Usage-based pricing built for scale
Get started for free and pay only for what you consume. If you’re looking for a model that is not listed below, please reach out.
TTS
Inworld TTS-1.5 Mini
$5/1Mcharacters ~ $0.005/minute
Inworld TTS-1.5 Max
$10/1M characters ~$0.01/minute
LLM
Pay the exact same rates as the model providers. No hidden markups.
Claude 3 Haiku
Anthropic
Input Cost ($/1M tokens)
$0.25
Output Cost ($/1M tokens)
$1.25
Claude 3.5 Haiku
Anthropic
Input Cost ($/1M tokens)
$0.8
Output Cost ($/1M tokens)
$4
Claude 3.7 Sonnet
Anthropic
Input Cost ($/1M tokens)
$3
Output Cost ($/1M tokens)
$15
Claude Haiku 4.5
Anthropic
Input Cost ($/1M tokens)
$1
Output Cost ($/1M tokens)
$5
Claude Opus 4
Anthropic
Input Cost ($/1M tokens)
$15
Output Cost ($/1M tokens)
$75
Claude Opus 4.1
Anthropic
Input Cost ($/1M tokens)
$15
Output Cost ($/1M tokens)
$75
Claude Opus 4.5
Anthropic
Input Cost ($/1M tokens)
$5
Output Cost ($/1M tokens)
$25
Claude Sonnet 4.5
Anthropic
Input Cost ($/1M tokens)
$3
Output Cost ($/1M tokens)
$15
GPT OSS 120B
Cerebras
Input Cost ($/1M tokens)
$0.35
Output Cost ($/1M tokens)
$0.75
Llama 3.1 8b
Cerebras
Input Cost ($/1M tokens)
$0.1
Output Cost ($/1M tokens)
$0.1
LLama-3.3-70b
Cerebras
Input Cost ($/1M tokens)
$0.85
Output Cost ($/1M tokens)
$1.2
DeepSeek R1 0528
Deepinfra
Input Cost ($/1M tokens)
$0.5
Output Cost ($/1M tokens)
$2.15
DeepSeek R1 Distill Llama 70B
Deepinfra
Input Cost ($/1M tokens)
$0.6
Output Cost ($/1M tokens)
$1.2
DeepSeek V3.1 Terminus
Deepinfra
Input Cost ($/1M tokens)
$0.21
Output Cost ($/1M tokens)
$0.79
DeepSeek V3.2
Deepinfra
Input Cost ($/1M tokens)
$0.26
Output Cost ($/1M tokens)
$0.39
GLM 4.6
Deepinfra
Input Cost ($/1M tokens)
$0.43
Output Cost ($/1M tokens)
$1.75
GLM 4.7
Deepinfra
Input Cost ($/1M tokens)
$0.43
Output Cost ($/1M tokens)
$1.75
Google Gemma 3 12b it
Deepinfra
Input Cost ($/1M tokens)
$0.04
Output Cost ($/1M tokens)
$0.13
Google Gemma 3 27b it
Deepinfra
Input Cost ($/1M tokens)
$0.09
Output Cost ($/1M tokens)
$0.16
Google Gemma 3 4b-it
Deepinfra
Input Cost ($/1M tokens)
$0.04
Output Cost ($/1M tokens)
$0.08
GPT OSS 120B
Deepinfra
Input Cost ($/1M tokens)
$0.039
Output Cost ($/1M tokens)
$0.19
GPT OSS 20B
Deepinfra
Input Cost ($/1M tokens)
$0.03
Output Cost ($/1M tokens)
$0.14
Hermes 3 Llama-3.1 405B
Deepinfra
Input Cost ($/1M tokens)
$1
Output Cost ($/1M tokens)
$1
Kimi K2 Instruct 0905
Deepinfra
Input Cost ($/1M tokens)
$0.4
Output Cost ($/1M tokens)
$2
Kimi K2 Thinking
