LLM token prices: azure_ai
LLM API prices per 1M tokens: input, output and cached input, from each provider's listing or the LiteLLM cross-check.
Sources for this list
- Last verified 2026-10-23T22:53:51+00:00 · https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json (community cross-check,
litellm)
No first-party source is read for this model yet; this value is a community cross-check and can lag the provider.
| SKU | Name | Input / 1M | Output / 1M | Cached input | Context window | Last verified | Source |
|---|---|---|---|---|---|---|---|
| Codestral-2501 | Codestral-2501 | USD 0.30 | USD 0.90 | – | 256,000 | 2026-10-23 22:53 UTC | source cross-check |
| Cohere-Embed-V5-Fast | Cohere-Embed-V5-Fast | USD 0.08 | Free | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| Cohere-Embed-V5-Pro | Cohere-Embed-V5-Pro | USD 0.12 | Free | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| Cohere-command-a-plus-05-2026 | Cohere-command-a-plus-05-2026 | USD 0.80 | USD 3.20 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| Cohere-embed-v3-english | Cohere-embed-v3-english | USD 0.10 | Free | – | 512 | 2026-10-23 22:53 UTC | source cross-check |
| Cohere-embed-v3-multilingual | Cohere-embed-v3-multilingual | USD 0.10 | Free | – | 512 | 2026-10-23 22:53 UTC | source cross-check |
| DeepSeek-V4-Flash-0731 | DeepSeek-V4-Flash-0731 | USD 0.44 | USD 1.32 | USD 0.014 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check |
| FW-DeepSeek-V3.2 | FW-DeepSeek-V3.2 | USD 0.62 | USD 1.85 | USD 0.31 | 163,840 | 2026-10-23 22:53 UTC | source cross-check |
| FW-DeepSeek-V4-Flash | FW-DeepSeek-V4-Flash | USD 0.15 | USD 0.31 | USD 0.03 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check |
| FW-DeepSeek-V4-Pro | FW-DeepSeek-V4-Pro | USD 1.925 | USD 3.828 | USD 0.165 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check |
| FW-DeepSeek-V4.1-Flash | FW-DeepSeek-V4.1-Flash | USD 0.375 | USD 1.50 | USD 0.008 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check |
| FW-GLM-5 | FW-GLM-5 | USD 1.10 | USD 3.52 | USD 0.22 | 200,000 | 2026-10-23 22:53 UTC | source cross-check |
| FW-GLM-5.1 | FW-GLM-5.1 | USD 1.54 | USD 4.84 | USD 0.286 | 202,800 | 2026-10-23 22:53 UTC | source cross-check |
| FW-GLM-5.2 | FW-GLM-5.2 | USD 1.54 | USD 4.84 | USD 0.15 | 1,048,576 | 2026-10-23 22:53 UTC | source cross-check |
| FW-GLM-5.2-Fast | FW-GLM-5.2-Fast | USD 2.31 | USD 7.26 | USD 0.231 | 1,048,576 | 2026-10-23 22:53 UTC | source cross-check |
| FW-GLM-5.3 | FW-GLM-5.3 | USD 1.75 | USD 5.50 | USD 0.325 | 1,048,576 | 2026-10-23 22:53 UTC | source cross-check |
| FW-GLM-5.3-Flash | FW-GLM-5.3-Flash | USD 0.188 | USD 0.625 | USD 0.038 | 1,048,576 | 2026-10-23 22:53 UTC | source cross-check |
| FW-GPT-OSS-120B | FW-GPT-OSS-120B | USD 0.165 | USD 0.66 | USD 0.082 | 131,072 | 2026-10-23 22:53 UTC | source cross-check |
| FW-Inkling | FW-Inkling | USD 1.10 | USD 4.46 | USD 0.19 | 1,048,576 | 2026-10-23 22:53 UTC | source cross-check |
| FW-Kimi-K2.5 | FW-Kimi-K2.5 | USD 0.66 | USD 3.30 | USD 0.11 | 262,144 | 2026-10-23 22:53 UTC | source cross-check |
| FW-Kimi-K2.6 | FW-Kimi-K2.6 | USD 1.045 | USD 4.40 | USD 0.176 | 262,144 | 2026-10-23 22:53 UTC | source cross-check |
| FW-Kimi-K2.7-Code | FW-Kimi-K2.7-Code | USD 1.05 | USD 4.40 | USD 0.21 | 262,144 | 2026-10-23 22:53 UTC | source cross-check |
| FW-Kimi-K3 | FW-Kimi-K3 | USD 3.00 | USD 15.00 | USD 0.30 | 1,048,576 | 2026-10-23 22:53 UTC | source cross-check |
| FW-MiniMax-M2.5 | FW-MiniMax-M2.5 | USD 0.33 | USD 1.32 | USD 0.033 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check |
| FW-MiniMax-M3 | FW-MiniMax-M3 | USD 0.33 | USD 1.32 | USD 0.066 | 512,000 | 2026-10-23 22:53 UTC | source cross-check |
| FW-Nemotron-3-Ultra-NVFP4 | FW-Nemotron-3-Ultra-NVFP4 | USD 0.66 | USD 2.64 | USD 0.13 | 262,144 | 2026-10-23 22:53 UTC | source cross-check |
