Pricing: Compare Groq API Pricing With Other API Providers
Check the latest prices of open-source LLM API providers. Evaluate and compare Groq API prices against other providers based on key metrics such as quality, context window, knowledge cutoff, and more.
API Providers Compared: Groq, Microsoft Azure, Amazon Bedrock, Together.ai, Fireworks AI, Baseten, Lepton AI, Deepinfra, Replicate, Databricks, Novita AI, and OctoAI.
Groq API Pricing
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
 | Gemma 2 9B | 8k | $0.20 | $0.20 | 71 |
| Gemma 7B Instruct | 8k | $0.07 | $0.07 | 45 |
 | Llama 3.1 Instruct 70B | 8k | $0.59 | $0.79 | 95 |
| Llama 3 Instruct 70B | 8k | $0.59 | $0.79 | 83 |
| Llama 3.1 Instruct 8B | 8k | $0.05 | $0.08 | 66 |
| Llama 3 Instruct 8B | 8k | $0.05 | $0.08 | 64 |
 | Mixtral 8x7B Instruct | 33k | $0.24 | $0.24 | 61 |
Microsoft Azure
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
| Llama 3 Instruct 70B | 8k | $0.59 | $0.79 | 83 |
| Llama 3 Instruct 8B | 8k | $0.37 | $1.10 | 64 |
Amazon Bedrock
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
| Llama 3 Instruct 70B | 8k | $2.65 | $3.50 | 83 |
| Llama 3.1 Instruct 8B | 128k | $0.30 | $0.60 | 66 |
| Llama 3 Instruct 8B | 8k | $0.30 | $0.60 | 64 |
| Mixtral 8x7B Instruct | 33k | $0.45 | $0.70 | 61 |
| Mixtral 7B Instruct | 33k | $0.15 | $0.20 | 40 |
Together.ai
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
| Gemma 2 9B | 8k | $0.30 | $0.30 | 71 |
| Gemma 2 27B | 8k | $0.80 | $0.80 | 78 |
| Gemma 7B Instruct | 8k | $0.20 | $0.20 | 45 |
| Llama 3.1 Instruct 70B Turbo | 4k | $0.88 | $0.88 | 95 |
| Llama 3.1 Instruct 405B Turbo | 4k | $5.00 | $5.00 | 100 |
| Llama 3 Instruct 70B Turbo | 8k | $0.88 | $0.88 | 83 |
| Llama 3.1 Instruct 8B Turbo | 33k | $0.18 | $0.18 | 66 |
| Llama 3 Instruct 8B | 8k | $0.20 | $0.20 | 64 |
| Mixtral 8x22B Instruct | 65k | $1.20 | $1.20 | 71 |
| Mixtral 8x7B Instruct | 33k | $0.60 | $0.60 | 61 |
| Mixtral 7B Instruct | 8k | $0.20 | $0.20 | 40 |
 | OpenChat 3.5 (1210) | 8k | $0.20 | $0.20 | 50 |
 | Qwen2 Instruct 72B | 33k | $0.90 | $0.90 | 83 |
 | Nous: Capybara 7B | 8k | $0.18 | $0.18 |
Fireworks AI
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
| Gemma 2 9B | 8k | $0.20 | $0.20 | 71 |
| Gemma 7B Instruct | 8k | $0.20 | $0.20 | 45 |
| Llama 3.1 Instruct 405B | 128k | $3.00 | $3.00 | 100 |
| Llama 3.1 Instruct 70B | 128k | $0.90 | $0.90 | 95 |
| Llama 3 Instruct 70B | 8k | $0.90 | $0.90 | 83 |
| Llama 3.1 Instruct 8B | 128k | $0.20 | $0.20 | 66 |
| Llama 3 Instruct 8B | 8k | $0.20 | $0.20 | 64 |
| Mixtral 8x22B Instruct | 65k | $1.20 | $1.20 | 71 |
| Mixtral 8x7B Instruct | 33k | $0.50 | $0.50 | 61 |
| Mixtral 7B Instruct | 33k | $0.20 | $0.20 | 40 |
| Qwen2 Instruct 72B | 33k | $0.90 | $0.90 | 83 |
Baseten
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
| Mistral 7B Instruct | 4k | $0.20 | $0.20 | 40 |
Lepton AI
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
| Llama 3.1 Instruct 405B | 128k | $2.80 | $2.80 | 100 |
| Llama 3.1 Instruct 70B | 128k | $0.80 | $0.80 | 95 |
| Llama 3 Instruct 70B | 8k | $0.80 | $0.80 | 83 |
| Llama 3.1 Instruct 8B | 128k | $0.70 | $0.70 | 66 |
| Llama 3 Instruct 8B | 8k | $0.07 | $0.07 | 64 |
