Polarison

Claude Haiku 4.5 vs DeepSeek V4.1 Flash: pricing and benchmarks

DeepSeek V4.1 Flash is 70% cheaper on input tokens ($0.30 vs $1.00 per 1M). DeepSeek V4.1 Flash is 76% cheaper on output tokens ($1.20 vs $5.00 per 1M). On our document Q&A workload (50,000 questions a month), DeepSeek V4.1 Flash costs $156.00 a month versus $550.00 for Claude Haiku 4.5, 72% less. Epoch AI has not published a capability index score for DeepSeek V4.1 Flash yet.

Prices verified September 14, 2026.

Which should you choose?

Overall capability
Too close to call

Epoch AI has not published a capability index score for DeepSeek V4.1 Flash yet.

Price
DeepSeek V4.1 Flash

DeepSeek V4.1 Flash costs $0.525 per 1M tokens (3:1 input-to-output mix) vs $2.00 for Claude Haiku 4.5, 74% less.

Pricing and specs

Claude Haiku 4.5DeepSeek V4.1 Flash
ProviderAnthropicDeepSeek
API model IDclaude-haiku-4-5-20251001deepseek-flash
Input / 1M tokens$1.00$0.30
Cached input / 1M tokens$0.10$0.006
Output / 1M tokens$5.00$1.20
Long-context rates
Context window200K tokens1M tokens
Max output64K tokens384K tokens
Batch discount50% off

Benchmarks

Claude Haiku 4.5DeepSeek V4.1 Flash
Epoch Capabilities Index142.4
GPQA Diamond· Science reasoning61.6%
FrontierMath (Tiers 1–3)· Advanced math
SimpleQA Verified· Factual accuracy13.2%
ARC-AGI-2· Abstract reasoning4.0%
DeepSWE· Coding
APEX-Agents· Agentic work8.9%

Source: Epoch AI, best recorded result per model (CC BY 4.0). A dash means no published score. See all benchmarks

Monthly cost for real workloads

WorkloadClaude Haiku 4.5DeepSeek V4.1 FlashDifference
Support chatbot
100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each.
$350.00$93.00DeepSeek V4.1 Flash 73% cheaper
Document Q&A (RAG)
50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each.
$550.00$156.00DeepSeek V4.1 Flash 72% cheaper
Coding agent
10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens.
$248.00$61.68DeepSeek V4.1 Flash 75% cheaper

Estimates use standard list prices and ignore cache-write surcharges. Different tokenizers can count the same text differently, so test with your own prompts.

Claude Haiku 4.5 vs DeepSeek V4.1 Flash cost calculator

Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.

Claude Haiku 4.5 pricing notes

Anthropic’s fastest model, with near-frontier intelligence.

  • Cache writes cost $1.25 (5-minute cache) or $2 (1-hour cache) per 1M tokens.
  • Uses Anthropic’s previous tokenizer.
Anthropic official pricing ↗

DeepSeek V4.1 Flash pricing notes

DeepSeek’s low-cost model with thinking and non-thinking modes, tool calls and vision input.

  • Prices shown are peak rates. Off-peak rates are half: peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday.
  • Compatible with both OpenAI-format and Anthropic-format APIs.
DeepSeek official pricing ↗

Frequently asked questions

Is Claude Haiku 4.5 cheaper than DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is 70% cheaper on input tokens ($0.30 vs $1.00 per 1M). DeepSeek V4.1 Flash is 76% cheaper on output tokens ($1.20 vs $5.00 per 1M). On our document Q&A workload (50,000 questions a month), DeepSeek V4.1 Flash costs $156.00 a month versus $550.00 for Claude Haiku 4.5, 72% less.
Which is more capable, Claude Haiku 4.5 or DeepSeek V4.1 Flash?
Epoch AI has not published a capability index score for DeepSeek V4.1 Flash yet.
How much does Claude Haiku 4.5 cost per 1M tokens?
Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens, and $0.10 per 1M cached input tokens on Anthropic’s standard tier.
How much does DeepSeek V4.1 Flash cost per 1M tokens?
DeepSeek V4.1 Flash costs $0.30 per 1M input tokens and $1.20 per 1M output tokens, and $0.006 per 1M cached input tokens on DeepSeek’s standard tier.
Which has the larger context window, Claude Haiku 4.5 or DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash has the larger context window: 1M tokens versus 200K for Claude Haiku 4.5.

Related comparisons