gpt-oss-120b vs Qwen3.7 Flash

At a Glance

Compare
Pricing and Limits
Input priceFrom · USD / 1M tokens$0.037Deepinfra · Sep 23, 2026$0.030Openrouter · Sep 23, 2026
Output priceFrom · USD / 1M tokens$0.17Deepinfra · Sep 23, 2026$0.13Openrouter · Sep 23, 2026
Context windowMaximum documented tokens131K1,000K
Model facts checkedAug 28, 2026View model evidence →Sep 3, 2026View model evidence →

Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →

Available Benchmarks

All benchmark results →
No Protocol-Matched Benchmark Yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.

Side-by-Side Facts

Fieldgpt-oss-120bQwen3.7 Flash
DeveloperOpenAIQwen
FamilyGpt Oss 120bQwen3 7
Modelgpt-oss-120bQwen3.7 Flash
Versiongpt-oss-120bQwen3.7 Flash
Lifecycleactiveactive
ReleasedUnknown2026-07-15
Knowledge cutoffUnknownUnknown
Input modalitiesTextText, Image, Video
Output modalitiesTextText
Context window131K1,000K
Total parameters116.8BUnknown
Active parameters5.1BUnknown
Licenseapache-2.0Unknown
Open weightsYesNo
API availableYesYes
Self-hostableYesNo
Provider accessCerebras (Standard), Deepinfra (Standard), Fireworks Ai (Serverless, Standard), Groq (Standard), Hugging Face (Standard), Openrouter (Standard), Together Ai (Serverless, Standard)Alibaba Cloud Model Studio (Standard), Openrouter (Standard)
Capabilitieschat, generation, reasoning, toolsagents, chat, generation, reasoning, structured_outputs, tools, vision

gpt-oss-120b Capabilities

chatgenerationreasoningtools
Serving providers7
Canonical IDopenai/gpt-oss-120b

Qwen3.7 Flash Capabilities

agentschatgenerationreasoningstructured outputstoolsvision
Serving providers2
Canonical IDqwen/qwen3.7-flash

Primary Evidence

Sources and Freshness

Questions

gpt-oss-120b vs Qwen3.7 Flash FAQs

Is gpt-oss-120b or Qwen3.7 Flash better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both gpt-oss-120b and Qwen3.7 Flash, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, gpt-oss-120b or Qwen3.7 Flash?+

gpt-oss-120b is $0.037 and Qwen3.7 Flash is $0.030 per million tokens, so Qwen3.7 Flash is cheaper on this metric. gpt-oss-120b is $0.17 and Qwen3.7 Flash is $0.13 per million tokens, so Qwen3.7 Flash is cheaper on this metric.

Which has a larger context window, gpt-oss-120b or Qwen3.7 Flash?+

Qwen3.7 Flash has the larger sourced context window. gpt-oss-120b supports 131K and Qwen3.7 Flash supports 1,000K.

Which performs better in benchmarks, gpt-oss-120b or Qwen3.7 Flash?+

There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.

Can gpt-oss-120b or Qwen3.7 Flash be self-hosted?+

gpt-oss-120b is the only model in this pair currently marked as self-hostable. gpt-oss-120b is open weight; Qwen3.7 Flash is not marked open weight.

Can gpt-oss-120b and Qwen3.7 Flash understand images?+

gpt-oss-120b is not documented with image input; Qwen3.7 Flash is documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, gpt-oss-120b or Qwen3.7 Flash?+

Neither has a larger sourced maximum output. gpt-oss-120b is — and Qwen3.7 Flash is 66K.

Do gpt-oss-120b and Qwen3.7 Flash support reasoning and tool use?+

gpt-oss-120b: reasoning and tool calling. Qwen3.7 Flash: reasoning, tool calling, and image input. Feature support does not establish relative quality.

Which is available from more inference providers, gpt-oss-120b or Qwen3.7 Flash?+

gpt-oss-120b has 7 sourced provider routes; Qwen3.7 Flash has 2, so gpt-oss-120b has broader tracked availability.

Which offers better value, gpt-oss-120b or Qwen3.7 Flash?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback