↑↓ move↵ openesc close

Overage / Metrics

Price per million cached input (read) tokens, every model

List price in USD per 1M tokens, cheapest first. Every row links to its vendor and its source.

Verified 2026-10-23 (2 days ago)Source: DeepSeek API, DeepInfra, Baseten, Crusoe Cloud and 6 more, linked on each service page212 prices from 10 providers; 212 verified in the last 7 days; newest 2026-10-24. Verified shows the oldest.

Price type: Input · Output · Cached input (read) · Cache write · Batch input · Batch output

Price per million cached input (read) tokens, every model, sortable
1deepseek-flash (off-peak)DeepSeek API$0.0031M2026-10-24
2deepseek-flash (peak)DeepSeek API$0.0061M2026-10-24
3deepseek-ai/DeepSeek-V4-Flash-Vision-ExpDeepInfra$0.0069unlisted2026-10-24
4DeepSeek V4.1 FlashBaseten$0.007unlisted2026-10-24
5DeepSeek V4.1 Flash 1017Baseten$0.007unlisted2026-10-24
6DeepSeek V4.1 FlashCrusoe Cloud$0.007unlisted2026-10-24
7Claude Haiku 5.5 (prompt <=100K tokens)Anthropic API$0.01unlisted2026-10-24
8GPT-5-nano Data ZoneAzure OpenAI Service$0.01unlisted2026-10-24
9GPT-5-nano GlobalAzure OpenAI Service$0.01unlisted2026-10-24
10GPT-6 Luna (short context) GlobalAzure OpenAI Service$0.01unlisted2026-10-24
11Gemini 2.5 Flash-LiteGoogle Gemini API$0.01unlisted2026-10-24
12Ministral 3 3BMistral AI API$0.01unlisted2026-10-23
13Mistral EmbedMistral AI API$0.01unlisted2026-10-23
14gpt-6-lunaOpenAI API$0.01unlisted2026-10-24
15GPT-6 Luna (short context) Data ZoneAzure OpenAI Service$0.011unlisted2026-10-24
16DeepSeek V4.1 Flash FastBaseten$0.014unlisted2026-10-24
17DeepSeek-V4-Flash-0731DeepInfra$0.0151.024M2026-10-24
18Codestral EmbedMistral AI API$0.015unlisted2026-10-23
19Ministral 3 8BMistral AI API$0.015unlisted2026-10-23
20Mistral Small 4Mistral AI API$0.015unlisted2026-10-23
21DeepSeek-V4-FlashDeepInfra$0.0181.024M2026-10-24
22GPT-5.4 nano GlobalAzure OpenAI Service$0.02unlisted2026-10-24
23GPT-5.6-luna (short context) GlobalAzure OpenAI Service$0.02unlisted2026-10-24
24GPT-6 Luna (long context) GlobalAzure OpenAI Service$0.02unlisted2026-10-24
25NVIDIA-Nemotron-3.5-Super-VLDeepInfra$0.02256K2026-10-24
26Ministral 3 14BMistral AI API$0.02unlisted2026-10-23
27GPT-6 Luna (long context) Data ZoneAzure OpenAI Service$0.022unlisted2026-10-24
28deepseek-v4-pro (off-peak)DeepSeek API$0.0221M2026-10-24
29Gemini 3.1 Flash-LiteGoogle Gemini API$0.025unlisted2026-10-24
30DeepSeek-V4-Flash-0731Baseten$0.028unlisted2026-10-24
31GPT-4.1-nano-2025-04-14 Data ZoneAzure OpenAI Service$0.03unlisted2026-10-24
32GPT-4.1-nano-2025-04-14 GlobalAzure OpenAI Service$0.03unlisted2026-10-24
33GPT-4.1-nano-2025-04-14 RegionalAzure OpenAI Service$0.03unlisted2026-10-24
34GPT-5-mini Data ZoneAzure OpenAI Service$0.03unlisted2026-10-24
35GPT-5-mini GlobalAzure OpenAI Service$0.03unlisted2026-10-24
36GPT-5.1-codex-mini GlobalAzure OpenAI Service$0.03unlisted2026-10-24
