Model pricing pages
AI Model Pricing Pages
Pricing pages for every tracked text, voice, image, video, and specialized model. Text-model pages combine prices, workload math, price history, and alternatives from the same dataset behind the main AI API pricing table.
Looking for launches? See the new AI model release tracker.
Indexed model pages
291
Current models
171
Last price refresh
Alibaba Qwen
4 current · 0 legacy / other available
Qwen3.6-Flash
$0.25 input / $1.50 output per 1M tokens
Cached input: $0.025/1M
Qwen3.7-Max
$2.50 input / $7.50 output per 1M tokens
Cached input: $0.25/1M
Qwen3.7-Plus
$0.32 input / $1.28 output per 1M tokens
Cached input: $0.032/1M
Qwen3.8-Flash
previewCurrent International pricing conflicts with the retained QwenCloud announcement input rate. Exact endpoint, region and availability reconciliation plus price-change consensus remain unresolved; retained numbers are historical, not a current quote.
Anthropic
6 current · 16 legacy / other available
Claude Fable 5.2
$8.00 input / $40.00 output per 1M tokens
Cached input: $0.20/1M
Claude Haiku 5.5
$0.10 input / $0.50 output per 1M tokens
Cached input: $0.01/1M
Claude Mythos 5.2
preview$8.00 input / $40.00 output per 1M tokens
Cached input: $0.20/1M
Claude Opus 5.5
$4.00 input / $20.00 output per 1M tokens
Cached input: $0.20/1M
Claude Sonnet 5
$2.00 input / $10.00 output per 1M tokens
Cached input: $0.20/1M
Claude Sonnet 5.5
$2.00 input / $10.00 output per 1M tokens
Cached input: $0.10/1M
Show legacy / other available (16)
Retained for migration and historical comparison. Previous generation does not mean officially shut down; check each model's lifecycle label and source.
Claude Fable 5
legacy$10.00 input / $50.00 output per 1M tokens
Cached input: $1.00/1M
Claude Fable 5.1
legacy$10.00 input / $50.00 output per 1M tokens
Cached input: $0.25/1M
Claude Haiku 3.5
legacy$0.80 input / $4.00 output per 1M tokens
Cached input: $0.08/1M
Claude Haiku 4.5
legacy$1.00 input / $5.00 output per 1M tokens
Cached input: $0.10/1M
Claude Mythos 5
legacy$10.00 input / $50.00 output per 1M tokens
Cached input: $1.00/1M
Claude Mythos 5.1
legacy$10.00 input / $50.00 output per 1M tokens
Cached input: $0.25/1M
Claude Opus 4
legacy$15.00 input / $75.00 output per 1M tokens
Cached input: $1.50/1M
Claude Opus 4.1
legacy$15.00 input / $75.00 output per 1M tokens
Cached input: $1.50/1M
Claude Opus 4.5
legacy$5.00 input / $25.00 output per 1M tokens
Cached input: $0.50/1M
Claude Opus 4.6
legacy$5.00 input / $25.00 output per 1M tokens
Cached input: $0.50/1M
Claude Opus 4.7
legacy$5.00 input / $25.00 output per 1M tokens
Cached input: $0.50/1M
Claude Opus 4.8
legacy$5.00 input / $25.00 output per 1M tokens
Cached input: $0.50/1M
Claude Opus 5
legacy$5.00 input / $25.00 output per 1M tokens
Cached input: $0.50/1M
Claude Sonnet 4
legacy$3.00 input / $15.00 output per 1M tokens
Cached input: $0.30/1M
Claude Sonnet 4.5
legacy$3.00 input / $15.00 output per 1M tokens
Cached input: $0.30/1M
Claude Sonnet 4.6
legacy$3.00 input / $15.00 output per 1M tokens
Cached input: $0.30/1M
castform
1 current · 0 legacy / other available
cerebras
1 current · 0 legacy / other available
Cohere
8 current · 3 legacy / other available
Command A
The current official Cohere catalog lists this model, but its exact current numerical API rates are not disclosed in the acquired pricing/billing pages. Retained numbers are historical observations, not current quotes.
