D
Cogito V2 Preview Llama 109b Moe Pricing (Updated 2025)
This page tracks Cogito V2 Preview Llama 109b Moe pricing and compares it with 133 competitor models. Prices are shown per 1M tokens (cost per token) with clear examples so you can estimate spend quickly.
29 out of our 483 tracked models have had a price change in December.
Make informed model choices with updates on pricing, new releases, and tools.
Last updated: December 17, 2025 at 08:05 AM
Current Pricing (per 1M tokens)
Provider | Model | Input Cost ($/M) | Output Cost ($/M) | Cache Read Cost | Cache Write Cost | Request Cost | Context Length |
|---|---|---|---|---|---|---|---|
M Deepcogito | cogito-v2-preview-llama-109b-moe | $0.180 | $0.590 | - | - | - | 32,767 |
G Google | gemma-3-4b-it | $0.017 | $0.068 | - | - | - | 96,000 |
G Google | gemma-3n-e4b-it | $0.020 | $0.040 | - | - | - | 32,768 |
DS Deepseek | deepseek-r1-0528-qwen3-8b | $0.020 | $0.100 | - | - | - | 32,768 |
QW Qwen | qwen3-8b | $0.028 | $0.110 | - | - | - | 128,000 |
G Google | gemma-2-9b-it | $0.030 | $0.090 | - | - | - | 8,192 |
QW Qwen | qwen-2.5-coder-32b-instruct | $0.030 | $0.110 | - | - | - | 32,768 |
M Deepseek | deepseek-r1-distill-llama-70b | $0.030 | $0.130 | - | - | - | 131,072 |
QW Qwen | qwen2.5-vl-72b-instruct | $0.030 | $0.130 | - | - | - | 32,768 |
G Google | gemma-3-12b-it | $0.030 | $0.100 | - | - | - | 131,072 |
QW Qwen | qwen2.5-coder-7b-instruct | $0.030 | $0.090 | - | - | - | 32,768 |
O OpenAI | gpt-oss-20b | $0.030 | $0.140 | - | - | - | 131,072 |
O OpenAI | gpt-oss-120b | $0.039 | $0.190 | - | - | - | 131,072 |
O OpenAI | gpt-oss-120b | $0.039 | $0.190 | - | - | - | 131,072 |
QW Qwen | qwen-2.5-7b-instruct | $0.040 | $0.100 | - | - | - | 32,768 |
G Google | gemma-3-27b-it | $0.040 | $0.150 | - | - | - | 96,000 |
QW Qwen | qwen-turbo | $0.050 | $0.200 | $0.020 | - | - | 1,000,000 |
QW Qwen | qwen2.5-vl-32b-instruct | $0.050 | $0.220 | - | - | - | 16,384 |
QW Qwen | qwen3-14b | $0.050 | $0.220 | - | - | - | 40,960 |
O OpenAI | gpt-5-nano | $0.050 | $0.400 | $0.005 | - | - | 400,000 |
QW Qwen | qwen3-30b-a3b-thinking-2507 | $0.051 | $0.340 | - | - | - | 32,768 |
QW Qwen | qwen3-30b-a3b | $0.060 | $0.220 | - | - | - | 40,960 |
QW Qwen | qwen3-coder-30b-a3b-instruct | $0.060 | $0.250 | - | - | - | 262,144 |
QW Qwen | qwen3-vl-8b-instruct | $0.064 | $0.400 | - | - | - | 131,072 |
QW Qwen | qwen-2.5-72b-instruct | $0.070 | $0.260 | - | - | - | 32,768 |
QW Qwen | qwen3-235b-a22b-2507 | $0.071 | $0.463 | - | - | - | 262,144 |
G Google | gemini-2.0-flash-lite-001 | $0.075 | $0.300 | - | - | - | 1,048,576 |
O OpenAI | gpt-oss-safeguard-20b | $0.075 | $0.300 | $0.037 | - | - | 131,072 |
QW Qwen | qwen3-32b | $0.080 | $0.240 | - | - | - | 40,960 |
QW Qwen | qwen3-30b-a3b-instruct-2507 | $0.080 | $0.330 | - | - | - | 262,144 |