| Mixtral 8x7B Instruct | 33k | $0.50 | $0.50 | 61 |
| Mixtral 7B Instruct | 33k | $0.07 | $0.07 | 40 |
Deepinfra
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
| Gemma 2 9B | 8k | $0.09 | $0.09 | 71 |
| Gemma 7B Instruct | 8k | $0.07 | $0.07 | 45 |
| Llama 3.1 Instruct 405B | 33k | $7.00 | $7.00 | 100 |
| Llama 3.1 Instruct 70B | 128k | $0.52 | $0.75 | 95 |
| Llama 3 Instruct 70B | 8k | $0.52 | $0.75 | 83 |
| Llama 3.1 Instruct 8B | 128k | $0.09 | $0.09 | 66 |
| Llama 3 Instruct 8B | 8k | $0.06 | $0.06 | 64 |
| Mixtral 8x22B Instruct | 65k | $0.65 | $0.65 | 71 |
| Mixtral 8x7B Instruct | 33k | $0.24 | $0.24 | 61 |
| Mixtral 7B Instruct | 8k | $0.06 | $0.77 | 40 |
| Phi-3 Medium Instruct 14B | 4k | $0.14 | $0.14 | |
| Qwen2 Instruct 72B | 33k | $0.56 | $0.90 | 83 |
| Qwen2 Instruct 7B | 33k | $0.07 | $0.07 | |
| OpenChat 3.5 (1210) | 8k | $0.07 | $0.07 | 50 |
Replicate
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
| Llama 3.1 Instruct 405B | 128k | $9.50 | $9.50 | 100 |
| Llama 3 Instruct 70B | 8k | $0.65 | $2.75 | 83 |
| Llama 3 Instruct 8B | 8k | $0.05 | $0.25 | 64 |
| Mixtral 8x7B Instruct | 33k | $0.30 | $1.00 | 61 |
| Mixtral 7B Instruct | 33k | $0.05 | $0.25 | 40 |
Novita AI
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
| Gemma 2 9B | 8k | $0.08 | $0.08 | 71 |
| Llama 3.1 Instruct 405B | 33k | $2.75 | $2.75 | 100 |
| Llama 3.1 Instruct 70B | 8k | $0.55 | $0.76 | 95 |
| Llama 3 Instruct 70B | 8k | $0.51 | $0.74 | 83 |
| Llama 3.1 Instruct 8B | 8k | $0.10 | $0.10 | 66 |
| Llama 3 Instruct 8B | 8k | $0.06 | $0.06 | 64 |
| Mixtral 7B Instruct | 33k | $0.06 | $0.06 | 40 |
| OpenChat 3.5 7B | 33k | $0.06 | $0.06 | 50 |
OctoAI
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
| Llama 3.1 Instruct 70B | 128k | $0.90 | $0.90 | 95 |
| Llama 3.1 Instruct 405B | 128k | $3.00 | $3.00 | 100 |
| Llama 3 Instruct 70B | 8k | $0.90 | $0.90 | 83 |
| Llama 3.1 Instruct 8B | 128k | $0.15 | $0.15 | 66 |
| Llama 3 Instruct 8B | 8k | $0.15 | $0.15 | 64 |
| Mixtral 8x22B Instruct | 65k | $1.20 | $1.20 | 71 |
| Mixtral 8x7B Instruct | 33k | $0.45 | $0.45 | 61 |
| Mixtral 7B Instruct | 33k | $0.15 | $0.15 | 40 |
| Qwen 2 7B Instruct | 33k | $0.15 | $0.15 |
Databricks
| Creator | Model | Context Window | Input Price $/1M | Ouput Price $/1M | Quality Index |
|---|---|---|---|---|---|
| Llama 3 Instruct 70B | 128k | $1.00 | $3.00 | 83 |
| Llama 3.1 Instruct 70B | 128k | $1.00 | $3.00 | 95 |
| Llama 3.1 Instruct 405B | 128k | $10.00 | $30.00 | 100 |
| Mixtral 8x7B Instruct | 33k | $0.75 | $2.25 | 61 |
Key Definitions
- Quality Index: A standardized score reflecting average performance across Chatbot Arena, MMLU, and MT-Bench benchmarks.
- Context Window: The maximum combined number of input and output tokens. (Note: Output token limits are often lower than input limits.)
- Input Price: Cost per token sent to the API in the request, in USD per million tokens.
- Output Price: Cost per token generated by the model (received from the API), in USD per million tokens.
- Knowledge Cutoff: The date the model’s training data was last updated. Information or events after this date may not be reflected in the model’s responses.
