#deepseek 3.2 exp
7 messages · Page 1 of 1 (latest)
I'm an AI assistant - my answers may be incorrect and I cannot see screenshots. Please verify information with the OpenRouter docs.
To help debug your "insufficient credits" error with DeepSeek V3.2 Exp, I need a bit more info:
- What is the exact error message you are seeing?
- Which model identifier are you using (e.g., deepseek/deepseek-v3.2-exp or something else)?
- Can you provide details about the code or API call you are making when this happens?
Regarding caching: "Caching" is listed as an endpoint feature for DeepSeek V3.2 Exp, but the documentation does not state that cache usage affects credit requirements or causes insufficient credit errors. Pricing is clearly listed as "$0.27 / M tokens input, $0.40 / M tokens output" for DeepSeek V3.2 Exp, and the cache feature is not explained as impacting billing OpenRouter Model Comparison.
Once you provide the details above, I can help further or escalate to support if needed. For billing or account issues, please email support@openrouter.ai, as billing is not handled on Discord.
-# This is an automated response powered by Answer HQ. Use !mute to stop the bot from responding.
It says that i have insufficient credits even when i have enough credits to use it.
It's deepseek-v3.2-exp
Thanks for clarifying you're using deepseek/deepseek-v3.2-exp. There is no documentation indicating that caching affects credit usage for this model. The pricing for DeepSeek V3.2 Exp is "$0.28/M input tokens, $0.42/M output tokens" and it is treated like other paid models on OpenRouter. There are no special cache-related credit requirements or restrictions listed for this model DeepSeek V3.2 Exp.
If you have sufficient credits but still receive an "insufficient credits" error, this is most likely a billing or account issue and not related to model caching. Please email support@openrouter.ai for help with your credits or billing balance, as billing issues are not handled on Discord.
-# This is an automated response powered by Answer HQ. Use !mute to stop the bot from responding.
Hello @dim helm looks like DeepSeek provider is out of balance again
Same trouble here
Yeah same here 