All Providers
402Models
53Families
2MMax Context
$0–$30Input Cost/MTok
$0–$180Output Cost/MTok
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Setup
Set the following environment variable to use LLM Gateway:
LLMGATEWAY_API_KEYModels (402)
| Model | Model ID | Input Cost | Output Cost | Context | Capabilities |
|---|---|---|---|---|---|
| Atria Dawn Preview (Atria) | atria/atria-dawn-preview | $0/MTok | $0/MTok | 262.1K | ReasoningTools |
| Qwen 3.7 Flash (Alibaba Cloud)qwen | alibaba/qwen3.7-flash | $0.03/MTok | $0.13/MTok | 1M | ReasoningTools |
| Llama 3.2 3B Instruct (NovitaAI)llama | novita/llama-3.2-3b-instruct | $0.03/MTok | $0.05/MTok | 32.8K | |
| GPT OSS 120B (Runware)gpt-oss | runware/gpt-oss-120b | $0.03/MTok | $0.14/MTok | 131.1K | ReasoningToolsOpen |
| GPT OSS 20B (Consensus Protocol)gpt-oss | consensusprotocol/gpt-oss-20b | $0.04/MTok | $0.19/MTok | 65.5K | ReasoningToolsOpen |
| GLM 4.6V FlashX (Z AI)glm-flash | zai/glm-4.6v-flashx | $0.04/MTok | $0.40/MTok | 128K | ReasoningTools |
| Qwen Flash (Alibaba Cloud)qwen | alibaba/qwen-flash | $0.05/MTok | $0.40/MTok | 1M | Tools |
| Qwen3 VL Flash (Alibaba Cloud) | alibaba/qwen3-vl-flash | $0.05/MTok | $0.40/MTok | 262.1K | Tools |
| DeepSeek V4 Flash (Consensus Protocol)deepseek-flash | consensusprotocol/deepseek-v4-flash | $0.05/MTok | $0.10/MTok | 1.1M | ReasoningToolsOpen |
| GPT 5 Nano (Azure)gpt-nano | azure/gpt-5-nano | $0.05/MTok | $0.40/MTok | 400K | ReasoningTools |
| GPT 5 Nano (OpenAI)gpt-nano | openai/gpt-5-nano | $0.05/MTok | $0.40/MTok | 400K | ReasoningTools |
| DeepSeek V4 Flash (Gonka24)deepseek-flash | gonka24/deepseek-v4-flash | $0.05/MTok | $0.10/MTok | 390K | ReasoningToolsOpen |
| GLM 4.7 Flash (EmberCloud)glm-flash | embercloud/glm-4.7-flash | $0.06/MTok | $0.40/MTok | 200K | ToolsOpen |
| InclusionAI Ling 3.0 Flash (NovitaAI)ling | novita/ling-3.0-flash | $0.06/MTok | $0.18/MTok | 262.1K | ReasoningTools |
| InclusionAI Ling 3.0 Flash (DeepInfra)ling | deepinfra/ling-3.0-flash | $0.06/MTok | $0.18/MTok | 262.1K | ReasoningTools |
| Seed 1.6 Flash (250715) (ByteDance)seed | bytedance/seed-1-6-flash-250715 | $0.07/MTok | $0.30/MTok | 256K | ReasoningTools |
| Qwen3 Coder 30B A3B Instruct (NovitaAI)qwen | novita/qwen3-coder-30b-a3b-instruct | $0.07/MTok | $0.27/MTok | 160K | ToolsOpen |
| Llama 3.2 11B Instruct (Inference.net)llama | inference.net/llama-3.2-11b-instruct | $0.07/MTok | $0.33/MTok | 128K | |
| Gemma 4 26B A4B IT (DeepInfra)gemma | deepinfra/gemma-4-26b-a4b-it | $0.07/MTok | $0.34/MTok | 262.1K | ReasoningToolsOpen |
| GLM 4.7 FlashX (Z AI)glm-flash | zai/glm-4.7-flashx | $0.07/MTok | $0.40/MTok | 200K | ReasoningToolsOpen |