QW Qwen | qwen3-next-80b-a3b-instruct | $0.090 | $1.100 | - | - | - | 262,144 |
G Google | gemini-2.0-flash-001 | $0.100 | $0.400 | $0.025 | $0.183 | - | 1,048,576 |
O OpenAI | gpt-4.1-nano | $0.100 | $0.400 | $0.025 | - | - | 1,047,576 |
G Google | gemini-2.5-flash-lite | $0.100 | $0.400 | $0.010 | $0.183 | - | 1,048,576 |
QW Qwen | qwen3-235b-a22b-thinking-2507 | $0.110 | $0.600 | - | - | - | 262,144 |
DS Deepseek | deepseek-r1-distill-qwen-14b | $0.120 | $0.120 | - | - | - | 32,768 |
QW Qwen | qwen3-next-80b-a3b-thinking | $0.120 | $1.200 | - | - | - | 131,072 |
O OpenAI | gpt-4o-mini | $0.150 | $0.600 | $0.075 | - | - | 128,000 |
QW Qwen | qwq-32b | $0.150 | $0.400 | - | - | - | 32,768 |
O OpenAI | gpt-4o-mini-search-preview | $0.150 | $0.600 | - | - | $0.028 | 128,000 |
DS Deepseek | deepseek-chat-v3-0324 | $0.150 | $0.750 | - | - | - | 8,192 |
DS Deepseek | deepseek-chat-v3.1 | $0.150 | $0.750 | - | - | - | 8,192 |
QW Qwen | qwen3-vl-30b-a3b-instruct | $0.150 | $0.600 | - | - | - | 262,144 |
QW Qwen | qwen3-vl-30b-a3b-thinking | $0.160 | $0.800 | - | - | - | 131,072 |
QW Qwen | qwen3-235b-a22b | $0.180 | $0.540 | - | - | - | 40,960 |
QW Qwen | qwen3-vl-8b-thinking | $0.180 | $2.100 | - | - | - | 256,000 |
QW Qwen | qwen-2.5-vl-7b-instruct | $0.200 | $0.200 | - | - | - | 32,768 |
QW Qwen | qwen3-vl-235b-a22b-instruct | $0.200 | $1.200 | - | - | - | 262,144 |
QW Qwen | qwen-vl-plus | $0.210 | $0.630 | - | - | - | 7,500 |
DS Deepseek | deepseek-v3.1-terminus | $0.210 | $0.790 | $0.168 | - | - | 163,840 |
DS Deepseek | deepseek-v3.1-terminus | $0.210 | $0.790 | $0.168 | - | - | 163,840 |
DS Deepseek | deepseek-v3.2-exp | $0.210 | $0.320 | - | - | - | 163,840 |
QW Qwen | qwen3-coder | $0.220 | $1.800 | - | - | - | 262,144 |
QW Qwen | qwen3-coder | $0.220 | $0.950 | - | - | - | 262,144 |
DS Deepseek | deepseek-r1-distill-qwen-32b | $0.240 | $0.240 | - | - | - | 64,000 |
DS Deepseek | deepseek-v3.2 | $0.240 | $0.380 | $0.190 | - | - | 163,840 |
A Anthropic | claude-3-haiku | $0.250 | $1.250 | $0.030 | $0.300 | - | 200,000 |
O OpenAI | gpt-5-mini | $0.250 | $2.000 | $0.025 | - | - | 400,000 |
O OpenAI | gpt-5.1-codex-mini | $0.250 | $2.000 | $0.025 | - | - | 400,000 |
DS Deepseek | deepseek-v3.2-speciale | $0.270 | $0.410 | - | - | - | 163,840 |
DS Deepseek | deepseek-chat | $0.300 | $1.200 | - | - | - | 163,840 |
DS Deepseek | deepseek-r1 | $0.300 | $1.200 | - | - | - | 163,840 |
G Google | gemini-2.5-flash | $0.300 | $2.500 | $0.030 | $0.383 | - | 1,048,576 |
G Google | gemini-2.5-flash-image-preview | $0.300 | $2.500 | - | - | - | 32,768 |
QW Qwen | qwen3-coder-flash | $0.300 | $1.500 | $0.080 | - | - | 128,000 |
QW Qwen | qwen3-vl-235b-a22b-thinking | $0.300 | $1.200 | - | - | - | 262,144 |
G Google | gemini-2.5-flash-image | $0.300 | $2.500 | - | - | - | 32,768 |
