Alexey Shurov.
Free tool

Claude vs DeepSeek API pricing, compared model by model

On 10 November 2026 the cheapest Anthropic model, Claude Haiku 5.5, costs $0.10 per million input tokens against $0.07 for the cheapest DeepSeek model, DeepSeek V4 Flash 0731, and the typical DeepSeek model is the cheaper of the two.

Prices checked 10 November 2026 at 06.00 UTC . Source OpenRouter public model list . US dollars per million tokens

At a glance

Claude (Anthropic)DeepSeek (DeepSeek)
Models listed1614
Cheapest modelClaude Haiku 5.5, $0.10 in, $0.50 outDeepSeek V4 Flash 0731, $0.07 in, $0.14 out
Most expensive modelClaude Opus 4.1, $15.00 in, $75.00 outDeepSeek V4 Pro 0423, $0.90 in, $1.50 out
Median input price$5.00$0.265
Median output price$25.00$0.92
Largest context1M, Claude Fable 5.21.05M, DeepSeek V4.1 Flash 1017
Newest modelClaude Fable 5.2, 2026-11-09DeepSeek V4.1 Flash 1017, 2026-10-17
Models with a batch price163

Every model, with your monthly cost

ModelProviderInputOutputCached inputBatch in / outContextYour monthListed
Claude Fable 5.2Anthropic$8.00$40.00$0.20$4.00 / $20.001M$1,080.002026-11-09
DeepSeek V4.1 Flash 1017DeepSeek$0.15$0.60$0.003$0.011 / $0.201.05M$18.002026-10-17
Claude Haiku 5.5Anthropic$0.10$0.50$0.01$0.05 / $0.251M$13.502026-10-07
Claude Sonnet 5.5Anthropic$2.00$10.00$0.10$1.00 / $5.001M$270.002026-09-28
Claude Opus 5.5Anthropic$4.00$20.00$0.20$2.00 / $10.001M$540.002026-09-22
DeepSeek V4.1 Flash
Relace, cheapest of 30 hosts
DeepSeek$0.006$0.50$0.005$0.112 / $0.3361.05M$7.862026-09-10
Claude Fable 5.1Anthropic$10.00$50.00$0.25$5.00 / $25.001M$1,350.002026-09-01
DeepSeek V4 Flash Vision Exp
DeepInfra, cheapest of 2 hosts
DeepSeek$0.44$1.32$0.0141.05M$46.202026-08-21
DeepSeek V4 Pro 0813DeepSeek$0.66$1.98$0.0221.05M$69.302026-08-12
DeepSeek V4 Flash 0731
Relace, cheapest of 24 hosts
DeepSeek$0.07$0.14$0.014$0.048 / $0.1441.05M$6.302026-07-31
Claude Opus 5Anthropic$5.00$25.00$0.50$2.50 / $12.501M$675.002026-07-24
Claude Sonnet 5Anthropic$2.00$10.00$0.20$1.00 / $5.001M$270.002026-06-30
Claude Fable 5Anthropic$10.00$50.00$1.00$5.00 / $25.001M$1,350.002026-06-09
Claude Opus 4.8Anthropic$5.00$25.00$0.50$2.50 / $12.501M$675.002026-05-27
DeepSeek V4 Pro 0423
Relace, cheapest of 12 hosts
DeepSeek$0.90$1.50$0.251.05M$76.502026-04-24
DeepSeek V4 Flash 0423
DeepInfra, cheapest of 13 hosts
DeepSeek$0.09$0.18$0.0181.05M$8.102026-04-24
Claude Opus 4.7Anthropic$5.00$25.00$0.50$2.50 / $12.501M$675.002026-04-16
Claude Sonnet 4.6Anthropic$3.00$15.00$0.30$1.50 / $7.501M$405.002026-02-17
Claude Opus 4.6Anthropic$5.00$25.00$0.50$2.50 / $12.501M$675.002026-02-04
DeepSeek V3.2
DeepInfra, cheapest of 7 hosts
DeepSeek$0.26$0.38$0.13164K$21.302025-12-01
Claude Opus 4.5Anthropic$5.00$25.00$0.50$2.50 / $12.50200K$675.002025-11-24
Claude Haiku 4.5Anthropic$1.00$5.00$0.10$0.50 / $2.50200K$135.002025-10-15
Claude Sonnet 4.5Anthropic$3.00$15.00$0.30$1.50 / $7.501M$405.002025-09-29
DeepSeek V3.2 Exp
served by SiliconFlow
DeepSeek$0.27$0.41164K$22.352025-09-29
DeepSeek V3.1 Terminus
served by SiliconFlow
DeepSeek$0.27$1.00164K$31.202025-09-22
DeepSeek V3.1
DeepInfra, cheapest of 4 hosts
DeepSeek$0.25$0.95$0.13164K$29.252025-08-21
Claude Opus 4.1
served by Amazon Bedrock
Anthropic$15.00$75.00$1.50$7.50 / $37.50200K$2,025.002025-08-05
R1 0528
DeepInfra, cheapest of 3 hosts
DeepSeek$0.50$2.15$0.35164K$62.252025-05-28
DeepSeek V3 0324
SiliconFlow, cheapest of 2 hosts
DeepSeek$0.25$1.00164K$30.002025-03-24
DeepSeek V3
DeepInfra, cheapest of 2 hosts
DeepSeek$0.32$0.89164K$32.552024-12-26

All Claude prices . All DeepSeek prices . Every provider

Common questions

Is Claude cheaper than DeepSeek?

On 10 November 2026, the median Anthropic model on this list costs $5.00 per million input tokens and $25.00 per million output tokens, against $0.265 and $0.92 for DeepSeek. By that measure DeepSeek is cheaper, but compare the specific models you would use, since both providers sell models at very different price points.

What is the cheapest Claude model compared with the cheapest DeepSeek model?

The cheapest Anthropic model on this list is Claude Haiku 5.5 at $0.10 in and $0.50 out per million tokens. The cheapest DeepSeek model is DeepSeek V4 Flash 0731 at $0.07 in and $0.14 out.

Which has the larger context window, Claude or DeepSeek?

The largest Claude context on this list is 1M tokens (Claude Fable 5.2) and the largest DeepSeek context is 1.05M tokens (DeepSeek V4.1 Flash 1017).

How should I choose between Claude and DeepSeek for a production agent?

Price per token is one input. Run both on a set of your own real cases, count how often each needs a retry or a human check, and compare the total cost of a correct answer rather than the cost of a token.

Choosing a model for a production agent

Price is one input. Quality on your own cases, latency and the cost of retries decide the rest. Tell me what you are building.

shurco.aiGuidesFree toolsSolutionsInsightsWork with meRSSllms.txt