| Hy MT2 Plus (Tencent Cloud)Hy | tencent/hy-mt2-plus | $0.07/MTok | $0.29/MTok | 8.2K | |
| DeepSeek V4 Flash (Runware)deepseek-flash | runware/deepseek-v4-flash | $0.08/MTok | $0.15/MTok | 1.0M | ReasoningToolsOpen |
| MiniMax M2.7 (Gonka24)minimax | gonka24/minimax-m2.7 | $0.08/MTok | $0.32/MTok | 204.8K | ReasoningToolsOpen |
| DeepSeek V4 Flash (DeepInfra)deepseek-flash | deepinfra/deepseek-v4-flash | $0.08/MTok | $0.18/MTok | 1M | ReasoningToolsOpen |
| Qwen 3.8 27B (Consensus Protocol) | consensusprotocol/Qwen3.8-27B | $0.08/MTok | $0.35/MTok | 32.8K | ReasoningTools |
| GLM 5.3 Flash (SCX.ai)glm-flash | scx-ai-gp/glm-5.3-flash | $0.09/MTok | $0.25/MTok | 1.0M | ReasoningToolsOpen |
| Qwen3 235B A22B Instruct 2507 (NovitaAI)qwen | novita/qwen3-235b-a22b-instruct-2507 | $0.09/MTok | $0.58/MTok | 131.1K | ToolsOpen |
| GPT OSS 20B (Groq)gpt-oss | groq/gpt-oss-20b | $0.10/MTok | $0.50/MTok | 131.1K | ReasoningToolsOpen |
| Gemini 2.5 Flash Lite (Google Vertex AI)gemini-flash-lite | google-vertex/gemini-2.5-flash-lite | $0.10/MTok | $0.40/MTok | 1.0M | Tools |
| Gemini 2.5 Flash Lite (Google AI Studio)gemini-flash-lite | google-ai-studio/gemini-2.5-flash-lite | $0.10/MTok | $0.40/MTok | 1.0M | Tools |
| GPT OSS 120B (ByteDance)gpt-oss | bytedance/gpt-oss-120b | $0.10/MTok | $0.50/MTok | 128K | ReasoningToolsOpen |
| Qwen 3.5 9B (DeepInfra)qwen | deepinfra/qwen3.5-9b | $0.10/MTok | $0.15/MTok | 262.1K | ReasoningToolsOpen |
| GLM 5.3 Flash (Consensus Protocol)glm-flash | consensusprotocol/glm-5.3-flash | $0.10/MTok | $0.25/MTok | 1.0M | ReasoningToolsOpen |
| Gemma 4 31B IT (Consensus Protocol)gemma | consensusprotocol/gemma-4-31b-it | $0.10/MTok | $0.25/MTok | 262.1K | ReasoningToolsOpen |
| GPT 4.1 Nano (Azure)gpt-nano | azure/gpt-4.1-nano | $0.10/MTok | $0.40/MTok | 1M | Tools |
| GPT 4.1 Nano (OpenAI)gpt-nano | openai/gpt-4.1-nano | $0.10/MTok | $0.40/MTok | 1M | Tools |
| Muse Spark 1.2 Contributor (Meta Contributor)muse | meta-contributor/muse-spark-1.2-contributor | $0.10/MTok | $0.20/MTok | 1.0M | ReasoningTools |
| Muse Spark 1.3 Contributor (Meta Contributor)muse | meta-contributor/muse-spark-1.3-contributor | $0.10/MTok | $0.20/MTok | 1.0M | ReasoningTools |
| GLM 4 32B (0414 128k) (Z AI)glm | zai/glm-4-32b-0414-128k | $0.10/MTok | $0.10/MTok | 128K | Tools |
| Mistral Small 3.2 (Mistral AI)mistral-small | mistral/mistral-small-2506 | $0.10/MTok | $0.30/MTok | 128K | Open |
| Ministral 3B (Mistral AI)ministral | mistral/ministral-3b-2512 | $0.10/MTok | $0.10/MTok | 131.1K | |
| Gemma 4 31B IT (Runware)gemma | runware/gemma-4-31b-it | $0.10/MTok | $0.30/MTok | 262.1K | ReasoningToolsOpen |