37GPT-5.6-luna (short context) Data ZoneAzure OpenAI Service$0.03unlisted2026-10-24
38GLM-5.3-FlashBaseten$0.03unlisted2026-10-24
39DeepSeek V4 Flash 0731Crusoe Cloud$0.03unlisted2026-10-24
40GLM-5.3 FlashCrusoe Cloud$0.03unlisted2026-10-24
41Nemotron 3 Nano 30BCrusoe Cloud$0.03unlisted2026-10-24
42Nemotron 3.5 Lightning 30B A3BCrusoe Cloud$0.03unlisted2026-10-24
43NVIDIA-Nemotron-3.5-LightningDeepInfra$0.03256K2026-10-24
44Gemini 3.5 Flash-LiteGoogle Gemini API$0.03unlisted2026-10-24
45CodestralMistral AI API$0.03unlisted2026-10-23
46Z.ai GLM 5.3 FlashMistral AI API$0.03unlisted2026-10-23
47MiniMax-M3.1-FlashSambaNova Cloud$0.03unlisted2026-10-24
48Gemini 3.6 Flash (Batch)Google Gemini API$0.0375unlisted2026-10-24
49Gemini 3.6 Flash (Flex)Google Gemini API$0.0375unlisted2026-10-24
50Gemini 3.8 Flash (Batch)Google Gemini API$0.0375unlisted2026-10-24
51Gemini 3.8 Flash (Flex)Google Gemini API$0.0375unlisted2026-10-24
52GPT-5.6-luna (long context) GlobalAzure OpenAI Service$0.04unlisted2026-10-24
53BeamBaseten$0.04unlisted2026-10-24
54Nemotron 3.5 Super VLBaseten$0.04unlisted2026-10-24
55deepseek-v4-pro (peak)DeepSeek API$0.0441M2026-10-24
56Claude Haiku 5.5 (prompt >100K tokens)Anthropic API$0.05unlisted2026-10-24
57GPT-5.6-luna (long context) Data ZoneAzure OpenAI Service$0.05unlisted2026-10-24
58GPT-OSS 120BCrusoe Cloud$0.05unlisted2026-10-24
59gemma-4-31B-it-turboDeepInfra$0.05256K2026-10-24
60Qwen3.5-35B-A3BDeepInfra$0.05256K2026-10-24
61Gemini 3 Flash PreviewGoogle Gemini API$0.05unlisted2026-10-24
62Gemini 4 Argon (Batch)Google Gemini API$0.05unlisted2026-10-24
63Gemini 4 Argon (Flex)Google Gemini API$0.05unlisted2026-10-24
64Mistral Large 3Mistral AI API$0.05unlisted2026-10-23
65GPT-4o-mini-0718 GlobalAzure OpenAI Service$0.075128K2026-10-24
66Gemini 3.6 Flash (Standard)Google Gemini API$0.075unlisted2026-10-24
67Gemini 3.8 Flash (Standard)Google Gemini API$0.075unlisted2026-10-24
68Claude Haiku 3.5Anthropic API$0.08unlisted2026-10-24
69GPT-5.4 mini GlobalAzure OpenAI Service$0.08unlisted2026-10-24
70Nemotron 3.5 Super VL 120B A12BCrusoe Cloud$0.08unlisted2026-10-24
71GPT-4o-mini-0718 RegionalAzure OpenAI Service$0.083128K2026-10-24
72GPT-4o-mini-0718 US/EU – Data ZonesAzure OpenAI Service$0.083128K2026-10-24
73GPT-5.4 mini Data ZoneAzure OpenAI Service$0.09unlisted2026-10-24
74Claude Haiku 4.5Anthropic API$0.10unlisted2026-10-24
75Claude Sonnet 5.5Anthropic API$0.10unlisted2026-10-24
76GPT-4.1-mini-2025-04-14 GlobalAzure OpenAI Service$0.10unlisted2026-10-24
77GPT-6.1 Sol (short context) GlobalAzure OpenAI Service$0.10unlisted2026-10-24
78DeepSeek-V4-ProDeepInfra$0.101.024M2026-10-24
79NVIDIA-Nemotron-3-Ultra-550B-A55BDeepInfra$0.10256K2026-10-24
80Qwen3-Coder-480B-A35B-Instruct-TurboDeepInfra$0.10256K2026-10-24
81Qwen3.6-35B-A3BDeepInfra$0.10256K2026-10-24
82Gemini 4 Argon (Standard)Google Gemini API$0.10unlisted2026-10-24