| FW-Nemotron-Lightning-3.5-30B-A3B | FW-Nemotron-Lightning-3.5-30B-A3B | USD 0.06 | USD 0.22 | USD 0.01 | 262,144 | 2026-10-23 22:53 UTC | source cross-check |
| Llama-3.3-70B-Instruct | Llama-3.3-70B-Instruct | USD 0.71 | USD 0.71 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | Llama-4-Maverick-17B-128E-Instruct-FP8 | USD 0.25 | USD 1.00 | – | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check |
| Llama-4-Scout-17B-16E-Instruct | Llama-4-Scout-17B-16E-Instruct | USD 0.20 | USD 0.78 | – | 10,000,000 | 2026-10-23 22:53 UTC | source cross-check |
| MAI-Code-1.1-Flash | MAI-Code-1.1-Flash | USD 0.20 | USD 1.20 | USD 0.02 | 256,000 | 2026-10-23 22:53 UTC | source cross-check |
| MAI-Cyber-1-Flash | MAI-Cyber-1-Flash | USD 0.60 | USD 3.50 | USD 0.06 | 256,000 | 2026-10-23 22:53 UTC | source cross-check |
| MAI-DS-R1 | MAI-DS-R1 | USD 1.35 | USD 5.40 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| MAI-Thinking-1 | MAI-Thinking-1 | USD 2.00 | USD 8.00 | USD 0.20 | 256,000 | 2026-10-23 22:53 UTC | source cross-check |
| Meta-Llama-3-70B-Instruct | Meta-Llama-3-70B-Instruct | USD 1.10 | USD 0.37 | – | 8,192 | 2026-10-23 22:53 UTC | source cross-check |
| Meta-Llama-3.1-70B-Instruct | Meta-Llama-3.1-70B-Instruct | USD 2.68 | USD 3.54 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-3-medium-128k-instruct | Phi-3-medium-128k-instruct | USD 0.17 | USD 0.68 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-3-medium-4k-instruct | Phi-3-medium-4k-instruct | USD 0.17 | USD 0.68 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-3-mini-128k-instruct | Phi-3-mini-128k-instruct | USD 0.13 | USD 0.52 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-3-mini-4k-instruct | Phi-3-mini-4k-instruct | USD 0.13 | USD 0.52 | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-3-small-128k-instruct | Phi-3-small-128k-instruct | USD 0.15 | USD 0.60 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-3-small-8k-instruct | Phi-3-small-8k-instruct | USD 0.15 | USD 0.60 | – | 8,192 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-3.5-MoE-instruct | Phi-3.5-MoE-instruct | USD 0.16 | USD 0.64 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-3.5-mini-instruct | Phi-3.5-mini-instruct | USD 0.13 | USD 0.52 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-3.5-vision-instruct | Phi-3.5-vision-instruct | USD 0.13 | USD 0.52 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-4 | Phi-4 | USD 0.125 | USD 0.50 | – | 16,384 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-4-mini-instruct | Phi-4-mini-instruct | USD 0.075 | USD 0.30 | – | 131,072 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-4-mini-reasoning | Phi-4-mini-reasoning | USD 0.075 | USD 0.30 | – | 131,072 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-4-multimodal-instruct | Phi-4-multimodal-instruct | USD 0.08 | USD 0.32 | – | 131,072 | 2026-10-23 22:53 UTC | source cross-check |
| Phi-4-reasoning | Phi-4-reasoning | USD 0.125 | USD 0.50 | – | 32,768 | 2026-10-23 22:53 UTC | source cross-check |
| azure_ai/claude-fable-5 | USD 10.00 | USD 50.00 | USD 1.00 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-fable-5-1 | USD 10.00 | USD 50.00 | USD 0.25 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-haiku-4-5 | USD 1.00 | USD 5.00 | USD 0.10 | 200,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-haiku-5-5 | USD 0.10 | USD 0.50 | USD 0.01 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-opus-4-5 | USD 5.00 | USD 25.00 | USD 0.50 | 200,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-opus-4-6 | USD 5.00 | USD 25.00 | USD 0.50 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-opus-4-7 | USD 5.00 | USD 25.00 | USD 0.50 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-opus-4-8 | USD 5.00 | USD 25.00 | USD 0.50 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-opus-5 | USD 5.00 | USD 25.00 | USD 0.50 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-opus-5-5 | USD 4.00 | USD 20.00 | USD 0.20 