| Qwen3 Coder Next (EmberCloud)qwen | embercloud/qwen3-coder-next | $0.11/MTok | $0.68/MTok | 262.1K | ToolsOpen |
| MiniMax M2.1 Lightning (MiniMax)minimax | minimax/minimax-m2.1-lightning | $0.12/MTok | $0.48/MTok | 196.6K | ReasoningTools |
| GLM 4.5 Air (EmberCloud)glm-air | embercloud/glm-4.5-air | $0.13/MTok | $0.85/MTok | 131K | ToolsOpen |
| Gemma 4 26B A4B IT (NovitaAI)gemma | novita/gemma-4-26b-a4b-it | $0.13/MTok | $0.40/MTok | 262.1K | ToolsOpen |
| Gemma 4 31B IT (DeepInfra)gemma | deepinfra/gemma-4-31b-it | $0.13/MTok | $0.38/MTok | 262.1K | ReasoningToolsOpen |
| Hy3 (Tencent Cloud)Hy | tencent/hy3 | $0.13/MTok | $0.53/MTok | 262.1K | ReasoningToolsOpen |
| Llama 3.3 70B Instruct (NovitaAI)llama | novita/llama-3.3-70b-instruct | $0.14/MTok | $0.40/MTok | 131.1K | ToolsOpen |
| MiMo V2.5 (Xiaomi)mimo | xiaomi/mimo-v2.5 | $0.14/MTok | $0.28/MTok | 1M | ReasoningToolsOpen |
| DeepSeek V4 Flash (CanopyWave)deepseek-flash | canopywave/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | ReasoningToolsOpen |
| DeepSeek V4 Flash (Together AI)deepseek-flash | together-ai/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 163.8K | ReasoningToolsOpen |
| DeepSeek V4 Flash (NovitaAI)deepseek-flash | novita/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1.1M | ReasoningToolsOpen |
| Hy3 (NovitaAI)Hy | novita/hy3 | $0.14/MTok | $0.58/MTok | 262.1K | ReasoningToolsOpen |
| Gemma 4 31B IT (NovitaAI)gemma | novita/gemma-4-31b-it | $0.14/MTok | $0.40/MTok | 262.1K | ToolsOpen |
| DeepSeek V4 Flash (RanoAI)deepseek-flash | ranoai/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | ReasoningToolsOpen |
| Hy3 (DeepInfra)Hy | deepinfra/hy3 | $0.14/MTok | $0.58/MTok | 262.1K | ReasoningToolsOpen |
| DeepSeek V4 Flash (Tencent Cloud)deepseek-flash | tencent/deepseek-v4-flash | $0.14/MTok | $0.28/MTok | 1M | ReasoningToolsOpen |
| Qwen3 Next 80B A3B Thinking (Vertex AI (OpenAI compatible))qwen | vertex-openai/qwen3-next-80b-a3b-thinking | $0.15/MTok | $1.20/MTok | 131.1K | ReasoningToolsOpen |
| Qwen3 Next 80B A3B Instruct (Vertex AI (OpenAI compatible))qwen | vertex-openai/qwen3-next-80b-a3b-instruct | $0.15/MTok | $1.20/MTok | 131.1K | ToolsOpen |
| GPT OSS 120B (Groq)gpt-oss | groq/gpt-oss-120b | $0.15/MTok | $0.75/MTok | 131.1K | ReasoningToolsOpen |
| Qwen 3.8 Flash (Alibaba Cloud)qwen | alibaba/qwen3.8-flash | $0.15/MTok | $0.47/MTok | 1M | ReasoningTools |
| GPT OSS 120B (Together AI)gpt-oss | together-ai/gpt-oss-120b | $0.15/MTok | $0.60/MTok | 131.1K | ReasoningToolsOpen |
| Qwen3 Next 80B A3B Instruct (NovitaAI)qwen | novita/qwen3-next-80b-a3b-instruct | $0.15/MTok | $1.50/MTok | 131.1K | ToolsOpen |
| GLM 5.3 Flash (NovitaAI)glm-flash | novita/glm-5.3-flash | $0.15/MTok | $0.50/MTok | 1.0M | ReasoningToolsOpen |