83Gemini Robotics ER 2 PreviewGoogle Gemini API$0.10unlisted2026-10-24
84gpt-6.1-solOpenAI API$0.10unlisted2026-10-24
85GPT-4.1-mini-2025-04-14 Data ZoneAzure OpenAI Service$0.11unlisted2026-10-24
86GPT-4.1-mini-2025-04-14 RegionalAzure OpenAI Service$0.11unlisted2026-10-24
87GPT-6.1 Sol (short context) Data ZoneAzure OpenAI Service$0.11unlisted2026-10-24
88Qwen3-VL-235B-A22B-InstructDeepInfra$0.11256K2026-10-24
89NVIDIA Nemotron 3 UltraBaseten$0.12unlisted2026-10-24
90Gemini 2.5 Pro (prompt <=200k tokens)Google Gemini API$0.125unlisted2026-10-24
91GPT-5 2025-08-07 GlobalAzure OpenAI Service$0.13unlisted2026-10-24
92GPT-5 chat GlobalAzure OpenAI Service$0.13unlisted2026-10-24
93GPT-5 Codex GlobalAzure OpenAI Service$0.13unlisted2026-10-24
94GPT-5.1 GlobalAzure OpenAI Service$0.13unlisted2026-10-24
95GPT-5.1-chat GlobalAzure OpenAI Service$0.13unlisted2026-10-24
96GPT-5.1-codex GlobalAzure OpenAI Service$0.13unlisted2026-10-24
97GPT-5.1-codex-max GlobalAzure OpenAI Service$0.13unlisted2026-10-24
98DeepSeek-V3.1DeepInfra$0.13160K2026-10-24
99DeepSeek-V3.2DeepInfra$0.13unlisted2026-10-24
100DeepSeek V4 Pro 0813Baseten$0.132unlisted2026-10-24
101Gemini 3.6 Flash (Priority)Google Gemini API$0.135unlisted2026-10-24
102Gemini 3.8 Flash (Priority)Google Gemini API$0.135unlisted2026-10-24
103GPT-5 Data ZoneAzure OpenAI Service$0.14unlisted2026-10-24
104GPT-5.1 Data ZoneAzure OpenAI Service$0.14unlisted2026-10-24
105GLM-5.2Baseten$0.14unlisted2026-10-24
106GLM-5.3Baseten$0.14unlisted2026-10-24
107Gemma 4 31BCrusoe Cloud$0.14unlisted2026-10-24
108Mistral Large 4Mistral AI API$0.14unlisted2026-10-23
109Z.ai GLM 5.3Mistral AI API$0.14unlisted2026-10-23
110Muse Spark OpenBaseten$0.15unlisted2026-10-24
111DeepSeek V4 ProCrusoe Cloud$0.15unlisted2026-10-24
112Nemotron 3 Super 120BCrusoe Cloud$0.15unlisted2026-10-24
113Qwen3.8 27BCrusoe Cloud$0.15unlisted2026-10-24
114Kimi-K2.6DeepInfra$0.15256K2026-10-24
115Mistral Medium 3.5Mistral AI API$0.15unlisted2026-10-23
116gpt-5.3-codexOpenAI API$0.175unlisted2026-10-24
117GPT-5.2 Codex GlobalAzure OpenAI Service$0.18unlisted2026-10-24
118GPT-5.2 GlobalAzure OpenAI Service$0.18unlisted2026-10-24
119GPT-5.2-chat latest GlobalAzure OpenAI Service$0.18unlisted2026-10-24
120GPT-5.3 Chat GlobalAzure OpenAI Service$0.18unlisted2026-10-24
121GPT-5.3 Codex GlobalAzure OpenAI Service$0.18unlisted2026-10-24
122Gemini 4 Argon (Priority)Google Gemini API$0.18unlisted2026-10-24
123Claude Opus 5.5Anthropic API$0.20unlisted2026-10-24
124Claude Sonnet 5Anthropic API$0.20unlisted2026-10-24
125GPT-5.2 Data ZoneAzure OpenAI Service$0.20unlisted2026-10-24
126GPT-5.2-chat Data ZoneAzure OpenAI Service$0.20unlisted2026-10-24
127GPT-5.6-terra (short context) GlobalAzure OpenAI Service$0.20unlisted2026-10-24
128GPT-6 Sol (short context) GlobalAzure OpenAI Service$0.20unlisted2026-10-24
129GPT-6.1 Sol (long context) GlobalAzure OpenAI Service$0.20unlisted2026-10-24