Command R7B
Current reviewed Command R7B API card and billing contract have not both reconciled. Retained rates are historical observations, not a current quote.
Embed 5 Fast
$0.08 input / $0.00 output per 1M tokens
Embed 5 Pro
$0.12 input / $0.00 output per 1M tokens
Embed v3 English
The current official Cohere catalog lists this model, but its exact current numerical API rates are not disclosed in the acquired pricing/billing pages. Retained numbers are historical observations, not current quotes.
Embed v3 Multilingual
The current official Cohere catalog lists this model, but its exact current numerical API rates are not disclosed in the acquired pricing/billing pages. Retained numbers are historical observations, not current quotes.
Rerank 5 Fast
$0.02 input / $0.00 output per 1M tokens
Rerank 5 Pro
$0.05 input / $0.00 output per 1M tokens
Show legacy / other available (3)
Retained for migration and historical comparison. Previous generation does not mean officially shut down; check each model's lifecycle label and source.
DeepSeek
2 current · 0 legacy / other available
Google Gemini
14 current · 19 legacy / other available
Gemini 2.5 Flash Preview TTS
$0.50 input / $10.00 output per 1M tokens
Gemini 2.5 Pro Preview TTS
$1.00 input / $20.00 output per 1M tokens
Gemini 3 Flash
preview$0.50 input / $3.00 output per 1M tokens
Cached input: $0.05/1M
Gemini 3 Flash Preview
$0.50 input / $3.00 output per 1M tokens
Cached input: $0.05/1M
Gemini 3 Pro Image (Nano Banana Pro) 🍌
$2.00 input / $12.00 output per 1M tokens
Gemini 3.1 Flash TTS Preview
$1.00 input / $20.00 output per 1M tokens
Gemini 3.1 Pro
preview$2.00 input / $12.00 output per 1M tokens
Cached input: $0.20/1M
Gemini 3.8 Flash
$0.75 input / $3.75 output per 1M tokens
Cached input: $0.075/1M
Gemini 3.8 Flash TTS
$0.50 input / $9.00 output per 1M tokens
Gemini 3.8 Flash-Lite TTS
$0.50 input / $6.00 output per 1M tokens
Gemini 4 Argon
$2.00 input / $10.00 output per 1M tokens
Cached input: $0.10/1M
Gemini 4 Carbon
$2.00 input / $10.00 output per 1M tokens
Cached input: $0.10/1M
Gemini Robotics ER 2 Preview
$1.00 input / $5.00 output per 1M tokens
Cached input: $0.10/1M
Gemini Robotics ER 2 Streaming Preview
$1.00 input / $5.00 output per 1M tokens
Show legacy / other available (19)
Retained for migration and historical comparison. Previous generation does not mean officially shut down; check each model's lifecycle label and source.
Gemini 2.0 Flash
deprecated$0.10 input / $0.40 output per 1M tokens
Cached input: $0.025/1M
Gemini 2.0 Flash-Lite
deprecated$0.075 input / $0.30 output per 1M tokens
Gemini 2.5 Flash
legacy$0.30 input / $2.50 output per 1M tokens
Cached input: $0.03/1M
Gemini 2.5 Flash-Lite
legacy$0.10 input / $0.40 output per 1M tokens
Cached input: $0.01/1M
Gemini 2.5 Pro
legacy$1.25 input / $10.00 output per 1M tokens
Cached input: $0.125/1M
Gemini 2.5 Pro (>200k tokens)
legacy$2.50 input / $15.00 output per 1M tokens
Cached input: $0.25/1M
Gemini 3 Pro
deprecated$2.00 input / $12.00 output per 1M tokens
Cached input: $0.20/1M
Gemini 3.1 Flash Image (Nano Banana 2) 🍌
legacy$0.50 input / $3.00 output per 1M tokens
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 🍌
legacy$0.25 input / $1.50 output per 1M tokens
Gemini 3.1 Flash-Lite
legacy$0.25 input / $1.50 output per 1M tokens
Cached input: $0.025/1M
Gemini 3.1 Pro Preview
legacy$2.00 input / $12.00 output per 1M tokens
Cached input: $0.20/1M
Gemini 3.1 Pro Preview
legacy$2.00 input / $12.00 output per 1M tokens
Cached input: $0.20/1M
