All Providers
96 Models
30 Families
2M Max Context
$0.02–$60 Input Cost/MTok
$0–$180 Output Cost/MTok
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Setup
Set the following environment variables to use Azure Cognitive Services:
AZURE_COGNITIVE_SERVICES_RESOURCE_NAME AZURE_COGNITIVE_SERVICES_API_KEY Models (96)
| Model | Model ID | Input Cost | Output Cost | Context | Capabilities |
|---|---|---|---|---|---|
| text-embedding-3-small text-embedding | text-embedding-3-small | $0.02/MTok | $0/MTok | 8.2K | |
| Ministral 3B ministral | ministral-3b | $0.04/MTok | $0.04/MTok | 128K | Tools Open |
| GPT-5 Nano gpt-nano | gpt-5-nano | $0.05/MTok | $0.40/MTok | 272K | Reasoning Tools |
| Phi-4-mini-reasoning phi | phi-4-mini-reasoning | $0.07/MTok | $0.30/MTok | 128K | Reasoning Tools Open |
| Phi-4-mini phi | phi-4-mini | $0.07/MTok | $0.30/MTok | 128K | Tools Open |
| Phi-4-multimodal phi | phi-4-multimodal | $0.08/MTok | $0.32/MTok | 128K | Open |
| Embed v3 Multilingual cohere-embed | cohere-embed-v3-multilingual | $0.10/MTok | $0/MTok | 512 | Open |
| Embed v3 English cohere-embed | cohere-embed-v3-english | $0.10/MTok | $0/MTok | 512 | Open |
| text-embedding-ada-002 text-embedding | text-embedding-ada-002 | $0.10/MTok | $0/MTok | 8.2K | |
| Mistral Small 3.1 mistral-small | mistral-small-2503 | $0.10/MTok | $0.30/MTok | 128K | Tools |
| GPT-4.1 nano gpt-nano | gpt-4.1-nano | $0.10/MTok | $0.40/MTok | 1.0M | Tools |
| Embed v4 cohere-embed | cohere-embed-v-4-0 | $0.12/MTok | $0/MTok | 128K | Open |
| Phi-4-reasoning-plus phi | phi-4-reasoning-plus | $0.13/MTok | $0.50/MTok | 32K | Reasoning Open |
| Phi-4 phi | phi-4 | $0.13/MTok | $0.50/MTok | 128K | Open |
| Phi-4-reasoning phi | phi-4-reasoning | $0.13/MTok | $0.50/MTok | 32K | Reasoning Open |
| Phi-3-mini-instruct (4k) phi | phi-3-mini-4k-instruct | $0.13/MTok | $0.52/MTok | 4.1K | Open |
| Phi-3.5-mini-instruct phi | phi-3.5-mini-instruct | $0.13/MTok | $0.52/MTok | 128K | Open |
| Phi-3-mini-instruct (128k) phi | phi-3-mini-128k-instruct | $0.13/MTok | $0.52/MTok | 128K | Open |
| text-embedding-3-large text-embedding | text-embedding-3-large | $0.13/MTok | $0/MTok | 8.2K | |
| Model Router model-router | model-router | $0.14/MTok | $0/MTok | 128K | Tools |
| Phi-3-small-instruct (8k) phi | phi-3-small-8k-instruct | $0.15/MTok | $0.60/MTok | 8.2K | Open |
| Phi-3-small-instruct (128k) phi | phi-3-small-128k-instruct | $0.15/MTok | $0.60/MTok | 128K | Open |
| Mistral Nemo mistral-nemo | mistral-nemo | $0.15/MTok | $0.15/MTok | 128K | Tools Open |
| Command R command-r | cohere-command-r-08-2024 | $0.15/MTok | $0.60/MTok | 128K | Tools Open |
| GPT-4o mini gpt-mini | gpt-4o-mini | $0.15/MTok | $0.60/MTok | 128K | Tools |
| Phi-3.5-MoE-instruct phi | phi-3.5-moe-instruct | $0.16/MTok | $0.64/MTok | 128K | Open |
| Phi-3-medium-instruct (4k) phi | phi-3-medium-4k-instruct | $0.17/MTok | $0.68/MTok | 4.1K | Open |
| Phi-3-medium-instruct (128k) phi | phi-3-medium-128k-instruct | $0.17/MTok | $0.68/MTok | 128K | Open |