130Gemini 3.1 Pro Preview (prompt <=200K tokens)Google Gemini API$0.20unlisted2026-10-24
131Qwen3.8-MaxDeepInfra$0.206250K2026-10-24
132GLM-5.2 FastBaseten$0.21unlisted2026-10-24
133GLM-5.3 FastBaseten$0.21unlisted2026-10-24
134GPT-5.6-terra (short context) Data ZoneAzure OpenAI Service$0.22unlisted2026-10-24
135GPT-6 Sol (short context) Data ZoneAzure OpenAI Service$0.22unlisted2026-10-24
136GPT-6.1 Sol (long context) Data ZoneAzure OpenAI Service$0.22unlisted2026-10-24
137Qwen3.5-397B-A17BDeepInfra$0.22256K2026-10-24
138Claude Fable 5.1Anthropic API$0.25unlisted2026-10-24
139Claude Mythos 5.1Anthropic API$0.25unlisted2026-10-24
140GPT-5.4 (<272k context length) GlobalAzure OpenAI Service$0.25unlisted2026-10-24
141Gemini 2.5 Pro (prompt >200k tokens)Google Gemini API$0.25unlisted2026-10-24
142GLM-5.3Crusoe Cloud$0.26unlisted2026-10-24
143GPT-5.4 (<272k context length) Data ZoneAzure OpenAI Service$0.28unlisted2026-10-24
144o4-mini 2025-04-16 GlobalAzure OpenAI Service$0.28unlisted2026-10-24
145Kimi-K3DeepInfra$0.2851.024M2026-10-24
146Claude Sonnet 4Anthropic API$0.30unlisted2026-10-24
147Claude Sonnet 4.5Anthropic API$0.30unlisted2026-10-24
148Claude Sonnet 4.6Anthropic API$0.30unlisted2026-10-24
149Kimi K3Baseten$0.30unlisted2026-10-24
150Nemotron 3 Nano OmniCrusoe Cloud$0.30unlisted2026-10-24
151o4-mini 2025-04-16 Data ZoneAzure OpenAI Service$0.31unlisted2026-10-24
152o4-mini 2025-04-16 RegionalAzure OpenAI Service$0.31unlisted2026-10-24
153DeepSeek-R1-0528DeepInfra$0.35160K2026-10-24
154GPT-5.6-sol (short context) GlobalAzure OpenAI Service$0.40unlisted2026-10-24
155GPT-5.6-terra (long context) GlobalAzure OpenAI Service$0.40unlisted2026-10-24
156GPT-6 Sol (long context) GlobalAzure OpenAI Service$0.40unlisted2026-10-24
157Gemini 3.1 Pro Preview (prompt >200K tokens)Google Gemini API$0.40unlisted2026-10-24
158gpt-5.6-solOpenAI API$0.40unlisted2026-10-24
159GPT-5.6-sol (short context) Data ZoneAzure OpenAI Service$0.44unlisted2026-10-24
160GPT-5.6-terra (long context) Data ZoneAzure OpenAI Service$0.44unlisted2026-10-24
161GPT-6 Sol (long context) Data ZoneAzure OpenAI Service$0.44unlisted2026-10-24
162Claude Opus 4.5Anthropic API$0.50unlisted2026-10-24
163Claude Opus 4.6Anthropic API$0.50unlisted2026-10-24
164Claude Opus 4.7Anthropic API$0.50unlisted2026-10-24
165Claude Opus 4.8Anthropic API$0.50unlisted2026-10-24
166Claude Opus 5Anthropic API$0.50unlisted2026-10-24
167GPT-4.1-2025-04-14 GlobalAzure OpenAI Service$0.50unlisted2026-10-24
168GPT-5.4 (>272k context length) GlobalAzure OpenAI Service$0.50unlisted2026-10-24
169GPT-5.5 GlobalAzure OpenAI Service$0.50unlisted2026-10-24
170GPT-Chat Latest 08062026 GlobalAzure OpenAI Service$0.50unlisted2026-10-24
171o3 2025-04-16 GlobalAzure OpenAI Service$0.50unlisted2026-10-24
172Qwen3.7-MaxDeepInfra$0.50250K2026-10-24
173chat-latestOpenAI API$0.50unlisted2026-10-24
174gpt-rosalind-discoveryOpenAI API$0.50unlisted2026-10-24
