DeepSeek V4 Flash vs GPT-OSS 20B
Two open-weight chat models on the same endpoint and API key, so switching between them is a one-word change. Below: what each costs for three realistic workloads, how they differ, and measured speed.
Inference APIs prices are read live from the price list.
- Cost: GPT-OSS 20B is cheaper in all three workloads, by 53–76%.
Side by side
| DeepSeek V4 Flash | GPT-OSS 20B | |
|---|---|---|
| Served by | Inference APIs | Inference APIs |
| Model author | DeepSeek | OpenAI |
| Model id | deepseek-ai/DeepSeek-V4-Flash | openai/gpt-oss-20b |
| Input price | $0.19 / 1M tokens | $0.04 / 1M tokens |
| Output price | $0.38 / 1M tokens | $0.19 / 1M tokens |
| Context window | 1M tokens | 131K tokens |
| Capabilities | Chat, Reasoning, Coding, Tool calling | Chat, Reasoning, Tool calling, JSON mode |
| Weights | Open | Open |
| Status | Available | Available |
| Limits | No per-minute or per-day request or token caps; usage draws on a prepaid balance | No per-minute or per-day request or token caps; usage draws on a prepaid balance |
| Time to first token | 0.85 s | — |
| Output speed | 54 tokens / s | — |
What three workloads cost
List prices applied to the same work. The cheaper side of each row is in bold.
| Workload | DeepSeek V4 Flash | GPT-OSS 20B | Difference |
|---|---|---|---|
| Chat assistant — 10,000 turns of 800 tokens in, 300 out | $2.66 | $0.89 | 67% |
| Long prompts or RAG — 10,000 requests of 8,000 in, 500 out | $17.10 | $4.15 | 76% |
| Generation-heavy — 10,000 requests of 500 in, 2,000 out | $8.55 | $4.00 | 53% |
GPT-OSS 20B is cheaper in all three workloads, by 53–76%. Reasoning models bill their thinking as output tokens, so real output counts run higher than the visible answer; treat the generation-heavy row as a floor for them.
When to choose which
- You need more than 131K tokens of context (it takes 1M)
- Cost per token matters most; it is the cheapest chat model here
- You process long documents and want a 1M-token context
- Multi-step coding or agent work; use GPT-OSS 120B or DeepSeek V4 Flash
- You need more than 131K tokens of context
- Cost is the deciding factor; it is cheaper in every workload above
- You are replacing llama-3.1-8b-instant on Groq and want the small model Groq itself recommends
- Classification, extraction and short assistant replies where cost per call matters more than depth
- A person is waiting for the answer and you leave reasoning on; at default settings it thought for about twenty seconds in our measurement
Price, context and speed are measurable; answer quality on your task is not something a table can settle. Both take the same request, so the honest test is to run your own prompts through each in the playground.
Measured speed
Medians of three streamed runs on 2026-09-17, public endpoint, a prompt that asks for about 120 words. Time to first token is the first token of any kind, reasoning included; output speed counts every generated token from that point. Reasoning models then think before the visible answer starts: DeepSeek V4 Flash began answering after 20.1 s at default settings, which you can shorten with the reasoning controls on each model page. Expect ±30% with time of day. Method and raw numbers: speed measurements.
Trying both
Same endpoint, same key. Change one string:
for MODEL in "deepseek-ai/DeepSeek-V4-Flash" "openai/gpt-oss-20b"; do
curl -s https://api.inferenceapis.com/v1/chat/completions \
-H "Authorization: Bearer $INFERENCE_API_KEY" -H "Content-Type: application/json" \
-d "{\"model\": \"$MODEL\", \"max_tokens\": 500, \"messages\": [{\"role\": \"user\", \"content\": \"Summarise the plot of Hamlet in two sentences.\"}]}" \
| jq -r '.model, .choices[0].message.content, .usage'
doneFAQ
Which is cheaper, DeepSeek V4 Flash or GPT-OSS 20B?
GPT-OSS 20B is cheaper in all three workloads, by 53–76%. The table above uses list prices: DeepSeek V4 Flash $0.19 / 1M tokens input, $0.38 / 1M tokens output; GPT-OSS 20B $0.04 / 1M tokens input, $0.19 / 1M tokens output.
How do I switch between them?
They are on the same endpoint and key. Change the model field from deepseek-ai/DeepSeek-V4-Flash to openai/gpt-oss-20b and nothing else.
Why does DeepSeek V4 Flash use more output tokens than the visible answer?
It is a reasoning model: it thinks before it answers and the thinking is billed as output tokens. Budget for that in output-heavy workloads, and set max_tokens to a few hundred or more so the answer is not cut off.
Spotted a price or limit that has changed? Tell us and we will re-check the provider page.