Skip to content
Model prices

Azure AI API pricing

97 Azure AI models, in US dollars per million tokens. Updated Oct 28, 2026.

97 models
US dollars per million tokens
ModelInputCached inputOutputContextNotes
claude-fable-5$10.00$1.00$50.001M
Retires Dec 5, 2027
claude-fable-5-1$10.00$0.25$50.001M
Retires Dec 5, 2027
claude-haiku-4-5$1.00$0.10$5.00200K
Retires Nov 15, 2026
claude-haiku-5-5$0.10$0.01$0.501M
Retires Sep 29, 2027
claude-opus-4-5$5.00$0.50$25.00200K
Retires Nov 24, 2026
claude-opus-4-6$5.00$0.50$25.001M
Retires Feb 2, 2027
claude-opus-4-7$5.00$0.50$25.001M
Retires Apr 6, 2027
claude-opus-4-8$5.00$0.50$25.001M
Retires Sep 1, 2027
claude-opus-5$5.00$0.50$25.001M
Retires Jul 8, 2027
claude-opus-5-5$4.00$0.20$20.001M
Retires Sep 18, 2027
claude-opus-5-5-fast$8.00$0.40$40.001M
Retires Oct 1, 2027
claude-sonnet-4-5$3.00$0.30$15.00200K
Retires Nov 30, 2026
claude-sonnet-4-6$3.00$0.30$15.001M
Retires Feb 10, 2027
claude-sonnet-5$2.00$0.20$10.001M
Retires Jun 30, 2027
claude-sonnet-5-5$2.00$0.20$10.001M
Retires Sep 29, 2027
Codestral-2501$0.30—$0.90256K
codex-mini$1.50$0.375$6.00200K
Retires Nov 15, 2026
cohere-command-a$2.50—$10.00131K
Cohere-embed-v3-english$0.10——1K
Embedding
Cohere-embed-v3-multilingual$0.10——1K
Embedding
Cohere-Embed-V5-Fast$0.08——128K
EmbeddingRetires Jan 23, 2027
Cohere-Embed-V5-Pro$0.12——128K
EmbeddingRetires Jan 23, 2027
deepseek-v3.2$0.58—$1.68128K
deepseek-v3.2-speciale$0.58—$1.68128K
deepseek-v4-flash$0.19$0.028$0.511M
Retires Feb 20, 2028
DeepSeek-V4-Flash-0731$0.44$0.014$1.321M
Retires Dec 3, 2026
deepseek-v4-pro$1.74$0.145$3.481M
Retires Feb 20, 2028
deepseek-v4.1-flash$0.30$0.006$1.201M
Retires Dec 15, 2026
embed-v-4-0$0.12——128K
Embedding
FW-DeepSeek-V3.2$0.62$0.31$1.85164K
Retires Jul 1, 2027
FW-DeepSeek-V4-Flash$0.15$0.03$0.311M
FW-DeepSeek-V4-Pro$1.93$0.165$3.831M
FW-DeepSeek-V4.1-Flash$0.375$0.008$1.501M
FW-GLM-5$1.10$0.22$3.52200K
Retires Jul 1, 2027
FW-GLM-5.1$1.54$0.286$4.84203K
Retires Jul 1, 2027
FW-GLM-5.2$1.54$0.15$4.841.05M
FW-GLM-5.2-Fast$2.31$0.231$7.261.05M
FW-GLM-5.3$1.75$0.325$5.501.05M
FW-GLM-5.3-Flash$0.188$0.038$0.6251.05M
FW-GPT-OSS-120B$0.165$0.082$0.66131K
Retires Jul 1, 2027
FW-Inkling$1.10$0.19$4.461.05M
FW-Kimi-K2.5$0.66$0.11$3.30262K
Retires Jul 1, 2027
FW-Kimi-K2.6$1.04$0.176$4.40262K
FW-Kimi-K2.7-Code$1.05$0.21$4.40262K
FW-Kimi-K3$3.00$0.30$15.001.05M
FW-MiniMax-M2.5$0.33$0.033$1.321M
Retires Jul 1, 2027
FW-MiniMax-M3$0.33$0.066$1.32512K
FW-Nemotron-3-Ultra-NVFP4$0.66$0.13$2.64262K
FW-Nemotron-Lightning-3.5-30B-A3B$0.06$0.01$0.22262K
