gpt-oss-20b pricing calculator
A small open-weight reasoning model that runs on 16GB consumer GPUs. Pricing shown is Together's serverless rate.
- Input
- $0.05 / 1M
- Cached input
- —
- Output
- $0.20 / 1M
- Context window
- 128K
- Batch API
- No
- Reasoning
- Yes
Workload
Quick presets
1,000 tokens ≈ 750 English words.
Pro / Agent mode
Caching, batch, multi-turn loops, reasoning tokens
Cost comparison
Cheapest / month
$4.72
gpt-oss-20b
Most expensive / month
$7.06
Qwen3 32B
Tokens / request
1.5K in
400 out (cheapest model)
| Remove | |||||
|---|---|---|---|---|---|
| gpt-oss-20bCheapestOpenAI via Together · $0.05 / $0.20 | $0.00015 | $0.155 | $4.72 | $56.58 | |
| Mistral Small 3.2 24BMistral via DeepInfra · $0.075 / $0.20 | $0.00019 | $0.1925 | $5.86 | $70.26 | |
| DeepSeek V4 Flash (open weights)DeepSeek via DeepInfra · $0.09 / $0.18 | $0.00021 | $0.207 | $6.30 | $75.55 | |
| Qwen3 32BAlibaba via DeepInfra · $0.08 / $0.28 | $0.00023 | $0.232 | $7.06 | $84.68 |
Monthly = daily × 30.42. Prices are list prices for the standard context tier. Long-context surcharges, regional pricing and taxes are not included.Official pricing: Together ↗ · DeepInfra ↗
What gpt-oss-20b costs for common workloads
Monthly estimates using the presets above, at list price.
| Workload | Per request / session | Monthly | Yearly |
|---|---|---|---|
| Small Chatbot1K chats/day, short prompts | $9.0e-5 | $2.74 | $32.85 |
| RAG App5K queries/day, 4K-token retrieved context | $0.00028 | $42.59 | $511.00 |
| Coding Agent200 sessions/day × 25 turns | $0.0675 | $410.67 | $4,928 |
| Enterprise Scale250K requests/day, batched | $0.00025 | $1,901 | $22,813 |
Official pricing ↗ (OpenAI via Together) · API model ID openai/gpt-oss-20b
gpt-oss-20b pricing FAQ
How much does gpt-oss-20b cost per 1M tokens?
gpt-oss-20b via Together costs $0.05 per 1M input tokens and $0.20 per 1M output tokens. Prices were last verified on Nov 21, 2026.
How much does one gpt-oss-20b request cost?
A typical request with 1,000 input tokens and 500 output tokens costs about $0.00015. At 1,000 such requests per day that is $4.56 per month.
Does gpt-oss-20b support prompt caching?
gpt-oss-20b via Together has no discounted cached-input price listed, so every input token is billed at the full rate.
Is there a Batch API discount for gpt-oss-20b?
No 50% batch discount is listed for gpt-oss-20b via Together.
What is the context window of gpt-oss-20b?
gpt-oss-20b supports up to 128K tokens of context.
Is gpt-oss-20b cheaper than Mistral Small 3.2 24B?
For a 1,000-in / 500-out request, gpt-oss-20b costs $0.00015 and Mistral Small 3.2 24B costs $0.00017, so gpt-oss-20b is 14% cheaper. Quality, speed and caching behaviour differ, so compare on your own workload above.
More AI cost tools
LLM API & Agent Cost Calculator
Compare per-request, monthly and yearly cost across 30+ models, with caching, batch and multi-turn agent modelling.
Open calculator →GBGPU & VRAM Calculator
See exactly how much VRAM a model needs (weights + KV cache + overhead) and which GPUs or Macs it fits on.
Open calculator →$/minVoice Agent Cost Calculator
Cost per minute and per call for STT + LLM + TTS + telephony voice agent stacks.
Open calculator →break-evenAPI vs Self-Hosting Break-Even
Find the monthly token volume where renting a dedicated GPU beats paying per token.
Open calculator →