| Qwen 3.8 Flash (NovitaAI)qwen | novita/qwen3.8-flash | $0.15/MTok | $0.47/MTok | 1M | ReasoningTools |
| Qwen3 VL 30B A3B Instruct (DeepInfra) | deepinfra/qwen3-vl-30b-a3b-instruct | $0.15/MTok | $0.60/MTok | 262.1K | Tools |
| GPT OSS 120B (Azure)gpt-oss | azure/gpt-oss-120b | $0.15/MTok | $0.60/MTok | 131.1K | ReasoningToolsOpen |
| DeepSeek V4.1 Flash (DeepSeek)deepseek-flash | deepseek/deepseek-v4.1-flash | $0.15/MTok | $0.60/MTok | 1.1M | ReasoningToolsOpen |
| GPT 4o Mini (OpenAI)gpt-mini | openai/gpt-4o-mini | $0.15/MTok | $0.60/MTok | 128K | Tools |
| GLM 5.3 Flash (Z AI)glm-flash | zai/glm-5.3-flash | $0.15/MTok | $0.50/MTok | 1.0M | ReasoningToolsOpen |
| Ministral 8B (Mistral AI)ministral | mistral/ministral-8b-2512 | $0.15/MTok | $0.15/MTok | 262.1K | |
| DeepSeek V4.1 Flash (Runware)deepseek-flash | runware/deepseek-v4.1-flash | $0.15/MTok | $0.60/MTok | 1.0M | ReasoningToolsOpen |
| GLM 5.3 Flash (Runware)glm-flash | runware/glm-5.3-flash | $0.15/MTok | $0.50/MTok | 1M | ReasoningToolsOpen |
| MiMo V2.5 (NovitaAI)mimo | novita/mimo-v2.5 | $0.17/MTok | $0.34/MTok | 1.0M | ReasoningToolsOpen |
| GPT OSS 120B (SCX.ai (Turbo))gpt-oss | scx-ai/gpt-oss-120b | $0.17/MTok | $0.55/MTok | 131.1K | ReasoningToolsOpen |
| Llama 4 Scout 17B Instruct (AWS Bedrock)llama | aws-bedrock/llama-4-scout-17b-instruct | $0.17/MTok | $0.66/MTok | 8.2K | Open |
| Llama 4 Scout 17B Instruct (NovitaAI)llama | novita/llama-4-scout-17b-instruct | $0.18/MTok | $0.59/MTok | 131.1K | Open |
| MiniMax M2 (MiniMax)minimax | minimax/minimax-m2 | $0.20/MTok | $1/MTok | 196.6K | ReasoningToolsOpen |
| MiniMax Text 01 (MiniMax)minimax | minimax/minimax-text-01 | $0.20/MTok | $1.10/MTok | 1M | ReasoningTools |
| DeepSeek V4 Flash (Alibaba Cloud)deepseek-flash | alibaba/deepseek-v4-flash | $0.20/MTok | $0.40/MTok | 1M | ReasoningToolsOpen |
| Qwen3 VL Plus (Alibaba Cloud)qwen | alibaba/qwen3-vl-plus | $0.20/MTok | $1.60/MTok | 262.1K | |
| Qwen Omni Turbo (Alibaba Cloud)qwen | alibaba/qwen-omni-turbo | $0.20/MTok | $0.80/MTok | 32.8K | |
| Qwen3 235B A22B FP8 (NovitaAI) | novita/qwen3-235b-a22b-fp8 | $0.20/MTok | $0.80/MTok | 41.0K | |
| Qwen3 VL 30B A3B Instruct (NovitaAI) | novita/qwen3-vl-30b-a3b-instruct | $0.20/MTok | $0.70/MTok | 131.1K | Tools |
| DeepSeek V4.1 Flash (DeepInfra)deepseek-flash | deepinfra/deepseek-v4.1-flash | $0.20/MTok | $0.60/MTok | 1.0M | ReasoningToolsOpen |
| Qwen3 VL 235B A22B Instruct (DeepInfra)qwen | deepinfra/qwen3-vl-235b-a22b-instruct | $0.20/MTok | $0.88/MTok | 262.1K | ToolsOpen |
| Grok 4.1 Fast Non Reasoning (Azure AI Foundry)grok | azure-ai-foundry/grok-4-1-fast-non-reasoning | $0.20/MTok | $0.50/MTok | 2M | Tools |