| Grok 4 Fast (Reasoning) grok | grok-4-fast-reasoning | $0.20/MTok | $0.50/MTok | 2M | Reasoning Tools |
| Llama 4 Scout 17B 16E Instruct llama | llama-4-scout-17b-16e-instruct | $0.20/MTok | $0.78/MTok | 128K | Tools Open |
| GPT-5.4 Nano gpt-nano | gpt-5.4-nano | $0.20/MTok | $1.25/MTok | 400K | Reasoning Tools |
| Llama 4 Maverick 17B 128E Instruct FP8 llama | llama-4-maverick-17b-128e-instruct-fp8 | $0.25/MTok | $1/MTok | 128K | Tools Open |
| GPT-5.1 Codex Mini gpt-codex | gpt-5.1-codex-mini | $0.25/MTok | $2/MTok | 400K | Reasoning Tools |
| GPT-5 Mini gpt-mini | gpt-5-mini | $0.25/MTok | $2/MTok | 272K | Reasoning Tools |
| Codestral 25.01 codestral | codestral-2501 | $0.30/MTok | $0.90/MTok | 256K | Tools |
| Meta-Llama-3-8B-Instruct llama | meta-llama-3-8b-instruct | $0.30/MTok | $0.61/MTok | 8.2K | Open |
| Meta-Llama-3.1-8B-Instruct llama | meta-llama-3.1-8b-instruct | $0.30/MTok | $0.61/MTok | 128K | Tools Open |
| Llama-3.2-11B-Vision-Instruct llama | llama-3.2-11b-vision-instruct | $0.37/MTok | $0.37/MTok | 128K | Tools Open |
| Mistral Medium 3 mistral-medium | mistral-medium-2505 | $0.40/MTok | $2/MTok | 128K | Tools |
| GPT-4.1 mini gpt-mini | gpt-4.1-mini | $0.40/MTok | $1.60/MTok | 1.0M | Tools |
| GPT-3.5 Turbo 0125 gpt | gpt-3.5-turbo-0125 | $0.50/MTok | $1.50/MTok | 16.4K | |
| DeepSeek-V3.1 deepseek | deepseek-v3.1 | $0.56/MTok | $1.68/MTok | 131.1K | Reasoning Tools Open |
| DeepSeek-V3.2-Speciale deepseek | deepseek-v3.2-speciale | $0.58/MTok | $1.68/MTok | 128K | Reasoning Open |
| DeepSeek-V3.2 deepseek | deepseek-v3.2 | $0.58/MTok | $1.68/MTok | 128K | Reasoning Tools Open |
| Kimi K2.5 kimi | kimi-k2.5 | $0.60/MTok | $3/MTok | 262.1K | Reasoning Tools Open |
| Kimi K2 Thinking kimi-thinking | kimi-k2-thinking | $0.60/MTok | $2.50/MTok | 262.1K | Reasoning Tools Open |
| Llama-3.3-70B-Instruct llama | llama-3.3-70b-instruct | $0.71/MTok | $0.71/MTok | 128K | Tools Open |
| GPT-5.4 Mini gpt-mini | gpt-5.4-mini | $0.75/MTok | $4.50/MTok | 400K | Reasoning Tools |
| Kimi K2.6 kimi | kimi-k2.6 | $0.95/MTok | $4/MTok | 262.1K | Reasoning Tools Open |
| Claude Haiku 4.5 claude-haiku | claude-haiku-4-5 | $1/MTok | $5/MTok | 200K | Reasoning Tools |
| GPT-3.5 Turbo 1106 gpt | gpt-3.5-turbo-1106 | $1/MTok | $2/MTok | 16.4K | |
| o1-mini o-mini | o1-mini | $1.10/MTok | $4.40/MTok | 128K | Reasoning Tools |
| o3-mini o-mini | o3-mini | $1.10/MTok | $4.40/MTok | 200K | Reasoning Tools |
| o4-mini o-mini | o4-mini | $1.10/MTok | $4.40/MTok | 200K | Reasoning Tools |
| DeepSeek-V3-0324 deepseek | deepseek-v3-0324 | $1.14/MTok | $4.56/MTok | 131.1K | Tools Open |
| GPT-5.1 Chat gpt-codex | gpt-5.1-chat | $1.25/MTok | $10/MTok | 128K | Reasoning Tools |
| GPT-5.1 Codex gpt-codex | gpt-5.1-codex | $1.25/MTok | $10/MTok | 400K | Reasoning Tools |
| GPT-5.1 gpt | gpt-5.1 | $1.25/MTok | $10/MTok | 272K | Reasoning Tools |
| GPT-5 gpt | gpt-5 | $1.25/MTok | $10/MTok | 272K | Reasoning Tools |
| GPT-5-Codex gpt-codex | gpt-5-codex | $1.25/MTok | $10/MTok | 400K | Reasoning Tools |
| GPT-5 Chat gpt-codex | gpt-5-chat | $1.25/MTok | $10/MTok | 128K | Reasoning |