Gemini 3.5 Flash
legacy$1.50 input / $9.00 output per 1M tokens
Cached input: $0.15/1M
Gemini 3.5 Flash-Lite
legacy$0.30 input / $2.50 output per 1M tokens
Cached input: $0.03/1M
Gemini 3.6 Flash
legacy$0.75 input / $3.75 output per 1M tokens
Cached input: $0.075/1M
Gemini 3.7 Flash
legacy$0.75 input / $3.75 output per 1M tokens
Cached input: $0.075/1M
Gemini Nano Banana 2.1 🍌
legacy$1.50 input / $7.50 output per 1M tokens
Gemini Omni 1.2 Flash
legacy$1.50 input / $9.00 output per 1M tokens
Gemini Omni Flash
legacy$1.50 input / $9.00 output per 1M tokens
Groq
5 current · 2 legacy / other available
GPT-OSS 120B
$0.15 input / $0.60 output per 1M tokens
Cached input: $0.075/1M
GPT-OSS 20B
$0.075 input / $0.30 output per 1M tokens
Cached input: $0.0375/1M
GPT-OSS Safeguard 20B
preview$0.075 input / $0.30 output per 1M tokens
Llama 3.1 8B Instant
Contact Sales: enterprise access, token prices and rate limits require a quote. Numerical rates retained only as historical observations.
Llama 3.3 70B Versatile
Contact Sales: enterprise access, token prices and rate limits require a quote. Numerical rates retained only as historical observations.
Show legacy / other available (2)
Retained for migration and historical comparison. Previous generation does not mean officially shut down; check each model's lifecycle label and source.
laminar
1 current · 0 legacy / other available
minimax
1 current · 0 legacy / other available
Mistral AI
5 current · 13 legacy / other available
Codestral
$0.30 input / $0.90 output per 1M tokens
Cached input: $0.03/1M
Ministral 3 14B
$0.20 input / $0.20 output per 1M tokens
Cached input: $0.02/1M
Ministral 3 3B
$0.10 input / $0.10 output per 1M tokens
Cached input: $0.01/1M
Ministral 3 8B
$0.15 input / $0.15 output per 1M tokens
Cached input: $0.015/1M
Mistral Small 4
$0.15 input / $0.60 output per 1M tokens
Cached input: $0.015/1M
Show legacy / other available (13)
Retained for migration and historical comparison. Previous generation does not mean officially shut down; check each model's lifecycle label and source.
Devstral Medium 2
legacy$0.40 input / $2.00 output per 1M tokens
Devstral Small 2
legacy$0.10 input / $0.30 output per 1M tokens
Magistral Medium
legacy$2.00 input / $5.00 output per 1M tokens
Magistral Small
legacy$0.50 input / $1.50 output per 1M tokens
Mistral 7B
legacy$0.25 input / $0.25 output per 1M tokens
Mistral Large 3
deprecated$0.50 input / $1.50 output per 1M tokens
Cached input: $0.05/1M
Mistral Medium 3
legacy$0.40 input / $2.00 output per 1M tokens
Mistral Medium 3.5
deprecated$1.50 input / $7.50 output per 1M tokens
Cached input: $0.15/1M
Mistral NeMo
legacy$0.15 input / $0.15 output per 1M tokens
Mixtral 8x22B
legacy$2.00 input / $6.00 output per 1M tokens
Mixtral 8x7B
legacy$0.70 input / $0.70 output per 1M tokens
Pixtral 12B
legacy$0.15 input / $0.15 output per 1M tokens
Pixtral Large
legacy$2.00 input / $6.00 output per 1M tokens
moonshot
1 current · 0 legacy / other available
Novita AI
72 current · 6 legacy / other available
AutoGLM-Phone-9B-Multilingual
$0.035 input / $0.138 output per 1M tokens
DeepSeek R1 (Turbo)
$0.70 input / $2.50 output per 1M tokens
DeepSeek R1 0528
$0.70 input / $2.50 output per 1M tokens
Cached input: $0.35/1M
DeepSeek R1 Distill Llama 70B
This exact endpoint is absent from Novita’s current public model listing. Current price and access remain unresolved; absence is not proof of retirement, and dated or successor routes are not substitutes. Retained rates are historical.
