DeepInfra review

DeepInfra is the value pick in this list. Its pricing page shows some of the lowest token rates we found for popular open models: DeepSeek-V4-Flash-0731 costs $0.06 per 1M input tokens and $0.18 per 1M output tokens with a 1024k context window, and GLM-5.3-Flash costs $0.15 and $0.50. Several models carried discounts when we checked, including 38% off GLM-5.3 and 51% off DeepSeek-V4.1-Flash-1017. The chat completions API is OpenAI-compatible for every language model, so moving an existing app usually means changing the base URL, key and model name. Beyond serverless tokens, DeepInfra offers a Batch API, LoRA adapters, private custom LLM deployments and DGX B300 GPU rentals at $5.89 per instance-hour. It ranks below Together AI and Fireworks AI on features because it publishes fewer service tiers and compliance details, and promotional rates can change, so budget on list prices.

Who it is for

Cost-focused developers running high token volumes

Price

Pay per token with no contracts; DeepSeek-V4-Flash-0731 at $0.06 per 1M input tokens and $0.18 per 1M output tokens.

DeepSeek-V4-Flash-0731 1024k $0.06 / $0.015 cached $0.18
Quoted from the vendor pricing page on November 12, 2026.

Key features

• OpenAI-compatible chat completions for all LLMs at https://api.deepinfra.com/v1/openai
• Large catalog across DeepSeek, Kimi, GLM, Qwen, Nemotron and other families
• Context windows up to 1024k tokens on DeepSeek V4 and GLM-5.3 models
• Batch API, LoRA adapters and private custom LLM deployments
• On-demand DGX B300 GPUs at $5.89 per instance-hour

Strengths and weaknesses

• Strength: DeepSeek-V4-Flash-0731 at $0.06 input and $0.18 output per 1M tokens
• Strength: No long-term contracts or upfront costs
• Strength: Frequent model discounts, such as 38% off GLM-5.3 input when we checked
• Weakness: Discounted rates are promotions and can change
• Weakness: Most non-language models are billed by execution time, which is harder to forecast
• Weakness: gpt-oss-120B is not on the main pricing page, so like-for-like comparison is harder

Key facts

• Cheapest listed LLM: DeepSeek-V4-Flash-0731, $0.06 input per 1M tokens
• Max context: 1024k tokens on several models
• API: OpenAI-compatible, plus Batch API
• GPU rental: DGX B300 at $5.89 per instance-hour

Where it ranks

DeepInfra is No. 2 in our Best AI Inference Platforms verdict.