post https://api.edenai.run/v2/text/chat
Available Providers
| Provider | Model | Version | Price | Billing unit |
|---|---|---|---|---|
| openai | o1 | v1Beta | 60.0 (per 1000000 token) | 1 token |
| openai | o3-mini | v1Beta | 4.4 (per 1000000 token) | 1 token |
| openai | gpt-4o | v1Beta | 10.0 (per 1000000 token) | 1 token |
| openai | gpt-4o-mini | v1Beta | 0.6 (per 1000000 token) | 1 token |
| openai | - | v1Beta | 10.0 (per 1000000 token) | 1 token |
| openai | gpt-4 | v1Beta | 60.0 (per 1000000 token) | 1 token |
| openai | o1-preview | v1Beta | 60.0 (per 1000000 token) | 1 token |
| openai | o1-mini | v1Beta | 12.0 (per 1000000 token) | 1 token |
| openai | gpt-4o-2024-05-13 | v1Beta | 15.0 (per 1000000 token) | 1 token |
| openai | gpt-4-turbo | v1Beta | 30.0 (per 1000000 token) | 1 token |
| openai | gpt-4.5-preview-2025-02-27 | v1Beta | 150.0 (per 1000000 token) | 1 token |
| openai | o1-2024-12-17 | v1Beta | 60.0 (per 1000000 token) | 1 token |
| gemini-1.5-flash-8b-latest | v1 | 0.3 (per 1000000 token) | 1 token | |
| - | v1 | 0.6 (per 1000000 token) | 1 token | |
| gemini-2.0-flash | v1 | 0.4 (per 1000000 token) | 1 token | |
| gemini-2.0-flash-lite-preview-02-05 | v1 | 0.3 (per 1000000 token) | 1 token | |
| gemini-1.5-flash-latest | v1 | 0.6 (per 1000000 token) | 1 token | |
| gemini-1.5-flash | v1 | 0.6 (per 1000000 token) | 1 token | |
| gemini-1.5-pro | v1 | 10.0 (per 1000000 token) | 1 token | |
| gemini-1.5-pro-latest | v1 | 10.0 (per 1000000 token) | 1 token | |
| gemini-1.5-flash-8b | v1 | 0.3 (per 1000000 token) | 1 token | |
| cohere | - | 2022-12-06 | 2.0 (per 1000000 token) | 1 token |
| cohere | command-light | 2022-12-06 | 0.6 (per 1000000 token) | 1 token |
| cohere | command-nightly | 2022-12-06 | 2.0 (per 1000000 token) | 1 token |
| cohere | command | 2022-12-06 | 2.0 (per 1000000 token) | 1 token |
| cohere | command-light-nightly | 2022-12-06 | 0.6 (per 1000000 token) | 1 token |
| cohere | command-r | 2022-12-06 | 1.5 (per 1000000 token) | 1 token |
| cohere | command-r-plus | 2022-12-06 | 15.0 (per 1000000 token) | 1 token |
| cohere | command-r7b-12-2024 | 2022-12-06 | 0.15 (per 1000000 token) | 1 token |
| meta | llama3-1-405b-instruct-v1:0 | boto3 (v1.35.84) | 2.4 (per 1000000 token) | 1 token |
| meta | llama3-1-70b-instruct-v1:0 | boto3 (v1.35.84) | 0.72 (per 1000000 token) | 1 token |
| meta | llama3-1-8b-instruct-v1:0 | boto3 (v1.35.84) | 0.22 (per 1000000 token) | 1 token |
| meta | - | boto3 (v1.35.84) | 0.15 (per 1000000 token) | 1 token |
| mistral | - | v0.0.1 | 6.0 (per 1000000 token) | 1 token |
| mistral | pixtral-large-latest | v0.0.1 | 6.0 (per 1000000 token) | 1 token |
| mistral | mistral-saba-latest | v0.0.1 | 0.6 (per 1000000 token) | 1 token |
| mistral | mistral-small-latest | v0.0.1 | 0.6 (per 1000000 token) | 1 token |
| mistral | mistral-large-latest | v0.0.1 | 6.0 (per 1000000 token) | 1 token |
| mistral | codestral-latest | v0.0.1 | 0.9 (per 1000000 token) | 1 token |
| perplexityai | - | v1.0 | 2.0 (per 1000000 token) | 1 token |
| perplexityai | sonar-pro | v1.0 | 30.0 (per 1000000 token) | 1 token |
| perplexityai | sonar | v1.0 | 2.0 (per 1000000 token) | 1 token |
| anthropic | - | bedrock-2023-05-31 | 15.0 (per 1000000 token) | 1 token |
| anthropic | claude-3-5-sonnet-latest | bedrock-2023-05-31 | 15.0 (per 1000000 token) | 1 token |
| anthropic | claude-3-5-haiku-latest | bedrock-2023-05-31 | 4.0 (per 1000000 token) | 1 token |
| anthropic | claude-3-opus-latest | bedrock-2023-05-31 | 75.0 (per 1000000 token) | 1 token |
| anthropic | claude-3-7-sonnet-20250219 | bedrock-2023-05-31 | 15.0 (per 1000000 token) | 1 token |
| xai | - | v1 | 10.0 (per 1000000 token) | 1 token |
| xai | grok-2-latest | v1 | 10.0 (per 1000000 token) | 1 token |
| xai | grok-2 | v1 | 10.0 (per 1000000 token) | 1 token |
| xai | grok-2-vision-1212 | v1 | 10.0 (per 1000000 token) | 1 token |
| deepseek | DeepSeek-V3 | v1 | 1.25 (per 1000000 token) | 1 token |
| deepseek | DeepSeek-R1 | v1 | 7.0 (per 1000000 token) | 1 token |
| deepseek | deepseek-llm-67b-chat | v1 | 0.9 (per 1000000 token) | 1 token |
| deepseek | - | v1 | 1.25 (per 1000000 token) | 1 token |
| amazon | - | boto3 (v1.29.6) | 0.24 (per 1000000 token) | 1 token |
| amazon | amazon.nova-lite-v1:0 | boto3 (v1.29.6) | 0.24 (per 1000000 token) | 1 token |
| amazon | amazon.nova-pro-v1:0 | boto3 (v1.29.6) | 3.2 (per 1000000 token) | 1 token |
| amazon | amazon.nova-micro-v1:0 | boto3 (v1.29.6) | 0.14 (per 1000000 token) | 1 token |
| together_ai | - | v1 | 1.2 (per 1000000 token) | 1 token |
| together_ai | Qwen/Qwen2.5-72B-Instruct-Turbo | v1 | 1.2 (per 1000000 token) | 1 token |
| together_ai | meta-llama/Llama-3.3-70B-Instruct-Turbo | v1 | 0.88 (per 1000000 token) | 1 token |
| together_ai | microsoft/WizardLM-2-8x22B | v1 | 1.2 (per 1000000 token) | 1 token |
Supported Detailed Languages
| Name | Value |
|---|---|
| Auto detection | auto-detect |
Supported Models
Default Models
| Name | Value |
|---|---|
| openai | gpt-4o |
gemini-1.5-flash | |
| cohere | command |
| meta | llama3-2-3b-instruct-v1:0 |
| mistral | mistral-large-latest |
| perplexityai | sonar |
| anthropic | claude-3-5-sonnet-latest |
| xai | grok-2-latest |
| deepseek | DeepSeek-V3 |
| amazon | amazon.nova-lite-v1:0 |
| together_ai | Qwen/Qwen2.5-72B-Instruct-Turbo |