# Anthropic vs DeepInfra

Canonical: https://inetgeek.com/compare/anthropic-vs-deepinfra/

Every value below is read from Anthropic's and DeepInfra's own documentation. See https://inetgeek.com/methodology/ for how.

## At a glance

| Criterion | Anthropic | DeepInfra |
| --- | --- | --- |
| Pricing model | Per million tokens, priced separately for input and output and per model, with multipliers stacked on top: prompt caching, a 50% batch discount, a 1.1x uplift for US-only inference on Claude 4.6 and later, and a fast-mode premium. | Two products on one bill: per-token serverless inference with a separate cached-input rate for each model, and dedicated GPUs billed per minute and invoiced weekly. Models without per-token pricing are billed for inference execution time instead. |
| Input price, top model | $10 per million input tokens for Claude Fable 5.1, the most capable model. Claude Opus 5 is $5 and Claude Sonnet 5 is $2. | $1.30 per million input tokens for DeepSeek-V4-Pro, the most expensive model in its catalogue. Cached input is $0.10. |
| Output price, top model | $50 per million output tokens for Claude Fable 5.1. Claude Opus 5 is $25 and Claude Sonnet 5 is $10. | $2.60 per million output tokens for DeepSeek-V4-Pro. |
| Input price, cheapest model | $1 per million input tokens for Claude Haiku 4.5, the cheapest current model, with output at $5. | $0.06 per million input tokens for DeepSeek-V4-Flash-0731, with cached input at $0.015 and output at $0.18. DeepSeek itself charges $0.44 at peak for the same checkpoint and Fireworks $0.22. |
| Context window | 1M tokens on Claude Fable 5.1, Claude Opus 5 and Claude Sonnet 5; 200K on Claude Haiku 4.5. Anthropic states the full 1M window is billed at standard per-token rates. | 1024k tokens on the DeepSeek V4 models it serves; 160k on the V3 generation. The window is the model's rather than a platform limit. |
| Prompt caching | Supported | Supported |

## Where they differ

### Pricing model

- Anthropic: Per million tokens, priced separately for input and output and per model, with multipliers stacked on top: prompt caching, a 50% batch discount, a 1.1x uplift for US-only inference on Claude 4.6 and later, and a fast-mode premium. ([source](https://docs.claude.com/en/docs/about-claude/pricing))
- DeepInfra: Two products on one bill: per-token serverless inference with a separate cached-input rate for each model, and dedicated GPUs billed per minute and invoiced weekly. Models without per-token pricing are billed for inference execution time instead. ([source](https://deepinfra.com/pricing))

### Input price, top model

- Anthropic: $10 per million input tokens for Claude Fable 5.1, the most capable model. Claude Opus 5 is $5 and Claude Sonnet 5 is $2. ([source](https://docs.claude.com/en/docs/about-claude/pricing))
- DeepInfra: $1.30 per million input tokens for DeepSeek-V4-Pro, the most expensive model in its catalogue. Cached input is $0.10. ([source](https://deepinfra.com/pricing))

### Output price, top model

- Anthropic: $50 per million output tokens for Claude Fable 5.1. Claude Opus 5 is $25 and Claude Sonnet 5 is $10. ([source](https://docs.claude.com/en/docs/about-claude/pricing))
- DeepInfra: $2.60 per million output tokens for DeepSeek-V4-Pro. ([source](https://deepinfra.com/pricing))

### Input price, cheapest model

- Anthropic: $1 per million input tokens for Claude Haiku 4.5, the cheapest current model, with output at $5. ([source](https://docs.claude.com/en/docs/about-claude/pricing))
- DeepInfra: $0.06 per million input tokens for DeepSeek-V4-Flash-0731, with cached input at $0.015 and output at $0.18. DeepSeek itself charges $0.44 at peak for the same checkpoint and Fireworks $0.22. ([source](https://deepinfra.com/pricing))

### Context window

- Anthropic: 1M tokens on Claude Fable 5.1, Claude Opus 5 and Claude Sonnet 5; 200K on Claude Haiku 4.5. Anthropic states the full 1M window is billed at standard per-token rates. ([source](https://docs.claude.com/en/docs/about-claude/models/overview))
- DeepInfra: 1024k tokens on the DeepSeek V4 models it serves; 160k on the V3 generation. The window is the model's rather than a platform limit. ([source](https://deepinfra.com/pricing))

## Which should you choose?

Pick Anthropic if Teams that want the full 1M-token window at the standard per-token rate rather than a long-context surcharge, and that can use caching and batch to cut a frontier-model bill roughly in half.

Pick DeepInfra if Running open-weight models at the lowest published per-token rates here — DeepSeek-V4-Flash at $0.06 per million input is a fraction of what the lab itself charges — with dedicated H100s at $2.20 an hour if throughput demands it.

Consider something else: Anthropic — Its cheapest model is $1 per million input tokens, several times what the budget tiers at Google, OpenAI and DeepSeek charge, so high-volume simple work is priced against you.

Consider something else: DeepInfra — Only some models carry per-token pricing; the rest bill for inference execution time, which is a different and harder thing to forecast.

## Documented by only one

- Startup credit program: Anthropic: Claude for Startups: free credits and priority rate limits, amount undisclosed until application. Open to any early-stage founder with or without VC backing per the FAQ, though the main eligibility list also requires equity funding, founding within the last 4 years, and no prior Anthropic startup credits.
- Max output tokens: Anthropic: 128K tokens on the top three models, 64K on Claude Haiku 4.5. The Batch API supports up to 300K output tokens on several models behind a beta header.
- Batch discount: Anthropic: 50% off both input and output tokens through the Batch API, for asynchronous processing.
- H100 SXM, per GPU-hour: DeepInfra: $2.20 per GPU-hour for a dedicated H100 80GB — below every dedicated cloud in this dataset. A100 80GB is $0.89, H200 $2.69, B200 $3.69. Billed in minute granularity, invoiced weekly.
- Largest GPU offered: DeepInfra: 270GB per GPU on a B300, at $4.89 per GPU-hour.

## Questions this comparison answers

**Should I choose Anthropic or DeepInfra?**

Pick Anthropic if Teams that want the full 1M-token window at the standard per-token rate rather than a long-context surcharge, and that can use caching and batch to cut a frontier-model bill roughly in half.
Pick DeepInfra if Running open-weight models at the lowest published per-token rates here — DeepSeek-V4-Flash at $0.06 per million input is a fraction of what the lab itself charges — with dedicated H100s at $2.20 an hour if throughput demands it.