Chat Pricing

Provider	Model	Billing unit/Input	Price/Input [USD]	Billing unit/Output	Price/Output [USD]
Anthropic	Claude-3-5-Haiku	1M tokens	0.8	1M tokens	4
AWS Bedrock	Command-r-plus	1M tokens	18	1M tokens	18
AWS Bedrock	Llama-3-70b-Chat	1M tokens	6.15	1M tokens	6.15
AWS Bedrock	Llama-3-8b-Chat	1M tokens	0.9	1M tokens	0.9
AWS Bedrock	Mistral-7b-Instruct-v0.2	1M tokens	0.35	1M tokens	0.35
AWS Bedrock	Nova-Micro-v1	1M tokens	0.035	1M tokens	0.14
Deepinfra	Gemma-2-27b-it	1M tokens	0.27	1M tokens	0.27
Deepinfra	Gemma-2-9b-it	1M tokens	0.03	1M tokens	0.06
Deepinfra	Hermes-3-Llama-3.1-405B	1M tokens	0.9	1M tokens	0.9
Deepinfra	L3-70B-Euryale-v2.1	1M tokens	0.35	1M tokens	0.4
Deepinfra	L3-8B-Lunaris-v1	1M tokens	0.03	1M tokens	0.06
Deepinfra	L3.1-70B-Euryale-v2.2	1M tokens	0.35	1M tokens	0.4
Deepinfra	Llama-3-70B-Instruct	1M tokens	0.23	1M tokens	0.4
Deepinfra	Llama-3-8B-Instruct	1M tokens	0.03	1M tokens	0.06
Deepinfra	Llama-3.1-8B-Instruct	1M tokens	0.03	1M tokens	0.05
Deepinfra	Llama-3.1-8B-Instruct-Turbo	1M tokens	0.02	1M tokens	0.05
Deepinfra	Llama-3.1-Nemotron-70B-Instruct	1M tokens	0.23	1M tokens	0.4
Deepinfra	Llama-3.2-11B-Vision-Instruct	1M tokens	0.055	1M tokens	0.055
Deepinfra	Llama-3.2-1B-Instruct	1M tokens	0.01	1M tokens	0.02
Deepinfra	Llama-3.2-3B-Instruct	1M tokens	0.018	1M tokens	0.03
Deepinfra	Llama-3.2-90B-Vision-Instruct	1M tokens	0.35	1M tokens	0.4
Deepinfra	Llama-3.3-70B-Instruct	1M tokens	0.23	1M tokens	0.4
Deepinfra	Llama-3.3-70B-Instruct-Turbo	1M tokens	0.13	1M tokens	0.4
Deepinfra	Lzlv_70b_fp16_hf	1M tokens	0.35	1M tokens	0.4
Deepinfra	Meta-Llama-3.1-405B-Instruct	1M tokens	0.9	1M tokens	0.9
Deepinfra	Meta-Llama-3.1-70B-Instruct	1M tokens	0.23	1M tokens	0.4
Deepinfra	Meta-Llama-3.1-70B-Instruct-Turbo	1M tokens	0.13	1M tokens	0.4
Deepinfra	Mistral-7b-Instruct-v0.3	1M tokens	0.03	1M tokens	0.055
Deepinfra	Mixtral-8x7b-Instruct-v0.1	1M tokens	0.24	1M tokens	0.24
Deepinfra	MythoMax-L2-13b	1M tokens	0.08	1M tokens	0.08
Deepinfra	Nemo-Instruct-2407	1M tokens	0.04	1M tokens	0.1
Deepinfra	Openchat_3.5	1M tokens	0.055	1M tokens	0.055
Deepinfra	QwQ-32B-Preview	1M tokens	0.15	1M tokens	0.6
Deepinfra	Qwen2.5-72B-Instruct	1M tokens	0.23	1M tokens	0.4
Deepinfra	Qwen2.5-Coder-32B-Instruct	1M tokens	0.08	1M tokens	0.18
Deepinfra	WizardLM-2-7B	1M tokens	0.055	1M tokens	0.055
Deepinfra	WizardLM-2-8x22B	1M tokens	0.5	1M tokens	0.5
Deepseek	Deepseek-R1	1M tokens	0.55	1M tokens	2.19
Fireworks AI	Llama-3-70b-Chat	1M tokens	1.8	1M tokens	1.8
Fireworks AI	Llama-3-8b-Chat	1M tokens	0.4	1M tokens	0.4
Fireworks AI	Llama-3.1-405b-Chat	1M tokens	6	1M tokens	6
Fireworks AI	Llama-3.1-8b-Chat	1M tokens	0.4	1M tokens	0.4
Fireworks AI	Mixtral-8x22b-Instruct-v0.1	1M tokens	2.4	1M tokens	2.4
Groq	Llama-3-70b-Chat	1M tokens	1.38	1M tokens	1.38
Groq	Llama-3-8b-Chat	1M tokens	0.13	1M tokens	0.13
Lepton AI	Llama-3-70b-Chat	1M tokens	1.6	1M tokens	1.6
Lepton AI	Llama-3-8b-Chat	1M tokens	0.14	1M tokens	0.14
Lepton AI	Mistral-7b-Instruct-v0.3	1M tokens	8	1M tokens	0.14
Mistral AI	Mistral-7b-Instruct-v0.3	1M tokens	0.5	1M tokens	0.5
