PROVIDER
DekaLLM
Published provider information and recorded endpoint observations.
Models
- DeepSeek: DeepSeek V4 Pro 0813
- Google: Gemma 4 26B A4B
- Google: Gemma 4 26B A4B
- Mistral: Mistral Nemo
- NVIDIA: Nemotron 3 Super
- NVIDIA: Nemotron 3 Super
- OpenAI: gpt-oss-120b
- OpenAI: gpt-oss-120b
- OpenAI: gpt-oss-20b
- OpenAI: gpt-oss-20b
- Qwen: Qwen3 30B A3B Instruct 2507
- Qwen: Qwen3.6 35B A3B
- Qwen: Qwen3.8 27B
- Z.ai: GLM 5.3
- Z.ai: GLM 5.3
Uptime · last 24 hours
97.2%
Input $0.88 / 1M tokens · Output $3.8 / 1M tokens
Context 1,048,576 tokens · Max output 943,718 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$3.8 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.15 / 1M tokens- Inputprompt
$0.88 / 1M tokens
Uptime · last 24 hours
100.0%
Input $0.06 / 1M tokens · Output $0.33 / 1M tokens
Context 262,144 tokens · Max output 235,929 tokens
Quantization BF16 · Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Tools, Tool choice, Logprobs, Top logprobs, Response format
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$0.33 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.04 / 1M tokens- Inputprompt
$0.06 / 1M tokens
Uptime · last 24 hours
100.0%
Input $0.06 / 1M tokens · Output $0.33 / 1M tokens
Context 262,144 tokens · Max output 235,929 tokens
Quantization BF16 · Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Tools, Tool choice, Logprobs, Top logprobs, Response format
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$0.33 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.04 / 1M tokens- Inputprompt
$0.06 / 1M tokens
Uptime · last 24 hours
100.0%
Input $0.018 / 1M tokens · Output $0.03 / 1M tokens
Context 131,072 tokens · Max output 104,857 tokens
Quantization FP8 · Status: Active
Parameters: Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Structured outputs, Logprobs, Top logprobs
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$0.03 / 1M tokens- Discountdiscount
0Unit not specified in source record- Inputprompt
$0.018 / 1M tokens
Uptime · last 24 hours
99.9%
Input $0.08 / 1M tokens · Output $0.45 / 1M tokens
Context 262,144 tokens · Max output 235,929 tokens
Quantization FP8 · Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Tools, Logprobs, Top logprobs, Structured outputs, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$0.45 / 1M tokens- Discountdiscount
0Unit not specified in source record- Inputprompt
$0.08 / 1M tokens
Uptime · last 24 hours
99.9%
Input $0.08 / 1M tokens · Output $0.45 / 1M tokens
Context 262,144 tokens · Max output 235,929 tokens
Quantization FP8 · Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Tools, Logprobs, Top logprobs, Structured outputs, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$0.45 / 1M tokens- Discountdiscount
0Unit not specified in source record- Inputprompt
$0.08 / 1M tokens
Uptime · last 24 hours
99.9%
Input $0.03 / 1M tokens · Output $0.18 / 1M tokens
Context 131,072 tokens · Max output 117,964 tokens
Quantization BF16 · Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$0.18 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.03 / 1M tokens- Inputprompt
$0.03 / 1M tokens
Uptime · last 24 hours
99.9%
Input $0.03 / 1M tokens · Output $0.18 / 1M tokens
Context 131,072 tokens · Max output 117,964 tokens
Quantization BF16 · Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$0.18 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.03 / 1M tokens- Inputprompt
$0.03 / 1M tokens
Uptime · last 24 hours
100.0%
Input $0.029 / 1M tokens · Output $0.14 / 1M tokens
Context 131,072 tokens · Max output 117,964 tokens
Quantization BF16 · Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$0.14 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.029 / 1M tokens- Inputprompt
$0.029 / 1M tokens
Uptime · last 24 hours
100.0%
Input $0.029 / 1M tokens · Output $0.14 / 1M tokens
Context 131,072 tokens · Max output 117,964 tokens
Quantization BF16 · Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$0.14 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.029 / 1M tokens- Inputprompt
$0.029 / 1M tokens
Uptime · last 24 hours
99.6%
Input $0.09 / 1M tokens · Output $0.3 / 1M tokens
Context 262,144 tokens · Max output 235,929 tokens
Status: Active
Parameters: Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$0.3 / 1M tokens- Discountdiscount
0Unit not specified in source record- Inputprompt
$0.09 / 1M tokens
Uptime · last 24 hours
99.8%
Input $0.1 / 1M tokens · Output $1 / 1M tokens
Context 262,144 tokens · Max output 235,929 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Tools, Tool choice, Logprobs, Top logprobs, Structured outputs, Response format
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$1 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.05 / 1M tokens- Inputprompt
$0.1 / 1M tokens
Uptime · last 24 hours
99.4%
Input $0.04 / 1M tokens · Output $2.5 / 1M tokens
Context 262,144 tokens · Max output 235,929 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$2.5 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.02 / 1M tokens- Inputprompt
$0.04 / 1M tokens
Uptime · last 24 hours
99.7%
Input $0.18 / 1M tokens · Output $2.95 / 1M tokens
Context 1,048,576 tokens · Max output 943,718 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$2.95 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.15 / 1M tokens- Inputprompt
$0.18 / 1M tokens
Uptime · last 24 hours
99.7%
Input $0.18 / 1M tokens · Output $2.95 / 1M tokens
Context 1,048,576 tokens · Max output 943,718 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Frequency penalty, Logit bias, Max tokens, Presence penalty, Seed, Stop, Temperature, Top p, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$2.95 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.15 / 1M tokens- Inputprompt
$0.18 / 1M tokens