DeepSeek V3 (Turbo)
$0.40 input / $1.30 output per 1M tokens
DeepSeek V3 0324
$0.27 input / $1.12 output per 1M tokens
Cached input: $0.135/1M
DeepSeek V3.1
$0.27 input / $1.00 output per 1M tokens
Cached input: $0.135/1M
DeepSeek V3.1 Terminus
$0.27 input / $1.00 output per 1M tokens
Cached input: $0.135/1M
DeepSeek V3.2
$0.269 input / $0.40 output per 1M tokens
Cached input: $0.1345/1M
DeepSeek V3.2 Exp
$0.27 input / $0.41 output per 1M tokens
DeepSeek V4 Flash
This exact endpoint is absent from Novita’s current public model listing. Current price and access remain unresolved; absence is not proof of retirement, and dated or successor routes are not substitutes. Retained rates are historical.
DeepSeek V4 Flash 0731
$0.44 input / $1.32 output per 1M tokens
Cached input: $0.028/1M
DeepSeek V4 Flash Vision Exp
$0.44 input / $1.32 output per 1M tokens
Cached input: $0.028/1M
DeepSeek V4 Pro
$1.60 input / $3.20 output per 1M tokens
Cached input: $0.135/1M
DeepSeek V4 Pro 0813
$1.32 input / $3.96 output per 1M tokens
Cached input: $0.044/1M
DeepSeek V4.1 Flash
$0.30 input / $1.20 output per 1M tokens
Cached input: $0.006/1M
DeepSeek V4.1 Flash
$0.30 input / $1.20 output per 1M tokens
Cached input: $0.006/1M
DeepSeek V4.1 Flash 1017
$0.30 input / $1.20 output per 1M tokens
Cached input: $0.006/1M
DeepSeek-OCR 2
$0.03 input / $0.03 output per 1M tokens
GLM 5.3
$1.40 input / $4.40 output per 1M tokens
Cached input: $0.26/1M
GLM 5.3 Flash
$0.15 input / $0.50 output per 1M tokens
Cached input: $0.03/1M
GLM 5.3 FlashX
$0.37 input / $1.25 output per 1M tokens
Cached input: $0.075/1M
GLM-5
$1.00 input / $3.20 output per 1M tokens
Cached input: $0.20/1M
GLM-5.1
$1.38 input / $4.40 output per 1M tokens
Cached input: $0.26/1M
GLM-5.2
$1.40 input / $4.40 output per 1M tokens
Cached input: $0.26/1M
Kimi K2 0905
$0.60 input / $2.50 output per 1M tokens
Kimi K2 Instruct
$0.57 input / $2.30 output per 1M tokens
Kimi K2 Thinking
$0.60 input / $2.50 output per 1M tokens
Cached input: $0.15/1M
Kimi K2.5
$0.60 input / $3.00 output per 1M tokens
Cached input: $0.10/1M
Kimi K2.6
$0.80 input / $3.40 output per 1M tokens
Cached input: $0.16/1M
Kimi K2.7 Code
$0.95 input / $4.00 output per 1M tokens
Cached input: $0.19/1M
Kimi K3
$3.00 input / $15.00 output per 1M tokens
Cached input: $0.30/1M
Kimi K3.1 Pro
$2.00 input / $10.00 output per 1M tokens
Cached input: $0.20/1M
Kimi K3.1 Pro Highspeed
$4.00 input / $20.00 output per 1M tokens
Cached input: $0.20/1M
Llama 3 8B Lunaris
Exact model is not listed in Novita’s current public model API. Current price and access remain unresolved; absence does not establish retirement. Retained numerical rates are historical observations.
Llama 3 8B Stheno V3.2
$0.05 input / $0.05 output per 1M tokens
Llama 3.1 70B Euryale V2.2
Exact model is not listed in Novita’s current public model API. Current price and access remain unresolved; absence does not establish retirement. Retained numerical rates are historical observations.