Mistral AI	Mistral-small	1M tokens	0.8	1M tokens	0.8
Mistral AI	Mixtral-8x22b-Instruct-v0.1	1M tokens	0.14	1M tokens	0.14
Mistral AI	Mixtral-8x7b-Instruct-v0.1	1M tokens	1.4	1M tokens	1.4
OpenAI	ChatGPT-4o-Latest	1M tokens	5	1M tokens	15
OpenAI	GPT-3.5-Turbo	1M tokens	0.5	1M tokens	1.5
OpenAI	GPT-3.5-Turbo-0125	1M tokens	0.5	1M tokens	1.5
OpenAI	GPT-3.5-Turbo-1106	1M tokens	1	1M tokens	2
OpenAI	GPT-4	1M tokens	30	1M tokens	60
OpenAI	GPT-4-0125-Preview	1M tokens	10	1M tokens	30
OpenAI	GPT-4-1106-Preview	1M tokens	10	1M tokens	30
OpenAI	GPT-4-Turbo-Preview	1M tokens	10	1M tokens	30
OpenAI	o1-Preview	1M tokens	15	1M tokens	60
OpenAI	o1-Preview-2024-09-12	1M tokens	15	1M tokens	60
OpenAI	o1-mini	1M tokens	3	1M tokens	12
OpenAI	o1-mini-2024-09-12	1M tokens	3	1M tokens	12
Perplexity	Sonar-Pro	1M tokens	0.3	1M tokens	1.5
Perplexity	Sonar-Reasoning-Pro	1M tokens	0.2	1M tokens	0.8
Perplexity	Sonar-deep-research	1M tokens	0.2	1M tokens	0.8
Replicate	Llama-3-70b-Chat	1M tokens	3.4	1M tokens	3.4
Replicate	Llama-3-8b-Chat	1M tokens	0.3	1M tokens	0.3
Together	DBRX-Instruct	1M tokens	1.2	1M tokens	1.2
Together	Deepseek-v3	1M tokens	1.25	1M tokens	1.25
Together	Gemma-2-27b-it	1M tokens	0.8	1M tokens	0.8
Together	Gemma-2-9b-it	1M tokens	0.3	1M tokens	0.3
Together	Gemma-2b-it	1M tokens	0.1	1M tokens	0.1
Together	Llama-3-70B-Instruct-Lite	1M tokens	0.54	1M tokens	0.54
Together	Llama-3-70B-Instruct-Turbo	1M tokens	0.88	1M tokens	0.88
Together	Llama-3-70b-Chat	1M tokens	0.88	1M tokens	0.88
Together	Llama-3-8B-Instruct-Lite	1M tokens	0.1	1M tokens	0.1
Together	Llama-3-8B-Instruct-Turbo	1M tokens	0.18	1M tokens	0.18
Together	Llama-3-8b-Chat	1M tokens	0.2	1M tokens	0.2
Together	Llama-3.1-405B-Instruct-Turbo	1M tokens	3.5	1M tokens	3.5
Together	Llama-3.1-70B-Instruct-Turbo	1M tokens	0.88	1M tokens	0.88
Together	Llama-3.1-Nemotron-70B-Instruct-HF	1M tokens	0.88	1M tokens	0.88
Together	Llama-3.2-3B-Instruct-Turbo	1M tokens	0.06	1M tokens	0.06
Together	Llama-3.3-70B-Instruct-Turbo	1M tokens	0.88	1M tokens	0.88
Together	Meta-Llama-3.1-8B-Instruct-Turbo	1M tokens	0.18	1M tokens	0.18
Together	Mistral-7B-Instruct-v0.1	1M tokens	0.2	1M tokens	0.2
Together	Mistral-7b-Instruct-v0.2	1M tokens	0.2	1M tokens	0.2
Together	Mistral-7b-Instruct-v0.3	1M tokens	0.2	1M tokens	0.2
Together	Mixtral-8x22b-Instruct-v0.1	1M tokens	1.2	1M tokens	1.2
Together	Mixtral-8x7b-Instruct-v0.1	1M tokens	0.6	1M tokens	0.6
Together	MythoMax-L2-13b	1M tokens	0.3	1M tokens	0.3
Together	Nous-Hermes-2-Mixtral-8x7B-DPO	1M tokens	0.6	1M tokens	0.6
Together	QwQ-32B-Preview	1M tokens	1.2	1M tokens	1.2
Together	Qwen2-72B-Instruct	1M tokens	0.9	1M tokens	0.9
Together	Qwen2.5-72B-Instruct-Turbo	1M tokens	1.2	1M tokens	1.2
Together	Qwen2.5-7B-Instruct-Turbo	1M tokens	0.3	1M tokens	0.3
Together	Qwen2.5-Coder-32B-Instruct	1M tokens	0.8	1M tokens	0.8
Together	SOLAR-10.7B-Instruct-v1.0	1M tokens	0.3	1M tokens	0.3
Together	WizardLM-2-8x22B	1M tokens	1.2	1M tokens	1.2
X	Grok-2	1M tokens	2	1M tokens	10
X	Grok-Beta	1M tokens	5	1M tokens	15