gpt-oss-120b vs Qwen3.8 27B API pricing
Updated
gpt-oss-120b: USD 0.03 input, USD 0.17 output per 1M tokens (CoreWeave Forge). Qwen3.8 27B: USD 0.039 input, USD 1.25 output per 1M tokens (Chutes). At 3 input tokens per output token, Qwen3.8 27B costs 5.3× as much as gpt-oss-120b (USD 0.3417 vs USD 0.065 per 1M).
How do gpt-oss-120b and Qwen3.8 27B differ on price?
- Cheapest input price: gpt-oss-120b USD 0.03 against USD 0.039 per 1M tokens, so Qwen3.8 27B costs 1.3× as much (30% more).
- Cheapest output price: gpt-oss-120b USD 0.17 against USD 1.25 per 1M tokens, so Qwen3.8 27B costs 7.4× as much.
- Among the 201 indexed models, gpt-oss-120b ranks 9th cheapest and Qwen3.8 27B 74th on the 3:1 blend.
- No input:output mix changes the answer: gpt-oss-120b is cheaper at every mix before cache discounts.
- Both list cached-input discounts: gpt-oss-120b at 4 standard prices of 21, from USD 0.015 (Fireworks AI, 90% below that provider's input price); Qwen3.8 27B at 14 standard prices of 19, from USD 0.0039 (Chutes, 90% below that provider's input price).
- Qwen3.8 27B states up to 1,000,000 tokens of context, 7.6× the 131,072 of gpt-oss-120b.
- gpt-oss-120b has 21 providers with a standard price, 2 more than Qwen3.8 27B; 10 providers sell both (DeepInfra, AkashML, Crusoe Cloud, CoreWeave Forge and 6 more).
- On one account, DeepInfra charges USD 0.07025 for gpt-oss-120b (1.08× its cheapest price) and USD 0.5813 for Qwen3.8 27B (1.7× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for gpt-oss-120b: its dearest standard price is 6.9× its cheapest, against 4.7× for Qwen3.8 27B.
- Qwen's own API charges USD 1.125 for Qwen3.8 27B at 3:1, 229% above the cheapest provider (Chutes).
- gpt-oss-120b has a batch price at 2 providers, from USD 0.07875 at 3:1 (Google Vertex AI); Qwen3.8 27B has a batch price at 1 provider, from USD 0.5625 at 3:1 (Doubleword).
- For the one-developer coding agent preset, the gap is USD 716.36 a year in gpt-oss-120b's favour (gpt-oss-120b USD 69.30 a month, Qwen3.8 27B USD 129.00).
- Per character of input, the gap depends on the language: gpt-oss-120b costs 1.03× as much as Qwen3.8 27B on Chinese text but 41% less than Qwen3.8 27B on Hindi, because the two tokenizers split those languages differently.
gpt-oss-120b and Qwen3.8 27B 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.
| Price | gpt-oss-120b | Qwen3.8 27B |
|---|---|---|
| Model page | OpenAI GPT OSS 120B OpenAI · 21 providers | Qwen3.8 27B Qwen · 19 providers |
| Cheapest standard price, blended 3:1 | USD 0.065 lower USD 0.03 in / USD 0.17 out at CoreWeave Forge CoreWeave Forge page checked 2026-11-15 | USD 0.3417 USD 0.039 in / USD 1.25 out at Chutes Chutes page checked 2026-11-15 |
| Cheapest input | USD 0.03 lower CoreWeave Forge source | USD 0.039 Chutes source |
| Cheapest cached input | USD 0.015 Fireworks AI source | USD 0.0039 lower Chutes source |
| Cheapest output | USD 0.17 lower CoreWeave Forge source | USD 1.25 Chutes source |
| Maker's own API | OpenAI publishes no paid standard price on its own API that we found. | USD 0.50 / USD 3 Alibaba Cloud source |
| Median standard price | USD 0.10 / USD 0.60 input / output, 21 prices | USD 0.40 / USD 2.50 input / output, 19 prices |
| Context window | 131,072 tokens, largest stated; from 128,000 at some providers | 1,000,000 tokens, largest stated; from 131,072 at some providers |
| Providers with a standard price | 21 | 19 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
- Promo: the provider calls the price promotional or discounted, so it is current now and can end without notice.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do gpt-oss-120b and Qwen3.8 27B 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).
| Workload | gpt-oss-120b | Qwen3.8 27B | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 5.76 CoreWeave Forge | USD 24.11 Chutes | USD 18.35 gpt-oss-120b lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 9.75 CoreWeave Forge | USD 25.58 Chutes | USD 15.83 gpt-oss-120b lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 69.30 CoreWeave Forge | USD 129.00 Chutes | USD 59.70 gpt-oss-120b lower |
gpt-oss-120b is cheaper on all three workloads. The widest gap is on Support chatbot: the dearer model costs 4.2× as much as the cheaper one.