Llama 3.1 8B Instruct
$0.02 input / $0.05 output per 1M tokens
Llama 3.3 70B Instruct
$0.135 input / $0.40 output per 1M tokens
Llama 4 Maverick Instruct
$0.27 input / $0.85 output per 1M tokens
Llama 4 Scout Instruct
$0.18 input / $0.59 output per 1M tokens
MiniMax M1
$0.55 input / $2.20 output per 1M tokens
MiniMax M2
$0.30 input / $1.20 output per 1M tokens
Cached input: $0.03/1M
MiniMax M2.1
$0.30 input / $1.20 output per 1M tokens
Cached input: $0.03/1M
MiniMax M2.5
$0.30 input / $1.20 output per 1M tokens
Cached input: $0.03/1M
MiniMax M2.5 Highspeed
$0.60 input / $2.40 output per 1M tokens
Cached input: $0.03/1M
MiniMax M2.7
$0.30 input / $1.20 output per 1M tokens
Cached input: $0.06/1M
MiniMax M3.1 Flash
$0.15 input / $0.60 output per 1M tokens
Cached input: $0.015/1M
Mistral NeMo
$0.04 input / $0.17 output per 1M tokens
Qwen 2.5 72B Instruct
$0.38 input / $0.40 output per 1M tokens
Qwen MT Plus
$0.25 input / $0.75 output per 1M tokens
Qwen3 235B A22B
$0.20 input / $0.80 output per 1M tokens
Qwen3 235B A22B Instruct 2507
$0.09 input / $0.58 output per 1M tokens
Qwen3 235B A22B Thinking 2507
$0.30 input / $3.00 output per 1M tokens
Qwen3 Coder 30B A3B Instruct
This exact endpoint is absent from Novita’s current public model listing. Current price and access remain unresolved; absence is not proof of retirement, and dated or successor routes are not substitutes. Retained rates are historical.
Qwen3 Coder 480B A35B Instruct
This exact endpoint is absent from Novita’s current public model listing. Current price and access remain unresolved; absence is not proof of retirement, and dated or successor routes are not substitutes. Retained rates are historical.
Qwen3 Coder Next
This exact endpoint is absent from Novita’s current public model listing. Current price and access remain unresolved; absence is not proof of retirement, and dated or successor routes are not substitutes. Retained rates are historical.
Qwen3 Next 80B A3B Instruct
$0.15 input / $1.50 output per 1M tokens
Qwen3 VL 235B A22B Instruct
$0.30 input / $1.50 output per 1M tokens
Qwen3 VL 235B A22B Thinking
$0.98 input / $3.95 output per 1M tokens
Qwen3 VL 30B A3B Instruct
$0.20 input / $0.70 output per 1M tokens
Qwen3.5-122B-A10B
$0.40 input / $3.20 output per 1M tokens
Qwen3.5-27B
$0.30 input / $2.40 output per 1M tokens
Qwen3.5-35B-A3B
$0.25 input / $2.00 output per 1M tokens
Qwen3.5-397B-A17B
$0.60 input / $3.60 output per 1M tokens
Qwen3.6-27B
$0.60 input / $3.60 output per 1M tokens
Qwen3.6-35B-A3B
$0.248 input / $1.49 output per 1M tokens
Qwen3.7-Max
$1.25 input / $3.75 output per 1M tokens
Cached input: $0.25/1M
Qwen3.8 2.4T A95B
$2.00 input / $6.00 output per 1M tokens
Cached input: $0.25/1M
Qwen3.8 27B
$0.42 input / $3.00 output per 1M tokens
Cached input: $0.085/1M
Qwen3.8 Flash
$0.15 input / $0.47 output per 1M tokens
Cached input: $0.016/1M
Qwen3.8 Max
$2.00 input / $6.00 output per 1M tokens
Cached input: $0.25/1M
Show legacy / other available (6)
Retained for migration and historical comparison. Previous generation does not mean officially shut down; check each model's lifecycle label and source.
GLM-4.5 Air
legacy$0.13 input / $0.85 output per 1M tokens
Cached input: $0.025/1M
GLM-4.5V
legacy$0.60 input / $1.80 output per 1M tokens
Cached input: $0.11/1M
GLM-4.6
legacy$0.55 input / $2.20 output per 1M tokens
Cached input: $0.11/1M
GLM-4.6V
legacy$0.30 input / $0.90 output per 1M tokens
Cached input: $0.055/1M
GLM-4.7
legacy$0.60 input / $2.20 output per 1M tokens
Cached input: $0.11/1M
GLM-4.7-Flash
legacy$0.07 input / $0.40 output per 1M tokens
Cached input: $0.01/1M
OpenAI
4 current · 47 legacy / other available
GPT-6 Astra
$10.00 input / $50.00 output per 1M tokens
Cached input: $1.00/1M
GPT-6 Luna
$0.10 input / $0.50 output per 1M tokens
Cached input: $0.01/1M
GPT-6.1 Sol
$2.00 input / $10.00 output per 1M tokens
Cached input: $0.10/1M
gpt-6.1-terra
$1.00 input / $5.00 output per 1M tokens
Cached input: $0.05/1M
Show legacy / other available (47)
Retained for migration and historical comparison. Previous generation does not mean officially shut down; check each model's lifecycle label and source.
gpt-3.5-turbo
shut downOpenAI shut down this API model on 2026-10-23.
gpt-3.5-turbo-0125
shut downOpenAI shut down this API model on 2026-10-23.
gpt-3.5-turbo-1106
shut downOpenAI shut down this API model on 2026-09-28.
gpt-3.5-turbo-instruct
shut downOpenAI shut down this API model on 2026-09-28.
gpt-4-0613
shut downOpenAI shut down this API model on 2026-10-23.
gpt-4-turbo-2024-04-09
shut downOpenAI shut down this API model on 2026-10-23.
GPT-4.1
deprecated$2.00 input / $8.00 output per 1M tokens
Cached input: $0.50/1M
GPT-4.1 mini
deprecated$0.40 input / $1.60 output per 1M tokens
Cached input: $0.10/1M
GPT-4.1 nano
shut downOpenAI shut down this API model on 2026-10-23.
GPT-4o
deprecated$2.50 input / $10.00 output per 1M tokens
Cached input: $1.25/1M
GPT-4o mini
deprecated$0.15 input / $0.60 output per 1M tokens
Cached input: $0.075/1M
gpt-4o-2024-05-13
shut downOpenAI shut down this API model on 2026-10-23.
GPT-5
deprecated$1.25 input / $10.00 output per 1M tokens
Cached input: $0.125/1M
GPT-5 mini
deprecated$0.25 input / $2.00 output per 1M tokens
Cached input: $0.025/1M
GPT-5 nano
deprecated$0.05 input / $0.40 output per 1M tokens
Cached input: $0.005/1M
GPT-5 Pro
deprecated$15.00 input / $120.00 output per 1M tokens
GPT-5.1
deprecated$1.25 input / $10.00 output per 1M tokens
Cached input: $0.125/1M
GPT-5.2
other available$1.75 input / $14.00 output per 1M tokens
Cached input: $0.175/1M
GPT-5.2 Pro
other available$21.00 input / $168.00 output per 1M tokens
GPT-5.4
other available$2.50 input / $15.00 output per 1M tokens
Cached input: $0.25/1M
GPT-5.4 mini
other available$0.75 input / $4.50 output per 1M tokens
Cached input: $0.075/1M
GPT-5.4 nano
deprecated$0.20 input / $1.25 output per 1M tokens
Cached input: $0.02/1M
GPT-5.4 Pro
other available$30.00 input / $180.00 output per 1M tokens
GPT-5.5
other available$5.00 input / $30.00 output per 1M tokens
Cached input: $0.50/1M
GPT-5.5 Cyber
availability unverified$12.50 input / $75.00 output per 1M tokens
Cached input: $1.25/1M
GPT-5.5 Pro
other available$30.00 input / $180.00 output per 1M tokens
GPT-5.6 Cyber
other available$12.50 input / $75.00 output per 1M tokens
Cached input: $1.25/1M
GPT-5.6 Luna
other available$0.20 input / $1.20 output per 1M tokens
Cached input: $0.02/1M
GPT-5.6 Sol
other available$4.00 input / $20.00 output per 1M tokens
Cached input: $0.40/1M
GPT-5.6 Terra
other available$2.00 input / $12.00 output per 1M tokens
Cached input: $0.20/1M
GPT-6 Cyber
other available$20.00 input / $100.00 output per 1M tokens
Cached input: $2.00/1M
GPT-6 Sol
other available$2.00 input / $10.00 output per 1M tokens
Cached input: $0.20/1M
GPT-Image-1 Mini
deprecatedSee rates and billing units
GPT-Image-1.5
deprecatedSee rates and billing units
GPT-Image-2
deprecatedSee rates and billing units
GPT-Image-2.5 Flare
other availableSee rates and billing units
GPT-Image-2.5 Sunburst
other availableSee rates and billing units
GPT-Image-2.6 Flare
other availableSee rates and billing units
GPT-Image-2.6 Sunburst
other availableSee rates and billing units
GPT-Live 1
other availableSee rates and billing units
GPT-Realtime-2.1
other availableSee rates and billing units
o1
shut downOpenAI shut down this API model on 2026-10-23.
