structured outputs: supported on both.qwen3.6-flash: in place when tracking began (October 6, 2026) · source · qwen3.7-flash: in place when tracking began (October 6, 2026) · source
  • Function calling: supported on both.qwen3.6-flash: in place when tracking began (October 6, 2026) · source · qwen3.7-flash: in place when tracking began (October 6, 2026) · source
  • Prompt caching: supported on both.qwen3.6-flash: in place when tracking began (October 6, 2026) · source · qwen3.7-flash: in place when tracking began (October 6, 2026) · source
  • Batch API: not supported (supported in the Beijing region only) on both.qwen3.6-flash: first seen October 8, 2026 · source · qwen3.7-flash: first seen October 8, 2026 · source
  • Image input: supported on both.qwen3.6-flash: in place when tracking began (October 6, 2026) · source · qwen3.7-flash: in place when tracking began (October 6, 2026) · source
  • Fine-tuning: not supported on both.qwen3.6-flash: in place when tracking began (October 6, 2026) · source · qwen3.7-flash: in place when tracking began (October 6, 2026) · source
  • Built-in web search: supported on both.qwen3.6-flash: in place when tracking began (October 6, 2026) · source · qwen3.7-flash: in place when tracking began (October 6, 2026) · source

Not published for qwen3.6-flash: PDF input, Reasoning / thinking, temperature parameter, top_p parameter, logprobs.

Not published for qwen3.7-flash: PDF input, Reasoning / thinking, temperature parameter, top_p parameter, logprobs.

Aliases

All aliases

No aliases point at either model.

Checklist

  1. Change the model string from qwen3.6-flash to qwen3.7-flash.

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: qwen3.6-flash, qwen3.7-flash.