BroadRouter

gpt-oss-20b vs Qwen3.6 35B A3B API pricing

Updated

gpt-oss-20b: USD 0.018 input, USD 0.09 output per 1M tokens (AkashML, promotional). Qwen3.6 35B A3B: USD 0.10 input, USD 0.89 output per 1M tokens (CoreWeave Forge). At 3 input tokens per output token, Qwen3.6 35B A3B costs 8.3× as much as gpt-oss-20b (USD 0.2975 vs USD 0.036 per 1M).

gpt-oss-20b and Qwen3.6 35B A3B are often compared as alternatives. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-16), with no claim about quality, speed or accuracy.

How do gpt-oss-20b and Qwen3.6 35B A3B differ on price?

gpt-oss-20b and Qwen3.6 35B A3B prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

gpt-oss-20b and Qwen3.6 35B A3B API prices compared
Pricegpt-oss-20bQwen3.6 35B A3B
Model pageGPT OSS 20B
OpenAI · 10 providers
Qwen3.6 35B A3B
Qwen · 12 providers
Cheapest standard price, blended 3:1USD 0.036 lower promo
USD 0.018 in / USD 0.09 out at AkashML
AkashML page checked 2026-11-15
USD 0.2975
USD 0.10 in / USD 0.89 out at CoreWeave Forge
CoreWeave Forge page checked 2026-11-15
Cheapest inputUSD 0.018 lower promo
AkashML source
USD 0.10
CoreWeave Forge source
Cheapest cached inputUSD 0.007 lower
Google Vertex AI source
USD 0.032
Featherless source
Cheapest outputUSD 0.09 lower promo
AkashML source
USD 0.89
CoreWeave Forge source
Cheapest non-promotional priceUSD 0.03 / USD 0.13
CoreWeave Forge, USD 0.055 blended source
The cheapest price is not promotional.
Maker's own APIOpenAI publishes no paid standard price on its own API that we found.USD 0.375 / USD 2.25
Alibaba Cloud source
Median standard priceUSD 0.04 / USD 0.19
input / output, 10 prices
USD 0.16 / USD 1.05
input / output, 12 prices
Context window131,072 tokens, largest stated262,144 tokens, largest stated; from 32,768 at some providers
Providers with a standard price1012

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do gpt-oss-20b and Qwen3.6 35B A3B cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on gpt-oss-20b and Qwen3.6 35B A3B
Workloadgpt-oss-20bQwen3.6 35B A3BDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 2.75
AkashML
USD 21.51
CoreWeave Forge
USD 18.76
gpt-oss-20b lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 5.02
AkashML
USD 32.67
CoreWeave Forge
USD 27.65
gpt-oss-20b lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 26.73
AkashML
USD 160.65
CoreWeave Forge
USD 133.92
gpt-oss-20b lower

gpt-oss-20b is cheaper on all three workloads. The widest gap is on Support chatbot: the dearer model costs 7.8× as much as the cheaper one.

Does the cheaper model change with your input:output ratio?

gpt-oss-20b is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Qwen3.6 35B A3B's, so the input:output ratio never changes the answer.

Price per 1M tokens of gpt-oss-20b and Qwen3.6 35B A3B at different input:output mixes
Input : output tokensgpt-oss-20bQwen3.6 35B A3B
1 : 3 (long answers)USD 0.072 lower
AkashML
USD 0.6925
CoreWeave Forge
1 : 1USD 0.054 lower
AkashML
USD 0.495
CoreWeave Forge
3 : 1 (the site’s blend)USD 0.036 lower
AkashML
USD 0.2975
CoreWeave Forge
10 : 1 (retrieval, long prompts)USD 0.02455 lower
AkashML
USD 0.1718
CoreWeave Forge
30 : 1 (agents, big contexts)USD 0.02032 lower
AkashML
USD 0.1255
CoreWeave Forge

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do gpt-oss-20b and Qwen3.6 35B A3B cost per character in other languages?

Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the gpt-oss (o200k_harmony) tokenizer for gpt-oss-20b and the Qwen3.8 27B tokenizer for Qwen3.6 35B A3B:

Input cost per 1M characters by language, gpt-oss-20b and Qwen3.6 35B A3B
Contentgpt-oss-20bQwen3.6 35B A3B
EnglishUSD 0.0064 lower
CoreWeave Forge
USD 0.022
CoreWeave Forge
Arabic MSAUSD 0.0096 lower
CoreWeave Forge
USD 0.031
CoreWeave Forge
Egyptian ArabicUSD 0.0100 lower
CoreWeave Forge
USD 0.033
CoreWeave Forge
HindiUSD 0.0097 lower
CoreWeave Forge
USD 0.042
CoreWeave Forge
ChineseUSD 0.023 lower
CoreWeave Forge
USD 0.058
CoreWeave Forge
SpanishUSD 0.0068 lower
CoreWeave Forge
USD 0.023
CoreWeave Forge
CodeUSD 0.0076 lower
CoreWeave Forge
USD 0.028
CoreWeave Forge

From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.

Check it on your own traffic

More comparisons: gpt-oss-120b vs gpt-oss-20b · Gemma 4 26B A4B vs gpt-oss-20b · Gemma 4 26B A4B vs Qwen3.6 35B A3B · DeepSeek V4.1 Flash vs Qwen3.6 35B A3B · Qwen3.6 35B A3B vs Qwen3.5 35B A3B · Qwen3.6 35B A3B vs Qwen3.6 27B · every gpt-oss-20b comparison · every Qwen3.6 35B A3B comparison · all 662 price comparisons

Questions

Is gpt-oss-20b cheaper than Qwen3.6 35B A3B?

Yes. On a blend of 3 input tokens to 1 output token, gpt-oss-20b costs USD 0.036 per 1M tokens and Qwen3.6 35B A3B USD 0.2975, at each model's cheapest standard price. For input alone, gpt-oss-20b is cheaper (USD 0.018 against USD 0.10 per 1M); for output alone, gpt-oss-20b is (USD 0.09 against USD 0.89). This compares price only, not quality.

What do gpt-oss-20b and Qwen3.6 35B A3B cost per 1M tokens?

gpt-oss-20b: from USD 0.018 input and USD 0.09 output at AkashML (promotional); median of 10 standard prices USD 0.04 / USD 0.19. Qwen3.6 35B A3B: from USD 0.10 input and USD 0.89 output at CoreWeave Forge; Alibaba Cloud's own API charges USD 0.375 / USD 2.25; median of 12 standard prices USD 0.16 / USD 1.05. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both gpt-oss-20b and Qwen3.6 35B A3B?

6 providers have a standard price for both: AkashML (USD 0.036 and USD 0.30 at 3:1), CoreWeave Forge (USD 0.055 and USD 0.2975 at 3:1), DeepInfra (USD 0.0575 and USD 0.3125 at 3:1), Parasail (USD 0.08 and USD 0.3625 at 3:1), Featherless (USD 0.0675 and USD 0.4179 at 3:1), SiliconFlow (USD 0.075 and USD 0.63 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.036 and USD 0.2975.

Which is cheaper for a coding agent or a chatbot, gpt-oss-20b or Qwen3.6 35B A3B?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 26.73 a month on gpt-oss-20b (AkashML) against USD 160.65 on Qwen3.6 35B A3B (CoreWeave Forge), a difference of USD 133.92. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 2.75 a month on gpt-oss-20b (AkashML) against USD 21.51 on Qwen3.6 35B A3B (CoreWeave Forge), a difference of USD 18.76. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of gpt-oss-20b and Qwen3.6 35B A3B change?

gpt-oss-20b is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Qwen3.6 35B A3B's, so the input:output ratio never changes the answer.

Do gpt-oss-20b and Qwen3.6 35B A3B have cached input pricing?

gpt-oss-20b from USD 0.007 per 1M cached input tokens (Google Vertex AI; 4 of 10 standard prices list a discount). Qwen3.6 35B A3B from USD 0.032 per 1M cached input tokens (Featherless; 6 of 12 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, gpt-oss-20b or Qwen3.6 35B A3B?

Qwen3.6 35B A3B: up to 262,144 tokens, against 131,072 for gpt-oss-20b, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity