제공자 · 2026-06-09
deepinfra
| 모델 | 입력 / 1M | 출력 / 1M | 컨텍스트 | 제공자 | 태그 |
|---|---|---|---|---|---|
| MiMo-V2.5 | $0.400 | $2.00 | 262K | 1 | tools · reasoning · vision · open-weights |
| MiMo-V2.5-Pro | $1.00 | $3.00 | 1.05M | 1 | tools · reasoning · open-weights |
| Qwen3 Coder 480B A35B Instruct Turbo파생 | $0.300 | $1.20 | 262K | 1 | tools · open-weights |
Frequently asked questions
How many AI models does deepinfra offer?
We track 2 canonical deepinfra models plus 1 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.
Which deepinfra model is the cheapest?
MiMo-V2.5 is currently the lowest-priced deepinfra model, at $0.400 per 1M input tokens and $2.00 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.
Which deepinfra model has the largest context window?
MiMo-V2.5-Pro leads at 1.05M tokens. This is the total of prompt + completion.
Which deepinfra models support tool calling?
Multiple deepinfra models support tool calling, with MiMo-V2.5 being a popular pick. The capability column in the table above marks every model with deepinfra tool-calling support.
Which deepinfra models accept image input?
MiMo-V2.5 accepts image input. Other vision-capable deepinfra models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.
What are the best alternatives to deepinfra?
Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.
How fresh is this deepinfra pricing data?
Daily. Our pipeline syncs every morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.
Explore more
Top deepinfra models
- MiMo-V2.5$0.40 in / $2.00 out
- MiMo-V2.5-Pro$1.00 in / $3.00 out
Browse by use case
Browse by capability
마지막 업데이트:
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.