| DeepSeek-R1 deepseek-thinking | deepseek-r1 | $1.35/MTok | $5.40/MTok | 163.8K | Reasoning Open |
| MAI-DS-R1 mai | mai-ds-r1 | $1.35/MTok | $5.40/MTok | 128K | Reasoning |
| DeepSeek-R1-0528 deepseek-thinking | deepseek-r1-0528 | $1.35/MTok | $5.40/MTok | 163.8K | Reasoning Tools Open |
| Codex Mini gpt-codex-mini | codex-mini | $1.50/MTok | $6/MTok | 200K | Reasoning Tools |
| GPT-3.5 Turbo 0301 gpt | gpt-3.5-turbo-0301 | $1.50/MTok | $2/MTok | 4.1K | |
| GPT-3.5 Turbo Instruct gpt | gpt-3.5-turbo-instruct | $1.50/MTok | $2/MTok | 4.1K | |
| GPT-5.2 Codex gpt-codex | gpt-5.2-codex | $1.75/MTok | $14/MTok | 400K | Reasoning Tools |
| GPT-5.2 Chat gpt-codex | gpt-5.2-chat | $1.75/MTok | $14/MTok | 128K | Reasoning Tools |
| GPT-5.3 Codex gpt-codex | gpt-5.3-codex | $1.75/MTok | $14/MTok | 400K | Reasoning Tools |
| GPT-5.2 gpt | gpt-5.2 | $1.75/MTok | $14/MTok | 400K | Reasoning Tools |
| Mistral Large 24.11 mistral-large | mistral-large-2411 | $2/MTok | $6/MTok | 128K | Tools |
| GPT-4.1 gpt | gpt-4.1 | $2/MTok | $8/MTok | 1.0M | Tools |
| o3 o | o3 | $2/MTok | $8/MTok | 200K | Reasoning Tools |
| Llama-3.2-90B-Vision-Instruct llama | llama-3.2-90b-vision-instruct | $2.04/MTok | $2.04/MTok | 128K | Tools Open |
| Command A command-a | cohere-command-a | $2.50/MTok | $10/MTok | 256K | Reasoning Tools Open |
| GPT-5.4 gpt | gpt-5.4 | $2.50/MTok | $15/MTok | 1.1M | Reasoning Tools |
| Command R+ command-r | cohere-command-r-plus-08-2024 | $2.50/MTok | $10/MTok | 128K | Tools Open |
| GPT-4o gpt | gpt-4o | $2.50/MTok | $10/MTok | 128K | Tools |
| Meta-Llama-3-70B-Instruct llama | meta-llama-3-70b-instruct | $2.68/MTok | $3.54/MTok | 8.2K | Open |
| Meta-Llama-3.1-70B-Instruct llama | meta-llama-3.1-70b-instruct | $2.68/MTok | $3.54/MTok | 128K | Tools Open |
| Claude Sonnet 4.5 claude-sonnet | claude-sonnet-4-5 | $3/MTok | $15/MTok | 200K | Reasoning Tools |
| GPT-3.5 Turbo 0613 gpt | gpt-3.5-turbo-0613 | $3/MTok | $4/MTok | 16.4K | |
| Claude Opus 4.5 claude-opus | claude-opus-4-5 | $5/MTok | $25/MTok | 200K | Reasoning Tools |
| Claude Opus 4.6 claude-opus | claude-opus-4-6 | $5/MTok | $25/MTok | 200K | Reasoning Tools |
| GPT-5.5 gpt | gpt-5.5 | $5/MTok | $30/MTok | 1.1M | Reasoning Tools |
| Meta-Llama-3.1-405B-Instruct llama | meta-llama-3.1-405b-instruct | $5.33/MTok | $16/MTok | 128K | Tools Open |
| GPT-4 Turbo Vision gpt | gpt-4-turbo-vision | $10/MTok | $30/MTok | 128K | Tools |
| GPT-4 Turbo gpt | gpt-4-turbo | $10/MTok | $30/MTok | 128K | Tools |
| Claude Opus 4.1 claude-opus | claude-opus-4-1 | $15/MTok | $75/MTok | 200K | Reasoning Tools |
| o1 o | o1 | $15/MTok | $60/MTok | 200K | Reasoning Tools |
| GPT-5 Pro gpt-pro | gpt-5-pro | $15/MTok | $120/MTok | 400K | Reasoning Tools |
| o1-preview o | o1-preview | $16.50/MTok | $66/MTok | 128K | Reasoning Tools |
| GPT-5.4 Pro gpt-pro | gpt-5.4-pro | $30/MTok | $180/MTok | 1.1M | Reasoning Tools |
| GPT-4 gpt | gpt-4 | $60/MTok | $120/MTok | 8.2K | Tools |
| GPT-4 32K gpt | gpt-4-32k | $60/MTok | $120/MTok | 32.8K | Tools |