DeepSeek V4 Flash 0731 vs GLM-4.5-Air
DeepSeek V4 Flash 0731 (DeepSeek) and GLM-4.5-Air (Z.ai) side by side: what each costs per million tokens through Rapid Router, how much context each takes, what each supports, and where independent benchmarks place them. Same API, same key; switching is a one-string change.
| DeepSeek V4 Flash 0731 | GLM-4.5-Air | |
|---|---|---|
| Input price per 1M | $0.060 | $0.030 |
| Output price per 1M | $0.180 | $0.140 |
| Context window | 1M tokens | 131K tokens |
| Max output | 384K tokens | 98K tokens |
| Input types | text | text |
| Capabilities | tools, JSON, reasoning | tools, reasoning |
| Author | DeepSeek | Z.ai |
| LMArena Overall | — | 1384 |
| LMArena Coding | — | 1397 |
| LMArena Math | — | 1396 |
| LMArena Creative writing | — | 1343 |
| LMArena Instruction following | — | 1354 |
| LMArena Hard prompts | — | 1379 |
| GPQA Diamond | 91.0% | — |
| OTIS Mock AIME | 94.4% | — |
| SimpleQA Verified | 33.6% | — |
| Humanity's Last Exam | — | 8.1% |
Scores from LMArena and Epoch AI, as published; a blank cell means not measured there.
What a month costs on each
| Workload | DeepSeek V4 Flash 0731 | GLM-4.5-Air |
|---|---|---|
| Chatbot month (15M in, 4M out) | $1.62 | $1.01 |
| RAG month (40M in, 3M out) | $2.94 | $1.62 |
| Coding month (60M in, 10M out) | $5.40 | $3.20 |
On a typical 75/25 input-output mix, GLM-4.5-Air costs less (about 36% less than DeepSeek V4 Flash 0731). DeepSeek V4 Flash 0731 takes the longer prompt at 1M tokens. Try your own numbers in the cost calculator.
Call either one
curl https://rapidrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $RAPIDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek/deepseek-v4-flash-0731", "messages": [{"role": "user", "content": "Hello"}]}'
# the other one: change the model string
-d '{"model": "z-ai/glm-4.5-air", ...}'Common questions
Which is cheaper, DeepSeek V4 Flash 0731 or GLM-4.5-Air?
GLM-4.5-Air is cheaper on a typical mix of 75% input and 25% output tokens, by about 36%. Through Rapid Router both are billed at the provider list price per million tokens.
Which has the larger context window?
DeepSeek V4 Flash 0731, at 1M tokens. GLM-4.5-Air offers 131K tokens.
Can I switch between DeepSeek V4 Flash 0731 and GLM-4.5-Air without changing code?
Yes. Both are callable at https://rapidrouter.ai/api/v1 with the same OpenAI-compatible request; only the model string changes (deepseek/deepseek-v4-flash-0731 or z-ai/glm-4.5-air).
How do I pay for DeepSeek V4 Flash 0731 or GLM-4.5-Air?
Top up a Rapid Router balance by card in US dollars, and both models debit that balance per request.
More DeepSeek models: DeepSeek API pricing · More GLM: Z.ai API pricing