Home/Models
Models/Alibaba

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 visual perception.

alibaba/qwen3.7-flash
Organization
Alibaba
Family
qwen
Providers
13
Context
1,000,000
Output limit
131,072
Knowledge
—
Release
2026-07-15
Updated
—
Weights
Closed
Input
text, image/bmp, image/jpeg, image/png, image/tiff, image/webp, image/heic, video/mp4, video/x-msvideo, video/x-matroska, video/quicktime, video/x-flv, video/x-ms-wmv
Output
text
Capabilities
—

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

15 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
AIHubMix
qwen3.7-flash
991,000131,072— / ————
View
Alibaba
qwen3.7-flash
1,000,000131,072— / ————
View
Alibaba (China)
qwen3.7-flash
1,000,000131,072— / ————
View
CrossModel
qwen/qwen3.7-flash
1,000,00065,536— / ————
View
DevPass (LLM Gateway)
qwen3.7-flash
983,6161,000,000— / ————
View
EmpirioLabs AI
qwen3-7-flash
983,61665,536— / ————
View
Kilo Gateway
qwen/qwen3.7-flash
1,000,00065,536— / ————
View
LLM Gateway
alibaba/qwen3.7-flash
983,61665,536— / ————
View
NanoGPT
qwen/qwen3.7-flash
991,80865,536— / ————
View
NanoGPT
qwen/qwen3.7-flash:thinking
983,61665,536— / ————
View
Alibabavia OpenRouter
qwen/qwen3.7-flash
unknown		1,000,00065,536$0.0345 / $0.1495YesYesNo
View
Alibabavia OpenRouter
qwen/qwen3.7-flash
unknown		1,000,00065,536$0.03 / $0.13YesYesNo
View
OrcaRouter
qwen/qwen3.7-flash
1,000,000131,072— / ————
View
Standard Compute
qwen/qwen3.7-flash
1,000,00050,000— / ————
View
Vercel AI Gateway
alibaba/qwen3.7-flash
991,00064,000— / ————
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.03Per 1M input tokens
Output from$0.13Per 1M output tokens
Available offers15Across 13 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 2 lowest-priced configurations
InputOutput
Alibabaalibaba
$0.03$0.13
Alibabaalibaba/us-east-1
$0.0345$0.1495
qwen/qwen3.7-flashObserved
Input
$0.03
Output
$0.13
Cache read
$0.006
Cache write
$0.038
Additional fees and pricing conditions

overrides · USD per token for token prices; time windows use UTC.

[
  {
    "prompt": "0.0000001",
    "completion": "0.0000004",
    "input_cache_read": "0.00000002",
    "input_cache_write": "0.000000125",
    "min_prompt_tokens": 32000
  },
  {
    "prompt": "0.0000002",
    "completion": "0.0000008",
    "input_cache_read": "0.00000004",
    "input_cache_write": "0.00000025",
    "min_prompt_tokens": 256000
  }
]
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Alibabaalibaba/us-east-1$0.0345$0.1495$0.0069—
Alibabaalibaba$0.03$0.13$0.006$0.038

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 2 endpoints
P50P75P90P99
Alibabaalibaba/us-east-1
854–3,731.45 ms
Alibabaalibaba
653–5,538.09 ms
All latency percentiles 2 endpoints
EndpointP50P75P90P99
Alibabaalibaba/us-east-1854 ms1,228 ms1,704 ms3,731.45 ms
Alibabaalibaba653 ms945 ms1,854 ms5,538.09 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 2 endpoints
P50P75P90P99
Alibabaalibaba/us-east-1
68–137 t/s
Alibabaalibaba
61–136 t/s
All throughput percentiles 2 endpoints
EndpointP50P75P90P99
Alibabaalibaba/us-east-168 t/s82 t/s99 t/s137 t/s
Alibabaalibaba61 t/s86 t/s107 t/s136 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 2 endpoints
Endpoint5 minutes30 minutes24 hours
Alibabaalibaba/us-east-1
Alibabaalibaba