Deepinfra
Input Cost ($/1M tokens)
$0.47
Output Cost ($/1M tokens)
$2
Llama 3.1 Nemotron 70B Instruct
Deepinfra
Input Cost ($/1M tokens)
$1.2
Output Cost ($/1M tokens)
$1.2
Llama 3.2 11B Vision Instruct
Deepinfra
Input Cost ($/1M tokens)
$0.049
Output Cost ($/1M tokens)
$0.049
Llama 3.2 3B Instruct
Deepinfra
Input Cost ($/1M tokens)
$0.02
Output Cost ($/1M tokens)
$0.02
Llama 3.3 Nemotron Super 49B v1.5
Deepinfra
Input Cost ($/1M tokens)
$0.1
Output Cost ($/1M tokens)
$0.4
Llama 4 Scout 17B 16E Instruct
Deepinfra
Input Cost ($/1M tokens)
$0.08
Output Cost ($/1M tokens)
$0.3
Llama-Guard-4-12B
Deepinfra
Input Cost ($/1M tokens)
$0.18
Output Cost ($/1M tokens)
$0.18
Microsoft Phi 4
Deepinfra
Input Cost ($/1M tokens)
$0.07
Output Cost ($/1M tokens)
$0.14
Microsoft WizardLM 2 8x22B
Deepinfra
Input Cost ($/1M tokens)
$0.48
Output Cost ($/1M tokens)
$0.48
MiniMax M2
Deepinfra
Input Cost ($/1M tokens)
$0.254
Output Cost ($/1M tokens)
$1.02
MiniMax M2.1
Deepinfra
Input Cost ($/1M tokens)
$0.28
Output Cost ($/1M tokens)
$1.2
Mistral Nemo Instruct 2407
Deepinfra
Input Cost ($/1M tokens)
$0.02
Output Cost ($/1M tokens)
$0.04
Mistral Small 24B Instruct 2501
Deepinfra
Input Cost ($/1M tokens)
$0.05
Output Cost ($/1M tokens)
$0.08
Mistral Small 3.2 24B Instruct 2506
Deepinfra
Input Cost ($/1M tokens)
$0.075
Output Cost ($/1M tokens)
$0.2
Nemotron 3 Nano 30B A3B
Deepinfra
Input Cost ($/1M tokens)
$0.06
Output Cost ($/1M tokens)
$0.24
Qwen 2.5 72B Instruct
Deepinfra
Input Cost ($/1M tokens)
$0.12
Output Cost ($/1M tokens)
$0.39
Qwen2.5 VL 32B Instruct
Deepinfra
Input Cost ($/1M tokens)
$0.2
Output Cost ($/1M tokens)
$0.6
Qwen3 235B A22B Thinking 2507
Deepinfra
Input Cost ($/1M tokens)
$0.23
Output Cost ($/1M tokens)
$2.39
Qwen3 30B A3B
Deepinfra
Input Cost ($/1M tokens)
$0.08
Output Cost ($/1M tokens)
$0.29
Qwen3 Next 80B A3B Instruct
Deepinfra
Input Cost ($/1M tokens)
$0.09
Output Cost ($/1M tokens)
$1.1
Qwen3 VL 235B A22B Instruct
Deepinfra
Input Cost ($/1M tokens)
$0.2
Output Cost ($/1M tokens)
$1.2
Qwen3 VL 30B A3B Instruct
Deepinfra
Input Cost ($/1M tokens)
$0.15
Output Cost ($/1M tokens)
$0.6
DeepSeek V3.1
Fireworks
Input Cost ($/1M tokens)
$0.56
Output Cost ($/1M tokens)
$1.68
GPT OSS 20B
Fireworks
Input Cost ($/1M tokens)
$0.07
Output Cost ($/1M tokens)
$0.3
Kimi K2 Instruct
Fireworks
Input Cost ($/1M tokens)
$0.6
Output Cost ($/1M tokens)
$2.5
Kimi K2 Thinking
Fireworks
Input Cost ($/1M tokens)
$0.6
Output Cost ($/1M tokens)