| Grok 4.1 Fast Reasoning (Azure AI Foundry)grok | azure-ai-foundry/grok-4-1-fast-reasoning | $0.20/MTok | $0.50/MTok | 2M | ReasoningTools |
| DeepSeek V4.1 Flash (Consensus Protocol)deepseek-flash | consensusprotocol/deepseek-v4.1-flash | $0.20/MTok | $0.60/MTok | 1.0M | ReasoningToolsOpen |
| GPT 5.6 Luna (Azure)gpt-luna | azure/gpt-5.6-luna | $0.20/MTok | $1.20/MTok | 1.1M | ReasoningTools |
| GPT 5.4 Nano (Azure)gpt-nano | azure/gpt-5.4-nano | $0.20/MTok | $1.25/MTok | 400K | ReasoningTools |
| GPT 5.6 Luna (OpenAI)gpt-luna | openai/gpt-5.6-luna | $0.20/MTok | $1.20/MTok | 1.1M | ReasoningTools |
| GPT 5.4 Nano (OpenAI)gpt-nano | openai/gpt-5.4-nano | $0.20/MTok | $1.25/MTok | 400K | ReasoningTools |
| GLM 4.5 Air (Z AI)glm-air | zai/glm-4.5-air | $0.20/MTok | $1.10/MTok | 128K | ToolsOpen |
| Ministral 14B (Mistral AI)ministral | mistral/ministral-14b-2512 | $0.20/MTok | $0.20/MTok | 262.1K | |
| Qwen3 235B A22B Instruct 2507 (Vertex AI (OpenAI compatible))qwen | vertex-openai/qwen3-235b-a22b-instruct-2507 | $0.22/MTok | $0.88/MTok | 262.1K | ToolsOpen |
| Qwen3 Coder 480B A35B Instruct (Vertex AI (OpenAI compatible))qwen | vertex-openai/qwen3-coder-480b-a35b-instruct | $0.22/MTok | $1.80/MTok | 262.1K | ToolsOpen |
| GPT 5.6 Luna (AWS Mantle)gpt-luna | aws-mantle/gpt-5.6-luna | $0.22/MTok | $1.32/MTok | 921.6K | ReasoningTools |
| DeepSeek V4 Flash (Fireworks AI)deepseek-flash | fireworks/deepseek-v4-flash | $0.22/MTok | $0.66/MTok | 1.0M | ReasoningToolsOpen |
| DeepSeek V4.1 Flash (Fireworks AI)deepseek-flash | fireworks/deepseek-v4.1-flash | $0.22/MTok | $0.66/MTok | 1.0M | ReasoningToolsOpen |
| Llama 4 Maverick 17B Instruct (AWS Bedrock)llama | aws-bedrock/llama-4-maverick-17b-instruct | $0.24/MTok | $0.97/MTok | 8.2K | Open |
| Qwen 3.6 35B A3B (NovitaAI)qwen | novita/qwen3.6-35b-a3b | $0.25/MTok | $1.49/MTok | 262.1K | ReasoningToolsOpen |
| Gemini 3.1 Flash Lite (Google Vertex AI)gemini-flash-lite | google-vertex/gemini-3.1-flash-lite | $0.25/MTok | $1.50/MTok | 1.0M | ReasoningTools |
| Qwen 3.6 Flash (Alibaba Cloud)qwen3.6 | alibaba/qwen3.6-flash | $0.25/MTok | $1.50/MTok | 1M | ReasoningTools |
| Gemini 3.1 Flash Lite (Google AI Studio)gemini-flash-lite | google-ai-studio/gemini-3.1-flash-lite | $0.25/MTok | $1.50/MTok | 1.0M | ReasoningTools |
| Seed 1.8 (251228) (ByteDance)seed | bytedance/seed-1-8-251228 | $0.25/MTok | $2/MTok | 256K | ReasoningTools |
| Seed 1.6 (250615) (ByteDance)seed | bytedance/seed-1-6-250615 | $0.25/MTok | $2/MTok | 256K | ReasoningTools |
| Seed 1.6 (250915) (ByteDance)seed | bytedance/seed-1-6-250915 | $0.25/MTok | $2/MTok | 256K | ReasoningTools |