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Nov 1, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Hermes Agentqwen/qwen3.7-flash-202607271 turn
$0.00022
Details
Hermes Agentqwen/qwen3.7-flash-202607272–9 turns
$0.001046
Details
Claude Codeqwen/qwen3.7-flash-202607272–9 turns
$0.001441
Details
Hermes Agentqwen/qwen3.7-flash-2026072750+ turns
$0.172727
Details
Hermes Agentqwen/qwen3.7-flash-2026072710–49 turns
$0.024381
Details

Source: OpenRouter, as of Nov 9, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days
Daily token usage3,185,594,165,724 reported tokens · 58 days with observations
Aug 16, 2026Nov 13, 2026
Daily observations · 58 days
Date (UTC)Reported tokensReported routes
Nov 13, 202682,681,511,4201
Nov 12, 202682,133,420,1271
Nov 11, 202687,701,538,5261
Nov 9, 202659,251,923,9041
Nov 8, 202651,209,846,9931
Nov 7, 202652,439,300,8441
Nov 6, 202650,935,962,2611
Nov 5, 202663,364,814,8231
Nov 4, 202671,401,009,7121
Nov 3, 202676,521,635,3121
Nov 2, 202672,736,454,9141
Nov 1, 202653,440,547,6001
Oct 31, 202673,633,708,7051
Oct 30, 202661,227,524,9991
Oct 29, 202663,920,645,3871
Oct 28, 202671,654,657,6941
Oct 27, 202668,863,635,6341
Oct 24, 202677,240,328,8791
Oct 23, 202661,429,335,0441
Oct 14, 202662,423,206,7871
Oct 13, 202658,644,137,4981
Oct 11, 202648,457,873,3191
Oct 10, 202645,873,272,9261
Oct 9, 202658,191,077,3031
Oct 6, 202653,778,316,0301
Oct 3, 202647,936,207,7491
Oct 2, 202654,987,015,3171
Oct 1, 202665,122,446,9511
Sep 29, 202653,064,199,5611
Sep 28, 202666,036,338,8591
Sep 27, 202666,671,634,4211
Sep 26, 202657,437,604,7971
Sep 25, 202666,890,138,4361
Sep 24, 202666,670,818,3221
Sep 23, 202668,423,870,0311
Sep 22, 202659,716,283,9011
Sep 21, 202655,183,797,2301
Sep 20, 202661,020,712,0341
Sep 19, 202658,698,340,7981
Sep 18, 202661,930,342,0251
Sep 17, 202652,118,079,6741
Sep 16, 202662,624,589,7091
Sep 15, 202650,850,643,2981
Sep 14, 202653,582,123,3981
Sep 13, 202642,198,216,5601
Sep 12, 202644,530,832,6941
Sep 11, 202648,082,456,4091
Sep 10, 202642,062,634,1021
Sep 9, 202634,786,923,5011
Aug 30, 202624,193,735,7401
Aug 29, 202624,321,568,0641
Aug 27, 202626,327,854,4621
Aug 26, 202626,368,988,9371
Aug 22, 202620,423,440,1751
Aug 20, 202630,476,116,0791
Aug 19, 202630,690,265,2391
Aug 18, 202630,466,319,1601
Aug 16, 202622,543,941,4501

Source: OpenRouter (openrouter.ai/rankings), as of Nov 14, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
qwen/qwen3.7-flashObserved
Context
1,000,000
Maximum output
65,536
Tokenizer
Qwen
Input
text, image, video
Output
text
Moderation
No
Added to OpenRouter
2026-07-27
Base URLhttps://openrouter.ai/api/v1
Model IDqwen/qwen3.7-flash
Version IDqwen/qwen3.7-flash-20260727

Reasoning

Required
No
Enabled by default
Yes
Default effort
—
Supported efforts
—

Supported parameters

  • include_reasoning
  • logprobs
  • max_tokens
  • presence_penalty
  • reasoning
  • response_format
  • seed
  • temperature
  • tool_choice
  • tools
  • top_logprobs
  • top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Qwen3.7 Flash cost?

Listed rates start at $0.03 per million input tokens and $0.13 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Qwen3.7 Flash?

There are 15 cataloged offers across 13 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,000,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 4 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · 3fc83b26635d
  • · 33a15c130a04
  • · 0820451f4867
  • · 5d50b1c408c0