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-sonnet-4-5 | USD 3.00 | USD 15.00 | USD 0.30 | 200,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-sonnet-4-6 | USD 3.00 | USD 15.00 | USD 0.30 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-sonnet-5 | USD 2.00 | USD 10.00 | USD 0.20 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/claude-sonnet-5-5 | USD 2.00 | USD 10.00 | USD 0.20 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/deepseek-v4-flash | USD 0.19 | USD 0.51 | USD 0.028 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/deepseek-v4-pro | USD 1.74 | USD 3.48 | USD 0.145 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-5.4 | USD 2.50 | USD 15.00 | USD 0.25 | 922,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-5.4-2026-03-05 | USD 2.50 | USD 15.00 | USD 0.25 | 922,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-5.4-mini | USD 0.75 | USD 4.50 | USD 0.075 | 272,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-5.4-mini-2026-03-17 | USD 0.75 | USD 4.50 | USD 0.075 | 272,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-5.4-nano | USD 0.20 | USD 1.25 | USD 0.02 | 272,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-5.4-nano-2026-03-17 | USD 0.20 | USD 1.25 | USD 0.02 | 272,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-5.4-pro | USD 30.00 | USD 180.00 | USD 3.00 | 922,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-5.4-pro-2026-03-05 | USD 30.00 | USD 180.00 | USD 3.00 | 922,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-5.5 | USD 5.00 | USD 30.00 | USD 0.50 | 922,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-5.5-2026-04-23 | USD 5.00 | USD 30.00 | USD 0.50 | 922,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-6-astra | USD 10.00 | USD 50.00 | USD 1.00 | 922,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-6-luna | USD 0.10 | USD 0.50 | USD 0.01 | 922,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-6-sol | USD 2.00 | USD 10.00 | USD 0.20 | 922,000 | 2026-10-23 22:53 UTC | source cross-check | |
| azure_ai/gpt-6.1-sol | USD 2.00 | USD 10.00 | USD 0.10 | 922,000 | 2026-10-23 22:53 UTC | source cross-check | |
| claude-opus-5-5-fast | claude-opus-5-5-fast | USD 8.00 | USD 40.00 | USD 0.40 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check |
| codex-mini | codex-mini | USD 1.50 | USD 6.00 | USD 0.375 | 200,000 | 2026-10-23 22:53 UTC | source cross-check |
| cohere-command-a | cohere-command-a | USD 2.50 | USD 10.00 | – | 131,072 | 2026-10-23 22:53 UTC | source cross-check |
| cohere-rerank-v3-english | cohere-rerank-v3-english | Free | Free | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| cohere-rerank-v3-multilingual | cohere-rerank-v3-multilingual | Free | Free | – | 4,096 | 2026-10-23 22:53 UTC | source cross-check |
| cohere-rerank-v4.0-fast | cohere-rerank-v4.0-fast | Free | Free | – | 32,768 | 2026-10-23 22:53 UTC | source cross-check |
| cohere-rerank-v4.0-pro | cohere-rerank-v4.0-pro | Free | Free | – | 32,768 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-r1 | deepseek-r1 | USD 1.35 | USD 5.40 | – | 2026-10-23 22:53 UTC | source cross-check | |
| deepseek-v3 | deepseek-v3 | USD 1.14 | USD 4.56 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-v3-0324 | deepseek-v3-0324 | USD 1.14 | USD 4.56 | – | 2026-10-23 22:53 UTC | source cross-check | |
| deepseek-v3.1 | deepseek-v3.1 | USD 1.23 | USD 4.94 | – | 2026-10-23 22:53 UTC | source cross-check | |
| deepseek-v3.2 | deepseek-v3.2 | USD 0.58 | USD 1.68 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-v3.2-speciale | deepseek-v3.2-speciale | USD 0.58 | USD 1.68 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| deepseek-v4.1-flash | deepseek-v4.1-flash | USD 0.30 | USD 1.20 | USD 0.006 | 1,000,000 | 2026-10-23 22:53 UTC | source cross-check |
| embed-v-4-0 | embed-v-4-0 | USD 0.12 | Free | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| gpt-5.5-2026-04-24 | gpt-5.5-2026-04-24 | USD 5.00 | USD 30.00 | USD 0.50 | 922,000 | 2026-10-23 22:53 UTC | source cross-check |