$2.5
Meta Llama 3.1 405B
Fireworks
Input Cost ($/1M tokens)
$3
Output Cost ($/1M tokens)
$3
Meta Llama 3.1 8B Instruct
Fireworks
Input Cost ($/1M tokens)
$0.2
Output Cost ($/1M tokens)
$0.2
Meta Llama 3.2 3B Instruct
Fireworks
Input Cost ($/1M tokens)
$0.1
Output Cost ($/1M tokens)
$0.1
Meta Llama 3.3 70B Instruct
Fireworks
Input Cost ($/1M tokens)
$0.9
Output Cost ($/1M tokens)
$0.9
Meta Llama 4 Maverick (Basic)
Fireworks
Input Cost ($/1M tokens)
$0.22
Output Cost ($/1M tokens)
$0.88
MiniMax M2
Fireworks
Input Cost ($/1M tokens)
$0.3
Output Cost ($/1M tokens)
$1.2
Mixtral 8x22b instruct
Fireworks
Input Cost ($/1M tokens)
$1.2
Output Cost ($/1M tokens)
$1.2
OpenAI gpt OSS 120b
Fireworks
Input Cost ($/1M tokens)
$0.15
Output Cost ($/1M tokens)
$0.6
Qwen3 235b a22b Thinking
Fireworks
Input Cost ($/1M tokens)
$0.11
Output Cost ($/1M tokens)
$0.6
Qwen3 Coder 30b a3b Instruct
Fireworks
Input Cost ($/1M tokens)
$0.15
Output Cost ($/1M tokens)
$0.6
Qwen3 Coder 480B
Fireworks
Input Cost ($/1M tokens)
$0.45
Output Cost ($/1M tokens)
$1.8
Qwen3 vl 235b a22b Instruct
Fireworks
Input Cost ($/1M tokens)
$0.12
Output Cost ($/1M tokens)
$0.56
Qwen3 vl 235b a22b Thinking
Fireworks
Input Cost ($/1M tokens)
$0.22
Output Cost ($/1M tokens)
$0.88
Qwen3 vl 30b a3b instruct
Fireworks
Input Cost ($/1M tokens)
$0.15
Output Cost ($/1M tokens)
$0.6
Qwen3 vl 30b a3b Thinking
Fireworks
Input Cost ($/1M tokens)
$0.15
Output Cost ($/1M tokens)
$0.6
Gemini 2.0 Flash
Google
Input Cost ($/1M tokens)
$0.1
Output Cost ($/1M tokens)
$0.4
Gemini 2.0 Flash-Lite
Google
Input Cost ($/1M tokens)
$0.075
Output Cost ($/1M tokens)
$0.3
Gemini 2.5 Flash
Google
Input Cost ($/1M tokens)
$0.3
Output Cost ($/1M tokens)
$2.5
Gemini 2.5 Flash Lite
Google
Input Cost ($/1M tokens)
$0.075
Output Cost ($/1M tokens)
$0.3
Gemini 2.5 Pro
Google
Input Cost ($/1M tokens)
$1.25
Output Cost ($/1M tokens)
$10
Gemini 3 flash
Google
Input Cost ($/1M tokens)
$0.5
Output Cost ($/1M tokens)
$3
Gemini 3 Pro
Google
Input Cost ($/1M tokens)
$2
Output Cost ($/1M tokens)
$12
DeepSeek R1 Distill Llama 70B 128k
Groq
Input Cost ($/1M tokens)
$0.75
Output Cost ($/1M tokens)
$0.99
Gemma 2 9B 8k
Groq
Input Cost ($/1M tokens)
$0.2
Output Cost ($/1M tokens)
$0.2
GPT OSS 120B 128k
Groq
Input Cost ($/1M tokens)
$0.15
Output Cost ($/1M tokens)
$0.6
GPT OSS 20B
Groq
Input Cost ($/1M tokens)
$0.075
Output Cost ($/1M tokens)
$0.3
GPT OSS 20B Safeguard
Groq
Input Cost ($/1M tokens)
$0.075
Output Cost ($/1M tokens)