gpt-5.4$2.50$0.25$15.00922K
Retires Sep 2, 2027
gpt-5.4-2026-03-05$2.50$0.25$15.00922K
Retires Sep 2, 2027
gpt-5.4-mini$0.75$0.075$4.50272K
Retires Sep 21, 2027
gpt-5.4-mini-2026-03-17$0.75$0.075$4.50272K
Retires Sep 21, 2027
gpt-5.4-nano$0.20$0.02$1.25272K
Retires Sep 21, 2027
gpt-5.4-nano-2026-03-17$0.20$0.02$1.25272K
Retires Sep 21, 2027
gpt-5.4-pro$30.00$3.00$180.00922K
Retires Sep 7, 2027
gpt-5.4-pro-2026-03-05$30.00$3.00$180.00922K
Retires Sep 7, 2027
gpt-5.5$5.00$0.50$30.00922K
Retires Oct 26, 2027
gpt-5.5-2026-04-23$5.00$0.50$30.00922K
gpt-5.5-2026-04-24$5.00$0.50$30.00922K
Retires Oct 26, 2027
gpt-6-astra$10.00$1.00$50.00922K
gpt-6-luna$0.10$0.01$0.50922K
gpt-6-sol$2.00$0.20$10.00922K
gpt-6.1-sol$2.00$0.10$10.00922K
gpt-chat-latest$5.00$0.50$30.00128K
Retires May 18, 2027
gpt-oss-120b$0.15—$0.60131K
grok-4$3.00—$15.00262K
grok-4-1-fast-non-reasoning$0.20—$0.50128K
grok-4-1-fast-reasoning$0.20—$0.50128K
grok-4-20-non-reasoning$1.25$1.25$2.50262K
Retires Apr 6, 2027
grok-4-20-reasoning$1.25$1.25$2.50262K
Retires Apr 6, 2027
grok-4.3$1.25$0.20$2.50200K
grok-4.6$2.00$0.50$6.00200K
grok-4.7$2.00$0.50$6.00500K
Retires Oct 5, 2027
grok-code-fast-1$0.20—$1.50256K
kimi-k2.5$0.60$0.10$3.00262K
Retires Jan 26, 2027
kimi-k2.6$0.95$0.16$4.00262K
Retires Apr 16, 2027
kimi-k2.7-code$0.95$0.19$4.00262K
Retires Apr 16, 2027
Llama-3.3-70B-Instruct$0.71—$0.71128K
Llama-4-Maverick-17B-128E-Instruct-FP8$0.25—$1.001M
Llama-4-Scout-17B-16E-Instruct$0.20—$0.7810M
MAI-Code-1.1-Flash$0.20$0.02$1.20256K
Retires Dec 9, 2026
MAI-Cyber-1-Flash$0.60$0.06$3.50256K
MAI-Thinking-1$2.00$0.20$8.00256K
ministral-3b$0.04—$0.04128K
Retires Dec 9, 2026
mistral-large-3$0.50—$1.50256K
mistral-large-latest$2.00—$6.00128K
mistral-medium-2505$0.40—$2.00131K
Retires Dec 9, 2026
mistral-medium-3-5$1.50—$7.50128K
mistral-small-2503$0.10—$0.30128K
Retires Dec 9, 2026
model_router$0.14—$0200K
Retires May 20, 2027
model-router$0.14—$0200K
Retires May 20, 2027
Phi-4$0.125—$0.5016K
Retires Jan 17, 2027
Phi-4-mini-instruct$0.075—$0.30131K
Retires Jan 17, 2027
Phi-4-mini-reasoning$0.075—$0.30131K
Retires Jan 17, 2027
Phi-4-multimodal-instruct$0.08—$0.32131K
Retires Jan 17, 2027
Phi-4-reasoning$0.125—$0.5033K
Retires Jan 17, 2027

See what your Azure AI calls actually cost, by service, model and customer, priced for where each call ran.

Get started free

List prices from LiteLLM's public price file. Long-prompt, batch and priority rates aren't shown; check Azure AI's pricing page before you commit to a budget. All providers