| gpt-chat-latest | gpt-chat-latest | USD 5.00 | USD 30.00 | USD 0.50 | 272,000 | 2026-10-23 22:53 UTC | source cross-check |
| gpt-oss-120b | gpt-oss-120b | USD 0.15 | USD 0.60 | – | 131,072 | 2026-10-23 22:53 UTC | source cross-check |
| grok-3 | grok-3 | USD 3.00 | USD 15.00 | – | 2026-10-23 22:53 UTC | source cross-check | |
| grok-3-mini | grok-3-mini | USD 0.25 | USD 1.27 | – | 2026-10-23 22:53 UTC | source cross-check | |
| grok-4 | grok-4 | USD 3.00 | USD 15.00 | – | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| grok-4-1-fast-non-reasoning | grok-4-1-fast-non-reasoning | USD 0.20 | USD 0.50 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| grok-4-1-fast-reasoning | grok-4-1-fast-reasoning | USD 0.20 | USD 0.50 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| grok-4-20-non-reasoning | grok-4-20-non-reasoning | USD 1.25 | USD 2.50 | USD 1.25 | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| grok-4-20-reasoning | grok-4-20-reasoning | USD 1.25 | USD 2.50 | USD 1.25 | 262,000 | 2026-10-23 22:53 UTC | source cross-check |
| grok-4-fast-non-reasoning | grok-4-fast-non-reasoning | USD 0.20 | USD 0.50 | – | 2026-10-23 22:53 UTC | source cross-check | |
| grok-4-fast-reasoning | grok-4-fast-reasoning | USD 0.20 | USD 0.50 | – | 2026-10-23 22:53 UTC | source cross-check | |
| grok-4.3 | grok-4.3 | USD 1.25 | USD 2.50 | USD 0.20 | 200,000 | 2026-10-23 22:53 UTC | source cross-check |
| grok-4.6 | grok-4.6 | USD 2.00 | USD 6.00 | USD 0.50 | 200,000 | 2026-10-23 22:53 UTC | source cross-check |
| grok-4.7 | grok-4.7 | USD 2.00 | USD 6.00 | USD 0.50 | 500,000 | 2026-10-23 22:53 UTC | source cross-check |
| grok-code-fast-1 | grok-code-fast-1 | USD 0.20 | USD 1.50 | – | 256,000 | 2026-10-23 22:53 UTC | source cross-check |
| jais-30b-chat | jais-30b-chat | USD 3,200.00 | USD 9,710.00 | – | 8,192 | 2026-10-23 22:53 UTC | source cross-check |
| jamba-instruct | jamba-instruct | USD 0.50 | USD 0.70 | – | 70,000 | 2026-10-23 22:53 UTC | source cross-check |
| kimi-k2-thinking | kimi-k2-thinking | USD 0.60 | USD 2.50 | – | 262,144 | 2026-10-23 22:53 UTC | source cross-check |
| kimi-k2.5 | kimi-k2.5 | USD 0.60 | USD 3.00 | USD 0.10 | 262,144 | 2026-10-23 22:53 UTC | source cross-check |
| kimi-k2.6 | kimi-k2.6 | USD 0.95 | USD 4.00 | USD 0.16 | 262,144 | 2026-10-23 22:53 UTC | source cross-check |
| kimi-k2.7-code | kimi-k2.7-code | USD 0.95 | USD 4.00 | USD 0.19 | 262,144 | 2026-10-23 22:53 UTC | source cross-check |
| ministral-3b | ministral-3b | USD 0.04 | USD 0.04 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| mistral-large | mistral-large | USD 4.00 | USD 12.00 | – | 32,000 | 2026-10-23 22:53 UTC | source cross-check |
| mistral-large-2407 | mistral-large-2407 | USD 2.00 | USD 6.00 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| mistral-large-3 | mistral-large-3 | USD 0.50 | USD 1.50 | – | 256,000 | 2026-10-23 22:53 UTC | source cross-check |
| mistral-large-latest | mistral-large-latest | USD 2.00 | USD 6.00 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| mistral-medium-2505 | mistral-medium-2505 | USD 0.40 | USD 2.00 | – | 131,072 | 2026-10-23 22:53 UTC | source cross-check |
| mistral-medium-3-5 | mistral-medium-3-5 | USD 1.50 | USD 7.50 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| mistral-nemo | mistral-nemo | USD 0.15 | USD 0.15 | – | 131,072 | 2026-10-23 22:53 UTC | source cross-check |
| mistral-small | mistral-small | USD 1.00 | USD 3.00 | – | 32,000 | 2026-10-23 22:53 UTC | source cross-check |
| mistral-small-2503 | mistral-small-2503 | USD 0.10 | USD 0.30 | – | 128,000 | 2026-10-23 22:53 UTC | source cross-check |
| model-router | model-router | USD 0.14 | Free | – | 200,000 | 2026-10-23 22:53 UTC | source cross-check |
| model_router | model_router | USD 0.14 | Free | – | 200,000 | 2026-10-23 22:53 UTC | source cross-check |