$0.3
Kimi K2 1T 256k
Groq
Input Cost ($/1M tokens)
$1
Output Cost ($/1M tokens)
$3
Llama 3 70B 8k
Groq
Input Cost ($/1M tokens)
$0.59
Output Cost ($/1M tokens)
$0.79
Llama 3 8B 8k
Groq
Input Cost ($/1M tokens)
$0.05
Output Cost ($/1M tokens)
$0.08
Llama 3.1 8B Instant 128k
Groq
Input Cost ($/1M tokens)
$0.05
Output Cost ($/1M tokens)
$0.08
Llama 3.3 70B Versatile 128k
Groq
Input Cost ($/1M tokens)
$0.59
Output Cost ($/1M tokens)
$0.79
Llama 4 Maverick (17Bx128E) 128k
Groq
Input Cost ($/1M tokens)
$0.2
Output Cost ($/1M tokens)
$0.6
Llama 4 Scout (17Bx16E) 128k
Groq
Input Cost ($/1M tokens)
$0.11
Output Cost ($/1M tokens)
$0.34
Llama Guard 3 8B 8k
Groq
Input Cost ($/1M tokens)
$0.2
Output Cost ($/1M tokens)
$0.2
Llama Guard 4 12B 128k
Groq
Input Cost ($/1M tokens)
$0.2
Output Cost ($/1M tokens)
$0.2
Mistral Saba 24B 32k
Groq
Input Cost ($/1M tokens)
$0.79
Output Cost ($/1M tokens)
$0.79
Qwen3 32B 131k
Groq
Input Cost ($/1M tokens)
$0.29
Output Cost ($/1M tokens)
$0.59
Inworld Knowledge
Inworld
Included
Included
Inworld Memory
Inworld
Included
Included
Inworld Safety
Inworld
Included
Included
gemma3 12B
Inworld (on-prem)
Contact for pricing
Contact for pricing
gemma3 27B
Inworld (on-prem)
Contact for pricing
Contact for pricing
gpt-oss 20B
Inworld (on-prem)
Contact for pricing
Contact for pricing
llama3.1 8B
Inworld (on-prem)
Contact for pricing
Contact for pricing
Voice Activity Detection (VAD)
Inworld (on-prem)
Included
Included
Codestral
Mistral
Input Cost ($/1M tokens)
$0.3
Output Cost ($/1M tokens)
$0.9
Devstral
Mistral
Input Cost ($/1M tokens)
$0.01
Output Cost ($/1M tokens)
$0.01
Devstral Medium
Mistral
Input Cost ($/1M tokens)
$0.01
Output Cost ($/1M tokens)
$0.01
Devstral Small
Mistral
Input Cost ($/1M tokens)
$0.01
Output Cost ($/1M tokens)
$0.01
Ministral 14b
Mistral
Input Cost ($/1M tokens)
$0.2
Output Cost ($/1M tokens)
$0.2
Ministral 3b
Mistral
Input Cost ($/1M tokens)
$0.1
Output Cost ($/1M tokens)
$0.1
Ministral 8b
Mistral
Input Cost ($/1M tokens)
$0.15
Output Cost ($/1M tokens)
$0.15
Ministral 8B 24.10
Mistral
Input Cost ($/1M tokens)
$0.1
Output Cost ($/1M tokens)
$0.1
Ministral Large 2411
Mistral
Input Cost ($/1M tokens)
$2
Output Cost ($/1M tokens)
$6
Ministral Large 2512
Mistral
Input Cost ($/1M tokens)
$0.5
Output Cost ($/1M tokens)
$1.5
Ministral Tiny
Mistral
Input Cost ($/1M tokens)
$0.15
Output Cost ($/1M tokens)
$0.15
Mistral Small 3.2
Mistral
Input Cost ($/1M tokens)
$0.1
Output Cost ($/1M tokens)