175gpt-rosalind-researchOpenAI API$0.50unlisted2026-10-24
176GPT-4.1-2025-04-14 Data ZoneAzure OpenAI Service$0.55unlisted2026-10-24
177GPT-4.1-2025-04-14 RegionalAzure OpenAI Service$0.55unlisted2026-10-24
178GPT-5.5 Data ZoneAzure OpenAI Service$0.55unlisted2026-10-24
179GPT-Chat Latest 07012026 Data ZoneAzure OpenAI Service$0.55unlisted2026-10-24
180o1-mini 2024-09-12 GlobalAzure OpenAI Service$0.55unlisted2026-10-24
181o3 2025-04-16 Data ZoneAzure OpenAI Service$0.55unlisted2026-10-24
182o3 2025-04-16 RegionalAzure OpenAI Service$0.55unlisted2026-10-24
183o3 mini 2025-01-31 GlobalAzure OpenAI Service$0.55unlisted2026-10-24
184o1-mini 2024-09-12 RegionalAzure OpenAI Service$0.605unlisted2026-10-24
185o1-mini 2024-09-12 US/EU – Data ZonesAzure OpenAI Service$0.605unlisted2026-10-24
186o3 mini 2025-01-31 RegionalAzure OpenAI Service$0.605unlisted2026-10-24
187o3 mini 2025-01-31-US/EU – Data ZonesAzure OpenAI Service$0.605unlisted2026-10-24
188GPT-5.6-sol (long context) GlobalAzure OpenAI Service$0.80unlisted2026-10-24
189GPT-5.6-sol (long context) Data ZoneAzure OpenAI Service$0.88unlisted2026-10-24
190Claude Fable 5Anthropic API$1unlisted2026-10-24
191Claude Mythos 5Anthropic API$1unlisted2026-10-24
192GPT-5.5 Long Context GlobalAzure OpenAI Service$1unlisted2026-10-24
193GPT-6 Astra (short context) GlobalAzure OpenAI Service$1unlisted2026-10-24
194gpt-6-astraOpenAI API$1unlisted2026-10-24
195GPT-5.5 Long Context Data ZoneAzure OpenAI Service$1.10unlisted2026-10-24
196GPT-6 Astra (short context) Data ZoneAzure OpenAI Service$1.10unlisted2026-10-24
197GPT-4o-2024-08-06 GlobalAzure OpenAI Service$1.25128K2026-10-24
198GPT-4o-2024-1120 GlobalAzure OpenAI Service$1.25128K2026-10-24
199gpt-5.6-cyberOpenAI API$1.25unlisted2026-10-24
200GPT-4o-2024-08-06 RegionalAzure OpenAI Service$1.375128K2026-10-24
201GPT-4o-2024-08-06 US/EU – Data ZonesAzure OpenAI Service$1.375128K2026-10-24
202GPT-4o-2024-1120 RegionalAzure OpenAI Service$1.375128K2026-10-24
203GPT-4o-2024-1120 US/EU – Data ZonesAzure OpenAI Service$1.375128K2026-10-24
204Claude Opus 4Anthropic API$1.50unlisted2026-10-24
205Claude Opus 4.1Anthropic API$1.50unlisted2026-10-24
206GPT-6 Astra (long context) GlobalAzure OpenAI Service$2unlisted2026-10-24
207GPT-6 Astra (long context) Data ZoneAzure OpenAI Service$2.20unlisted2026-10-24
208o3-deep research GlobalAzure OpenAI Service$2.50unlisted2026-10-24
209o1 2024-12-17 GlobalAzure OpenAI Service$7.50unlisted2026-10-24
210o1 2024-12-17 RegionalAzure OpenAI Service$8.25unlisted2026-10-24
211o1 2024-12-17 US/EU – Data ZonesAzure OpenAI Service$8.25unlisted2026-10-24
212o1 preview 2024-09-12 US/EU – Data ZonesAzure OpenAI Service$8.25unlisted2026-10-24

USD per 1M tokens. "+" marks a model whose price changes with volume; the standard band is shown. Hover a verified badge for the freshness sentence. A price we could not source is "unlisted", never estimated.