QW Qwen | qwen-plus | $0.400 | $1.200 | $0.160 | - | - | 131,072 |
O OpenAI | gpt-4.1-mini | $0.400 | $1.600 | $0.100 | - | - | 1,047,576 |
DS Deepseek | deepseek-r1-0528 | $0.400 | $1.750 | - | - | - | 163,840 |
O OpenAI | gpt-3.5-turbo | $0.500 | $1.500 | - | - | - | 16,385 |
DS Deepseek | deepseek-prover-v2 | $0.500 | $2.180 | - | - | - | 163,840 |
QW Qwen | qwen3-vl-32b-instruct | $0.500 | $1.500 | - | - | - | 262,144 |
G Google | gemma-2-27b-it | $0.650 | $0.650 | - | - | - | 8,192 |
A Anthropic | claude-3.5-haiku | $0.800 | $4.000 | $0.080 | $1.000 | - | 200,000 |
QW Qwen | qwen-vl-max | $0.800 | $3.200 | - | - | - | 131,072 |
M Deepcogito | cogito-v2-preview-llama-70b | $0.880 | $0.880 | - | - | - | 32,768 |
O OpenAI | gpt-3.5-turbo-0613 | $1.000 | $2.000 | - | - | - | 4,095 |
QW Qwen | qwen3-coder-plus | $1.000 | $5.000 | $0.100 | - | - | 128,000 |
A Anthropic | claude-haiku-4.5 | $1.000 | $5.000 | $0.100 | $1.250 | - | 200,000 |
O OpenAI | o3-mini | $1.100 | $4.400 | $0.550 | - | - | 200,000 |
O OpenAI | o3-mini-high | $1.100 | $4.400 | $0.550 | - | - | 200,000 |
O OpenAI | o4-mini | $1.100 | $4.400 | $0.275 | - | - | 200,000 |
O OpenAI | o4-mini-high | $1.100 | $4.400 | $0.275 | - | - | 200,000 |
QW Qwen | qwen3-max | $1.200 | $6.000 | $0.240 | - | - | 256,000 |
G Google | gemini-2.5-pro-preview | $1.250 | $10.000 | $0.310 | $1.625 | - | 1,048,576 |
G Google | gemini-2.5-pro | $1.250 | $10.000 | $0.125 | $1.625 | - | 1,048,576 |
O OpenAI | gpt-5 | $1.250 | $10.000 | $0.125 | - | - | 400,000 |
O OpenAI | gpt-5-chat | $1.250 | $10.000 | $0.125 | - | - | 128,000 |
O OpenAI | gpt-5-codex | $1.250 | $10.000 | $0.125 | - | - | 400,000 |
O OpenAI | gpt-5.1-codex | $1.250 | $10.000 | $0.125 | - | - | 400,000 |
O OpenAI | gpt-5.1-chat | $1.250 | $10.000 | $0.125 | - | - | 128,000 |
O OpenAI | gpt-5.1 | $1.250 | $10.000 | $0.125 | - | - | 400,000 |
D Deepcogito | cogito-v2.1-671b | $1.250 | $1.250 | - | - | - | 128,000 |
O OpenAI | gpt-5.1-codex-max | $1.250 | $10.000 | $0.125 | - | - | 400,000 |
O OpenAI | gpt-3.5-turbo-instruct | $1.500 | $2.000 | - | - | - | 4,095 |
O OpenAI | codex-mini | $1.500 | $6.000 | $0.375 | - | - | 200,000 |
QW Qwen | qwen-max | $1.600 | $6.400 | $0.640 | - | - | 32,768 |
O OpenAI | gpt-5.2 | $1.750 | $14.000 | $0.175 | - | - | 400,000 |
O OpenAI | gpt-5.2-chat | $1.750 | $14.000 | $0.175 | - | - | 128,000 |
O OpenAI | gpt-4.1 | $2.000 | $8.000 | $0.500 | - | - | 1,047,576 |
O OpenAI | o3 | $2.000 | $8.000 | $0.500 | - | - | 200,000 |
O OpenAI | o4-mini-deep-research | $2.000 | $8.000 | $0.500 | - | - | 200,000 |
G Google | gemini-3-pro-preview | $2.000 | $12.000 | $0.200 | $2.375 | - | 1,048,576 |
G Google | gemini-3-pro-image-preview | $2.000 | $12.000 | - | - | - | 65,536 |
O OpenAI | gpt-4o | $2.500 | $10.000 | $1.250 | - | - | 128,000 |