o1-pro
shut downOpenAI shut down this API model on 2026-10-23.
o3
deprecated$2.00 input / $8.00 output per 1M tokens
Cached input: $0.50/1M
o3-mini
shut downOpenAI shut down this API model on 2026-10-23.
o3-pro
deprecated$20.00 input / $80.00 output per 1M tokens
o4-mini
shut downOpenAI shut down this API model on 2026-10-23.
Perplexity
4 current · 0 legacy / other available
Sonar
The retained Sonar pricing route now serves current Agent/Orchestrator billing documentation without this exact Sonar rate. A migration guide does not verify the old endpoint’s price or retirement; retained token rates are historical.
Sonar Deep Research
The retained Sonar pricing route now serves current Agent/Orchestrator billing documentation without this exact Sonar rate. A migration guide does not verify the old endpoint’s price or retirement; retained token rates are historical.
Sonar Pro
The retained Sonar pricing route now serves current Agent/Orchestrator billing documentation without this exact Sonar rate. A migration guide does not verify the old endpoint’s price or retirement; retained token rates are historical.
Sonar Reasoning Pro
The retained Sonar pricing route now serves current Agent/Orchestrator billing documentation without this exact Sonar rate. A migration guide does not verify the old endpoint’s price or retirement; retained token rates are historical.
telnyx
1 current · 0 legacy / other available
Together AI
23 current · 10 legacy / other available
Cogito v2.1 671B
$1.25 input / $1.25 output per 1M tokens
DeepSeek V4 Pro
$1.32 input / $3.96 output per 1M tokens
Cached input: $0.13/1M
Gemma 3n E4B Instruct
$0.06 input / $0.12 output per 1M tokens
Gemma 4 31B IT
$0.39 input / $0.97 output per 1M tokens
Gemma 4 31B IT Pearl
$0.28 input / $0.86 output per 1M tokens
GLM-5.1
$1.40 input / $4.40 output per 1M tokens
Cached input: $0.26/1M
GLM-5.2
$1.40 input / $4.40 output per 1M tokens
Cached input: $0.26/1M
GPT-OSS 120B
$0.15 input / $0.60 output per 1M tokens
GPT-OSS 20B
Dedicated deployment: bills per minute per ready hardware replica, not per token. The card’s $0.05/$0.20 token observations are not a serverless offer.
Kimi K2.6
$1.20 input / $4.50 output per 1M tokens
Cached input: $0.20/1M
Kimi K2.7 Code
Current Together sources do not establish this exact Kimi K2.7 Code serverless token offer. A fine-tuning row or Kimi K3 card is not a current inference quote. Retained rates are historical.
Llama 3 8B Instruct Lite
$0.14 input / $0.14 output per 1M tokens
Llama 3.3 70B
Together explicitly says this model is not available on its Serverless API. Retained card token figures are historical observations, not a current callable offer. Dedicated access, billing and exact limits remain unresolved.
