gpt-oss-20b vs Ministral 3 3B 2512
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on November 14, 2026· 230 models
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
- Reasoning estimated
- ▲
- Speed estimated
- Input
- Output
- Context
- 131 K tokens
- Max output
- ▲118 K
- Input, $ per 1M tokens
- ▲$0.030
- Output, $ per 1M tokens
- $0.130
- Cache read, $ per 1M
- $0.030
- Batch (input / output)
- $0.024 / $0.112
- Tool calling
- Yes
- Released
- 08/05/2025
- Knowledge cutoff
- 2024-06
- API id
- openai/gpt-oss-20b
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
- Reasoning estimated
- Speed estimated
- ▲
- Input
- Output
- Context
- 131 K tokens
- Max output
- 105 K
- Input, $ per 1M tokens
- $0.100
- Output, $ per 1M tokens
- ▲$0.100
- Cache read, $ per 1M
- $0.010
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- ▲12/02/2025
- Knowledge cutoff
- —
- API id
- mistralai/ministral-3b-2512
Which is the better API choice: gpt-oss-20b vs Ministral 3 3B 2512?
- gpt-oss-20b: cheapest input (70% less than Ministral 3 3B 2512)
- Ministral 3 3B 2512: cheapest output
- Ministral 3 3B 2512: the newest (12/02/2025)
- gpt-oss-20b: most reasoning (estimated)
- Ministral 3 3B 2512: the fastest (estimated)
Pricing is split: gpt-oss-20b wins on input and Ministral 3 3B 2512 wins on output. All accept 131 K tokens of context. On capabilities, Ministral 3 3B 2512 accepts images; gpt-oss-20b has a reasoning mode. gpt-oss-20b offers a batch tier at half price for jobs that do not need an immediate answer.
What would your product cost?
Estimate the monthly cost with your app's real volume. List prices, no cache or batch discounts.
With gpt-oss-20b you save $0.93 a month versus Ministral 3 3B 2512 (49% less).
The 6 cheapest for this scenario (chat, last 12 months)
- 1Lyria 3 Pro Preview Google$0.00
- 2Lyria 3 Clip Preview Google$0.00
- 3Qwen3.7 Flash Qwen$0.97
- 4DeepSeek V4.1 Flash DeepSeek$1.57
- 5DeepSeek V4 Flash 0731 DeepSeek$1.85
- 6Ministral 3 3B 2512 Mistral$1.90
Paste your prompt: tokens and cost per model
Rough estimate (about 4 characters per token). Nothing is sent to any server.
Cost of sending it 1,000 times (input only)
- 1gpt-oss-20b OpenAI$0.002
- 2Ministral 3 3B 2512 Mistral$0.008
- 3Claude Haiku 5.5 Anthropic$0.008
- 4Claude Sonnet 5.5 Anthropic$0.152
- 5Claude Opus 5.5 Anthropic$0.304
- 6Claude Opus 5 Anthropic$0.380
- 7Claude Fable 5.2 Anthropic$0.608
- 8Claude Fable 5.1 Anthropic$0.760
Popular comparisons
- Claude Fable 5.2 vs GPT-6.1 Terra
- Claude Fable 5.2 vs Gemini 4 Hydrogen
- Claude Fable 5.2 vs DeepSeek V4.1 Flash 1017
- Claude Fable 5.2 vs Grok 4.7
- GPT-6.1 Terra vs Gemini 4 Hydrogen
- GPT-6.1 Terra vs DeepSeek V4.1 Flash 1017
- GPT-6.1 Terra vs Grok 4.7
- Gemini 4 Hydrogen vs DeepSeek V4.1 Flash 1017
- Gemini 4 Hydrogen vs Grok 4.7
- DeepSeek V4.1 Flash 1017 vs Grok 4.7
More free tools
See allFrequently asked questions
Which is the better API choice: gpt-oss-20b vs Ministral 3 3B 2512?
Pricing is split: gpt-oss-20b wins on input and Ministral 3 3B 2512 wins on output. All accept 131 K tokens of context. On capabilities, Ministral 3 3B 2512 accepts images; gpt-oss-20b has a reasoning mode. gpt-oss-20b offers a batch tier at half price for jobs that do not need an immediate answer.
Which is cheaper: gpt-oss-20b and Ministral 3 3B 2512?
gpt-oss-20b is cheaper: $0.030 per million input tokens and $0.130 per million output tokens, versus $0.100 / $0.100 for Ministral 3 3B 2512.
Which has more context: gpt-oss-20b and Ministral 3 3B 2512?
gpt-oss-20b and Ministral 3 3B 2512 accept the same context: 131 K tokens.
Which is newer: gpt-oss-20b and Ministral 3 3B 2512?
Ministral 3 3B 2512 was released on 12/02/2025; gpt-oss-20b on 08/05/2025.
What would 10,000 requests a month cost with gpt-oss-20b and Ministral 3 3B 2512?
With 1,500 input and 400 output tokens per request: gpt-oss-20b: $0.97; Ministral 3 3B 2512: $1.90 a month, at list price.
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.