Does the cheaper model change with your input:output ratio?
gpt-oss-120b 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 Qwen3.8 27B's, so the input:output ratio never changes the answer.
| Input : output tokens | gpt-oss-120b | Qwen3.8 27B |
|---|---|---|
| 1 : 3 (long answers) | USD 0.135 lower CoreWeave Forge | USD 0.9472 Chutes |
| 1 : 1 | USD 0.10 lower CoreWeave Forge | USD 0.6445 Chutes |
| 3 : 1 (the site’s blend) | USD 0.065 lower CoreWeave Forge | USD 0.3417 Chutes |
| 10 : 1 (retrieval, long prompts) | USD 0.04273 lower CoreWeave Forge | USD 0.1491 Chutes |
| 30 : 1 (agents, big contexts) | USD 0.03452 lower CoreWeave Forge | USD 0.07806 Chutes |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do gpt-oss-120b and Qwen3.8 27B 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-120b and the Qwen3.8 27B tokenizer for Qwen3.8 27B:
| Content | gpt-oss-120b | Qwen3.8 27B |
|---|---|---|
| English | USD 0.0064 lower CoreWeave Forge | USD 0.0087 Chutes |
| Arabic MSA | USD 0.0096 lower CoreWeave Forge | USD 0.012 Chutes |
| Egyptian Arabic | USD 0.0100 lower CoreWeave Forge | USD 0.013 Chutes |
| Hindi | USD 0.0097 lower CoreWeave Forge | USD 0.016 Chutes |
| Chinese | USD 0.023 CoreWeave Forge | USD 0.023 lower Chutes |
| Spanish | USD 0.0068 lower CoreWeave Forge | USD 0.0091 Chutes |
| Code | USD 0.0076 lower CoreWeave Forge | USD 0.011 Chutes |
From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.
Qwen3.8 27B on BroadNet Inference
BroadRouter is BroadNet's own site, so BroadNet's price is shown here for reference and is not part of the comparison above. BroadNet Inference serves Qwen3.8 27B as broadnet/qwen3.8-27b at USD 0.175 input, USD 0.0435 cached and USD 2.17 output per 1M tokens (USD 0.6737 blended 3:1; the cheapest third-party standard price above is USD 0.3417). On BroadNet it reads up to 262,144 tokens per request and accepts text and image input (BroadNet rate card).
Check it on your own traffic
- OpenAI GPT OSS 120B API pricing: all 21 providers and other tiers.
- Qwen3.8 27B API pricing: all 19 providers and other tiers.
- Cost calculator with gpt-oss-120b and Qwen3.8 27B preloaded
- gpt-oss token counter
- Qwen token counter
- Prompt caching calculator
More comparisons: gpt-oss-120b vs gpt-oss-20b · gpt-oss-120b vs Llama 3.3 70B · Nemotron 3 Super vs gpt-oss-120b · gpt-oss-120b vs DeepSeek V4.1 Flash · GPT-6 Luna vs gpt-oss-120b · gpt-oss-120b vs Gemma 4 26B A4B · Qwen3.8 27B vs Qwen3.6 27B · DeepSeek V4.1 Flash vs Qwen3.8 27B · Gemma 4 31B vs Qwen3.8 27B · GLM 5.3 vs Qwen3.8 27B · Qwen3.8 27B vs Llama 4 Maverick · Qwen3.8 27B vs MiniMax M3 · Qwen3.8 27B vs DeepSeek V3.2 · Qwen3.8 27B vs MiniMax M3.1 Flash · every gpt-oss-120b comparison · every Qwen3.8 27B comparison · all 662 price comparisons
Questions
Is gpt-oss-120b cheaper than Qwen3.8 27B?