| GPT 5.1 Codex mini (Azure)gpt-codex | azure/gpt-5.1-codex-mini | $0.25/MTok | $2/MTok | 400K | ReasoningTools |
| GPT 5 Mini (Azure)gpt-mini | azure/gpt-5-mini | $0.25/MTok | $2/MTok | 400K | ReasoningTools |
| GPT 5 Mini (OpenAI)gpt-mini | openai/gpt-5-mini | $0.25/MTok | $2/MTok | 400K | ReasoningTools |
| DeepSeek V3.2 (DeepInfra)deepseek | deepinfra/deepseek-v3.2 | $0.26/MTok | $0.38/MTok | 160K | ToolsOpen |
| DeepSeek V3.2 (NovitaAI)deepseek | novita/deepseek-v3.2 | $0.27/MTok | $0.40/MTok | 163.8K | ReasoningToolsOpen |
| MiniMax M2.1 (MiniMax)minimax | minimax/minimax-m2.1 | $0.27/MTok | $1.10/MTok | 196.6K | ReasoningToolsOpen |
| Llama 4 Maverick 17B Instruct (NovitaAI)llama | novita/llama-4-maverick-17b-instruct | $0.27/MTok | $0.85/MTok | 1.0M | Open |
| DeepSeek V3.2 (ByteDance)deepseek | bytedance/deepseek-v3.2 | $0.28/MTok | $0.42/MTok | 131.1K | ReasoningToolsOpen |
| Gemma 4 31B IT (SCX.ai (Turbo))gemma | scx-ai/gemma-4-31b-it | $0.30/MTok | $0.91/MTok | 131.1K | ToolsOpen |
| Gemini 3.5 Flash Lite (Google Vertex AI)gemini-flash-lite | google-vertex/gemini-3.5-flash-lite | $0.30/MTok | $2.50/MTok | 1.0M | ReasoningTools |
| Gemini 2.5 Flash (Google Vertex AI)gemini-flash | google-vertex/gemini-2.5-flash | $0.30/MTok | $2.50/MTok | 1.0M | ReasoningTools |
| MiniMax M2.7 (MiniMax)minimax | minimax/minimax-m2.7 | $0.30/MTok | $1.20/MTok | 204.8K | ReasoningToolsOpen |
| MiniMax M2.5 (MiniMax)minimax | minimax/minimax-m2.5 | $0.30/MTok | $1.20/MTok | 204.8K | ReasoningToolsOpen |
| Qwen3 Coder Flash (Alibaba Cloud)qwen | alibaba/qwen3-coder-flash | $0.30/MTok | $1.50/MTok | 1M | Tools |
| DeepSeek V4.1 Flash (Alibaba Cloud)deepseek-flash | alibaba/deepseek-v4.1-flash | $0.30/MTok | $1.20/MTok | 1M | ReasoningToolsOpen |
| MiniMax M3 (Together AI)minimax | together-ai/minimax-m3 | $0.30/MTok | $1.20/MTok | 524.3K | ReasoningOpen |
| DeepSeek V4.1 Flash (Together AI)deepseek-flash | together-ai/deepseek-v4.1-flash | $0.30/MTok | $1.20/MTok | 1.0M | ReasoningToolsOpen |
| Gemini 3.5 Flash Lite (Google AI Studio)gemini-flash-lite | google-ai-studio/gemini-3.5-flash-lite | $0.30/MTok | $2.50/MTok | 1.0M | ReasoningTools |
| Gemini 2.5 Flash (Google AI Studio)gemini-flash | google-ai-studio/gemini-2.5-flash | $0.30/MTok | $2.50/MTok | 1.0M | ReasoningTools |
| Qwen3 235B A22B Thinking 2507 (NovitaAI) | novita/qwen3-235b-a22b-thinking-2507 | $0.30/MTok | $3/MTok | 131.1K | Tools |
| MiniMax M2.1 (NovitaAI)minimax | novita/minimax-m2.1 | $0.30/MTok | $1.20/MTok | 204.8K | ReasoningToolsOpen |
| GLM 4.6V (NovitaAI)glm | novita/glm-4.6v | $0.30/MTok | $0.90/MTok | 131.1K | ReasoningToolsOpen |