Llama 4 Maverick
Dedicated deployment: bills per minute per ready hardware replica, not per token. Token-card figures do not establish a current serverless offer.
Llama 4 Scout
Dedicated deployment: bills per minute per ready hardware replica, not per token. Token-card figures do not establish a current serverless offer.
MiniMax M2.7
$0.30 input / $1.20 output per 1M tokens
Cached input: $0.06/1M
MiniMax M3
$0.30 input / $1.20 output per 1M tokens
Cached input: $0.06/1M
Nemotron 3 Ultra 550B A55B
$0.60 input / $3.60 output per 1M tokens
Cached input: $0.20/1M
Qwen2.5 7B Instruct Turbo
$0.30 input / $0.30 output per 1M tokens
Qwen3 235B A22B Instruct 2507
$0.20 input / $0.60 output per 1M tokens
Qwen3.5 397B A17B
$0.60 input / $3.60 output per 1M tokens
Cached input: $0.35/1M
Qwen3.5 9B
$0.17 input / $0.25 output per 1M tokens
RNJ-1 Instruct
$0.15 input / $0.15 output per 1M tokens
Show legacy / other available (10)
Retained for migration and historical comparison. Previous generation does not mean officially shut down; check each model's lifecycle label and source.
DeepSeek R1
legacy$3.00 input / $7.00 output per 1M tokens
DeepSeek V3
legacy$1.25 input / $1.25 output per 1M tokens
DeepSeek V3.1
legacy$0.60 input / $1.70 output per 1M tokens
GLM-5
legacy$1.00 input / $3.20 output per 1M tokens
LFM2 24B A2B
legacy$0.03 input / $0.12 output per 1M tokens
Llama 3.1 405B
legacy$3.50 input / $3.50 output per 1M tokens
MiniMax M2.5
legacy$0.30 input / $1.20 output per 1M tokens
Cached input: $0.06/1M
Mistral Large
legacy$3.00 input / $9.00 output per 1M tokens
Mixtral 8x22B
legacy$1.20 input / $1.20 output per 1M tokens
Qwen 2.5 72B
legacy$1.20 input / $1.20 output per 1M tokens
TypeSafe AI
1 current · 0 legacy / other available
xAI
15 current · 4 legacy / other available
Grok 4.20 0309 Non-Reasoning
$1.25 input / $2.50 output per 1M tokens
Cached input: $0.20/1M
Grok 4.20 0309 Reasoning
$1.25 input / $2.50 output per 1M tokens
Cached input: $0.20/1M
Grok 4.20 Multi-Agent 0309
$1.25 input / $2.50 output per 1M tokens
Cached input: $0.20/1M
Grok 4.3
$1.25 input / $2.50 output per 1M tokens
Cached input: $0.20/1M
Grok 4.6
$2.00 input / $6.00 output per 1M tokens
Cached input: $0.50/1M
Grok 4.7
$2.00 input / $6.00 output per 1M tokens
Cached input: $0.50/1M
Grok Build 0.1
$1.00 input / $2.00 output per 1M tokens
Cached input: $0.20/1M
Grok Imagine Image
See rates and billing units
Grok Imagine Image 2.0
See rates and billing units
Grok Imagine Video
See rates and billing units
Grok Imagine Video 1.5
See rates and billing units
Grok Voice Think Fast 1.0
No exact current rate/identity binding was recovered for this historical voice SKU. Current Grok Voice or Transcribe successor rates do not establish this endpoint’s price, access or default status. Retained rates are historical.
Grok Voice Think Fast 2.0
No exact current rate/identity binding was recovered for this historical voice SKU. Current Grok Voice or Transcribe successor rates do not establish this endpoint’s price, access or default status. Retained rates are historical.
Grok Voice Transcribe 1.0
No exact current rate/identity binding was recovered for this historical voice SKU. Current Grok Voice or Transcribe successor rates do not establish this endpoint’s price, access or default status. Retained rates are historical.
Grok Voice Transcribe 2.0
See rates and billing units
Show legacy / other available (4)
Retained for migration and historical comparison. Previous generation does not mean officially shut down; check each model's lifecycle label and source.
Z.ai
2 current · 0 legacy / other available