$0.3
Pixtral 12b
Mistral
Input Cost ($/1M tokens)
$0.1
Output Cost ($/1M tokens)
$0.1
Pixtral Large
Mistral
Input Cost ($/1M tokens)
$2
Output Cost ($/1M tokens)
$6
Chatgpt 4o Latest
OpenAI
Input Cost ($/1M tokens)
$5
Output Cost ($/1M tokens)
$15
GPT 3.5 Turbo
OpenAI
Input Cost ($/1M tokens)
$0.5
Output Cost ($/1M tokens)
$1.5
GPT 3.5 Turbo 16k
OpenAI
Input Cost ($/1M tokens)
$3
Output Cost ($/1M tokens)
$4
GPT 4
OpenAI
Input Cost ($/1M tokens)
$30
Output Cost ($/1M tokens)
$60
GPT 4 Turbo
OpenAI
Input Cost ($/1M tokens)
$10
Output Cost ($/1M tokens)
$30
GPT 4.1
OpenAI
Input Cost ($/1M tokens)
$2
Output Cost ($/1M tokens)
$8
GPT 4.1 Mini
OpenAI
Input Cost ($/1M tokens)
$0.4
Output Cost ($/1M tokens)
$1.6
GPT 4.1 Nano
OpenAI
Input Cost ($/1M tokens)
$0.1
Output Cost ($/1M tokens)
$0.4
GPT 4o
OpenAI
Input Cost ($/1M tokens)
$2.5
Output Cost ($/1M tokens)
$10
GPT 4o mini
OpenAI
Input Cost ($/1M tokens)
$0.15
Output Cost ($/1M tokens)
$0.6
GPT 4o Search Preview
OpenAI
Input Cost ($/1M tokens)
$2.5
Output Cost ($/1M tokens)
$10
GPT 5
OpenAI
Input Cost ($/1M tokens)
$1.25
Output Cost ($/1M tokens)
$10
GPT 5 Chat Latest
OpenAI
Input Cost ($/1M tokens)
$1.25
Output Cost ($/1M tokens)
$10
GPT 5 Mini
OpenAI
Input Cost ($/1M tokens)
$0.25
Output Cost ($/1M tokens)
$2
GPT 5 Nano
OpenAI
Input Cost ($/1M tokens)
$0.05
Output Cost ($/1M tokens)
$0.4
GPT 5.1
OpenAI
Input Cost ($/1M tokens)
$1.25
Output Cost ($/1M tokens)
$10
GPT 5.2
OpenAI
Input Cost ($/1M tokens)
$1.75
Output Cost ($/1M tokens)
$14
o1
OpenAI
Input Cost ($/1M tokens)
$15
Output Cost ($/1M tokens)
$60
o1-mini
OpenAI
Input Cost ($/1M tokens)
$1.1
Output Cost ($/1M tokens)
$4.4
o1-pro
OpenAI
Input Cost ($/1M tokens)
$150
Output Cost ($/1M tokens)
$600
o3
OpenAI
Input Cost ($/1M tokens)
$2
Output Cost ($/1M tokens)
$8
o3-mini
OpenAI
Input Cost ($/1M tokens)
$1.1
Output Cost ($/1M tokens)
$4.4
o3-pro
OpenAI
Input Cost ($/1M tokens)
$20
Output Cost ($/1M tokens)
$80
o4-mini
OpenAI
Input Cost ($/1M tokens)
$1.1
Output Cost ($/1M tokens)
$4.4
Llama-3.3-70B-Instruct
Tenstorrent
Input Cost ($/1M tokens)
$0.4
Output Cost ($/1M tokens)
$0.4
Other models
Model
Provider
Type
Cost
sentence-transformers/paraphrase-multilingual-mpnet-base-v2
Inworld
Type
Embedding
Cost
0.0007
Whisper-large-v3
OpenAI
Type
STT
Cost
0.0025
BAAI/bge-large-en-v1.5
Inworld
Type
Embedding
Cost
0.0023
Prices reflect the best publicly available pricing from third party model providers and are subject to change.