Yes. On a blend of 3 input tokens to 1 output token, gpt-oss-120b costs USD 0.065 per 1M tokens and Qwen3.8 27B USD 0.3417, at each model's cheapest standard price. For input alone, gpt-oss-120b is cheaper (USD 0.03 against USD 0.039 per 1M); for output alone, gpt-oss-120b is (USD 0.17 against USD 1.25). This compares price only, not quality.
What do gpt-oss-120b and Qwen3.8 27B cost per 1M tokens?
gpt-oss-120b: from USD 0.03 input and USD 0.17 output at CoreWeave Forge; median of 21 standard prices USD 0.10 / USD 0.60. Qwen3.8 27B: from USD 0.039 input and USD 1.25 output at Chutes; Alibaba Cloud's own API charges USD 0.50 / USD 3; median of 19 standard prices USD 0.40 / USD 2.50. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both gpt-oss-120b and Qwen3.8 27B?
10 providers have a standard price for both: DeepInfra (USD 0.07025 and USD 0.5813 at 3:1), AkashML (USD 0.0745 and USD 0.6638 at 3:1), Crusoe Cloud (USD 0.10 and USD 0.6875 at 3:1), CoreWeave Forge (USD 0.065 and USD 1.05 at 3:1), Novita AI (USD 0.10 and USD 1.065 at 3:1), Venice (USD 0.1275 and USD 1.138 at 3:1), Featherless (USD 0.2625 and USD 1.05 at 3:1), Cerebras (USD 0.45 and USD 1.115 at 3:1), Cloudflare Workers AI (USD 0.45 and USD 1.138 at 3:1), Groq (USD 0.2625 and USD 1.60 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.065 and USD 0.3417.
Which is cheaper for a coding agent or a chatbot, gpt-oss-120b or Qwen3.8 27B?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 69.30 a month on gpt-oss-120b (CoreWeave Forge) against USD 129.00 on Qwen3.8 27B (Chutes), a difference of USD 59.70. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 5.76 a month on gpt-oss-120b (CoreWeave Forge) against USD 24.11 on Qwen3.8 27B (Chutes), a difference of USD 18.35. 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-120b and Qwen3.8 27B change?
gpt-oss-120b 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 Qwen3.8 27B's, so the input:output ratio never changes the answer.
Do gpt-oss-120b and Qwen3.8 27B have cached input pricing?
gpt-oss-120b from USD 0.015 per 1M cached input tokens (Fireworks AI; 4 of 21 standard prices list a discount). Qwen3.8 27B from USD 0.0039 per 1M cached input tokens (Chutes; 14 of 19 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-120b or Qwen3.8 27B?
Qwen3.8 27B: up to 1,000,000 tokens, against 131,072 for gpt-oss-120b, 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.
Can I use Qwen3.8 27B on BroadNet Inference?
BroadNet Inference serves Qwen3.8 27B as broadnet/qwen3.8-27b at USD 0.175 input and USD 2.17 output per 1M tokens (rate card synced 2026-11-14). BroadRouter is BroadNet's own site, so BroadNet's price is shown for reference and not ranked against the providers above.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- CoreWeave Forge: pricing (checked 2026-11-15)
- Fireworks AI: pricing (checked 2026-11-14)
- Chutes: pricing (checked 2026-11-15)
- Alibaba Cloud: own API pricing (checked 2026-11-14)
- DeepInfra: pricing (checked 2026-11-14)
- DeepInfra: pricing (checked 2026-11-14)
- AkashML: pricing (checked 2026-11-15)
- AkashML: pricing (checked 2026-11-15)
- Crusoe Cloud: pricing (checked 2026-11-15)
- Novita AI: pricing (checked 2026-11-14)
- Venice: pricing (checked 2026-11-15)
- Featherless: pricing (checked 2026-11-15)
- Featherless: pricing (checked 2026-11-15)
- Cerebras: pricing (checked 2026-11-14)
- Cloudflare Workers AI: pricing (checked 2026-11-14)
- Groq: pricing (checked 2026-11-14)
- Groq: pricing (checked 2026-11-14)
- Google Vertex AI: pricing (checked 2026-11-14)
- Doubleword: pricing (checked 2026-11-16)
- BroadNet Inference rate card, pricing.json (synced 2026-11-14)