Claude 3.7 Sonnet
Anthropic · text, image → text
Support for the thinking parameter through the original Claude SDK.
Input$3.3 /M
Output$16.5 /M
← ModelsClaude 3.7 Sonnet
DeepSeek V4 Flash
Claude 3.7 Sonnet vs DeepSeek V4 Flash
Compare Claude 3.7 Sonnet from Anthropic and DeepSeek V4 Flash from DeepSeek on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Claude 3.7 SonnetDeepSeek V4 Flash+ Add model · 2/4
DeepSeek V4 Flash
DeepSeek · text → text
(This model currently points to the older 0423 version; if you need to request the latest version, you can choose the model deepseek-v4-flash-0731)DeepSeek-V4 features an ultra-long context of one million characters and achieves leading performance domestically and in the open-source domain in agent capabilities, world knowledge, and reasoning.
Input$0.142 /M
Output$0.284 /M
Cache read$0.0284 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Claude 3.7 Sonnet
DeepSeek V4 Flash
Input /M
$3.3
$0.142
Output /M
$16.5
$0.284
Cache read /M
-
$0.0284
Context length
200,000
1,000,000
Max output
128,000
384,000
Time to First Token
0.6 s
1.0 s
Throughput
57.3 tok/s
66.5 tok/s
Modalities
textimage
text
Supported Parameters
thinkingtoolsfunction callingstructured outputs
toolsfunction callingstructured outputsthinking
API Formats
chat_completions · claude_api
Released
-
April 24, 2026
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
claude-3-7-sonnetdeepseek-v4-flash
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
claude-3-7-sonnetdeepseek-v4-flash
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
claude-3-7-sonnetdeepseek-v4-flash
13401380142014601500
Overall
13711436
Coding
14301483
Math
13621426
Hard prompts
13981459
Instruction following
13841428
Multi-turn
13961452
Creative writing
13761408
Longer query
14101448
Chinese
13811473
English
13851445
Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.
Cost calculator
Estimate your monthly bill for the same workload on each model.
DeepSeek V4 Flash
$12.78 /mo
Claude 3.7 Sonnet
$446 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Claude 3.7 Sonnet, DeepSeek V4 Flash?
DeepSeek V4 Flash: $0.284/M output tokens; Claude 3.7 Sonnet: $16.5/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
DeepSeek V4 Flash: 1483; Claude 3.7 Sonnet: 1430 (LMArena coding leaderboard).
Which responds faster?
Claude 3.7 Sonnet: 0.6s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
How large is each context window?
Claude 3.7 Sonnet accepts 200,000 and DeepSeek V4 Flash accepts 1,000,000 input tokens. Maximum output per request is 128,000 tokens on Claude 3.7 Sonnet and 384,000 tokens on DeepSeek V4 Flash.
Which one generates tokens faster?
DeepSeek V4 Flash at 66.5 tok/s and Claude 3.7 Sonnet at 57.3 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
Claude 3.7 Sonnet accepts text and image input and supports thinking, tool calling, function calling and structured outputs; DeepSeek V4 Flash accepts text input and supports tool calling, function calling, structured outputs and thinking.
Can I call Claude 3.7 Sonnet and DeepSeek V4 Flash with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