O OpenAI | gpt-4o-search-preview | $2.500 | $10.000 | - | - | $0.035 | 128,000 |
O OpenAI | gpt-4o-audio-preview | $2.500 | $10.000 | - | - | - | 128,000 |
O OpenAI | gpt-5-image-mini | $2.500 | $2.000 | $0.250 | - | - | 400,000 |
O OpenAI | gpt-3.5-turbo-16k | $3.000 | $4.000 | - | - | - | 16,385 |
A Anthropic | claude-3.7-sonnet | $3.000 | $15.000 | $0.300 | $3.750 | - | 200,000 |
A Anthropic | claude-3.7-sonnet | $3.000 | $15.000 | $0.300 | $3.750 | - | 200,000 |
A Anthropic | claude-sonnet-4 | $3.000 | $15.000 | $0.300 | $3.750 | - | 1,000,000 |
A Anthropic | claude-sonnet-4.5 | $3.000 | $15.000 | $0.300 | $3.750 | - | 1,000,000 |
M Deepcogito | cogito-v2-preview-llama-405b | $3.500 | $3.500 | - | - | - | 32,768 |
O OpenAI | chatgpt-4o-latest | $5.000 | $15.000 | - | - | - | 128,000 |
A Anthropic | claude-opus-4.5 | $5.000 | $25.000 | $0.500 | $6.250 | - | 200,000 |
O OpenAI | gpt-4o | $6.000 | $18.000 | - | - | - | 128,000 |
A Anthropic | claude-3.5-sonnet | $6.000 | $30.000 | - | - | - | 200,000 |
O OpenAI | gpt-4-1106-preview | $10.000 | $30.000 | - | - | - | 128,000 |
O OpenAI | gpt-4-turbo-preview | $10.000 | $30.000 | - | - | - | 128,000 |
O OpenAI | gpt-4-turbo | $10.000 | $30.000 | - | - | - | 128,000 |
O OpenAI | o3-deep-research | $10.000 | $40.000 | $2.500 | - | - | 200,000 |
O OpenAI | gpt-5-image | $10.000 | $10.000 | $1.250 | - | - | 400,000 |
A Anthropic | claude-3-opus | $15.000 | $75.000 | $1.500 | $18.750 | - | 200,000 |
O OpenAI | o1 | $15.000 | $60.000 | $7.500 | - | - | 200,000 |
A Anthropic | claude-opus-4 | $15.000 | $75.000 | $1.500 | $18.750 | - | 200,000 |
A Anthropic | claude-opus-4.1 | $15.000 | $75.000 | $1.500 | $18.750 | - | 200,000 |
O OpenAI | gpt-5-pro | $15.000 | $120.000 | - | - | - | 400,000 |
O OpenAI | o3-pro | $20.000 | $80.000 | - | - | - | 200,000 |
O OpenAI | gpt-5.2-pro | $21.000 | $168.000 | - | - | - | 400,000 |
O OpenAI | gpt-4 | $30.000 | $60.000 | - | - | - | 8,191 |
O OpenAI | gpt-4-0314 | $30.000 | $60.000 | - | - | - | 8,191 |
O OpenAI | o1-pro | $150.000 | $600.000 | - | - | - | 200,000 |
* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.
What does "cost per token" mean?
Tokens are the basic units that AI models use to process text. Generally, 1,000 tokens ≈ ~750 words. The cost per token determines how much you pay for each unit of text processed by the model.
Formula: Total Cost = (tokens / 1,000) × price per 1K tokens
Examples
Example usage with Cogito V2 Preview Llama 109b Moe: A 500-word prompt + 300-word response ≈ ~1,067 tokens total.
- • 1,000 tokens ≈ ~750 words of text
- • Short email: ~200-400 tokens
- • Blog post: ~1,000-3,000 tokens
- • Research paper: ~10,000+ tokens
Cogito V2 Preview Llama 109b Moe Cost Example:
1,000 input tokens + 500 output tokens = $0.000475
All Provider Models
Loading provider information...