Progga DeepSeek V4.1 Flash
deepseek-v4.1-flash- Input
- BDT 14
- Output
- BDT 70
- Cached
- BDT 0.42
- Speed (TPS)
- 251.5 tok/s
- First token (TTFT)
- 4.7 s
Progga pricing
Model prices in BDT, without a subscription
Every price below is in Bangladeshi taka per 1 million tokens. Your prepaid balance works across both the API and Progga Chat.
Input
Tokens you send, including instructions, conversation history, and other request content.
Output
Tokens generated by the model in its response.
Cached input
Repeated input reused from a provider cache and billed at a lower rate.
Available models
BDT per 1 million tokens. Prices can include up to six decimal places.
Only active, currently routable models are listed.
Deepseek v4 Flash 0731
deepseek-v4-flash-0731- Input
- BDT 8.05
- Output
- BDT 16.1
- Cached
- BDT 1.61
- Speed (TPS)
- 400.4 tok/s
- First token (TTFT)
- 1.4 s
Deepseek v4 Flash (Vision Exp)
deepseek-v4-flash-vision-exp- Input
- BDT 18.48
- Output
- BDT 55.44
- Cached
- BDT 0.6
- Speed (TPS)
- —
- First token (TTFT)
- —
Deepseek v4 Pro 0813
deepseek-v4-pro-0813- Input
- BDT 50
- Output
- BDT 112
- Cached
- BDT 1.5
- Speed (TPS)
- —
- First token (TTFT)
- —
glm-5.2
glm-5.2- Input
- BDT 22
- Output
- BDT 73.8
- Cached
- BDT 3.5
- Speed (TPS)
- —
- First token (TTFT)
- —
GLM 5.3
glm-5.3- Input
- BDT 55.552
- Output
- BDT 194.432
- Cached
- BDT 8.3328
- Speed (TPS)
- —
- First token (TTFT)
- —
glm-5.3-flash
glm-5.3-flash- Input
- BDT 10.5
- Output
- BDT 35
- Cached
- BDT 2.1
- Speed (TPS)
- —
- First token (TTFT)
- —
kimi-k2.5
kimi-k2.5- Input
- BDT 49
- Output
- BDT 238
- Cached
- BDT 9.8
- Speed (TPS)
- —
- First token (TTFT)
- —
kimi-k2.6
kimi-k2.6- Input
- BDT 70
- Output
- BDT 278.6
- Cached
- BDT 7
- Speed (TPS)
- —
- First token (TTFT)
- —
kimi-k2.7-code
kimi-k2.7-code- Input
- BDT 77
- Output
- BDT 315
- Cached
- BDT 7
- Speed (TPS)
- —
- First token (TTFT)
- —
kimi-k3
kimi-k3- Input
- BDT 282.808
- Output
- BDT 1131.209
- Cached
- BDT 35.351
- Speed (TPS)
- —
- First token (TTFT)
- —
mimo-v2.5-pro
mimo-v2.5-pro- Input
- BDT 56
- Output
- BDT 112
- Cached
- BDT 0.42
- Speed (TPS)
- —
- First token (TTFT)
- —
minimax-m2.5
minimax-m2.5- Input
- BDT 15.4
- Output
- BDT 133
- Cached
- BDT 2.800001
- Speed (TPS)
- —
- First token (TTFT)
- —
muse-spark-1.3
muse-spark-1.3- Input
- BDT 175
- Output
- BDT 595
- Cached
- BDT 21
- Speed (TPS)
- —
- First token (TTFT)
- —
muse-spark-1.3-contributor
muse-spark-1.3-contributor- Input
- BDT 14
- Output
- BDT 28
- Cached
- BDT 0.5
- Speed (TPS)
- —
- First token (TTFT)
- —
qwen3.8-27b
qwen3.8-27b- Input
- BDT 25
- Output
- BDT 294
- Cached
- BDT 8.5
- Speed (TPS)
- —
- First token (TTFT)
- —
qwen3.8-flash
qwen3.8-flash- Input
- BDT 21
- Output
- BDT 65.8
- Cached
- BDT 2.24
- Speed (TPS)
- —
- First token (TTFT)
- —
Observed performance
- Higher TPS (tokens per second) is faster. Lower TTFT (time to first token) is faster.
- TPS and TTFT are observed medians over the last 24 hours of successful streaming API requests, refreshed every six hours.
- Client network latency is excluded, so your own request latency will be higher and actual performance varies.
- An em dash means Not enough recent data: fewer than ten recent requests were available for that model.
Metrics last calculated Sep 12, 2026, 6:00 PM.
How billing works
Requests reserve enough balance before they start, then settle against the model's actual reported token usage. Unused reserved balance is released. Your Billing and Usage pages show the resulting BDT cost.