| MiniMax M2.7 (NovitaAI)minimax | novita/minimax-m2.7 | $0.30/MTok | $1.20/MTok | 204.8K | ReasoningToolsOpen |
| MiniMax M2.5 (NovitaAI)minimax | novita/minimax-m2.5 | $0.30/MTok | $1.20/MTok | 204.8K | ReasoningToolsOpen |
| DeepSeek V4.1 Flash (NovitaAI)deepseek-flash | novita/deepseek-v4.1-flash | $0.30/MTok | $1.20/MTok | 1.0M | ReasoningToolsOpen |
| Qwen3 VL 235B A22B Instruct (NovitaAI)qwen | novita/qwen3-vl-235b-a22b-instruct | $0.30/MTok | $1.50/MTok | 131.1K | ToolsOpen |
| MiniMax M2.7 (Tencent Cloud)minimax | tencent/minimax-m2.7 | $0.30/MTok | $1.20/MTok | 200K | ReasoningToolsOpen |
| MiniMax M3 (Tencent Cloud)minimax | tencent/minimax-m3 | $0.30/MTok | $1.20/MTok | 1M | ReasoningToolsOpen |
| GLM 4.6V (Z AI)glm | zai/glm-4.6v | $0.30/MTok | $0.90/MTok | 128K | ReasoningToolsOpen |
| Codestral (Mistral AI)codestral | mistral/codestral-2508 | $0.30/MTok | $0.90/MTok | 256K | |
| GPT OSS 120B (Cerebras)gpt-oss | cerebras/gpt-oss-120b | $0.35/MTok | $0.75/MTok | 131.1K | ReasoningToolsOpen |
| Qwen3 32B (SCX.ai (Turbo))qwen | scx-ai/qwen3-32b | $0.36/MTok | $0.87/MTok | 32.8K | ReasoningToolsOpen |
| Qwen 3.6 35B A3B (Alibaba Cloud)qwen | alibaba/qwen3.6-35b-a3b | $0.38/MTok | $2.25/MTok | 262.1K | ReasoningToolsOpen |
| GLM 4.7 (EmberCloud)glm | embercloud/glm-4.7 | $0.38/MTok | $1.98/MTok | 200K | ReasoningToolsOpen |
| Qwen3 Coder 480B A35B Instruct (NovitaAI)qwen | novita/qwen3-coder-480b-a35b-instruct | $0.38/MTok | $1.55/MTok | 262.1K | ToolsOpen |
| Qwen Plus (Alibaba Cloud)qwen | alibaba/qwen-plus | $0.40/MTok | $1.20/MTok | 131.1K | Tools |
| Qwen 3.7 Plus (Alibaba Cloud)qwen | alibaba/qwen3.7-plus | $0.40/MTok | $1.60/MTok | 1M | ReasoningTools |
| Qwen Plus Latest (Alibaba Cloud)qwen | alibaba/qwen-plus-latest | $0.40/MTok | $1.20/MTok | 1M | Tools |
| MiMo V2.5 (DeepInfra)mimo | deepinfra/mimo-v2.5 | $0.40/MTok | $2/MTok | 262.1K | ReasoningToolsOpen |
| GPT 4.1 Mini (Azure)gpt-mini | azure/gpt-4.1-mini | $0.40/MTok | $1.60/MTok | 1M | Tools |
| GPT 4.1 Mini (OpenAI)gpt-mini | openai/gpt-4.1-mini | $0.40/MTok | $1.60/MTok | 1M | Tools |
| Devstral 2 (Mistral AI)devstral | mistral/devstral-2512 | $0.40/MTok | $2/MTok | 262.1K | Open |
| Kimi K2.5 (EmberCloud)kimi-k2 | embercloud/kimi-k2.5 | $0.41/MTok | $1.98/MTok | 262.1K | ToolsOpen |
| Qwen 3.8 27B (NovitaAI)qwen | novita/qwen3.8-27b | $0.42/MTok | $3/MTok | 1M | ReasoningToolsOpen |
| ERNIE 4.5 VL 424B A47B (NovitaAI)ernie | novita/ernie-4.5-vl-424b-a47b | $0.42/MTok | $1.25/MTok | 123K | Reasoning |
| MiMo V2.5 Pro (Xiaomi)mimo | xiaomi/mimo-v2.5-pro | $0.43/MTok | $0.87/MTok | 1M | ReasoningToolsOpen |
| DeepSeek V4 Pro (DeepSeek)deepseek-thinking | deepseek/deepseek-v4-pro | $0.43/MTok | $0.87/MTok | 1.1M | ReasoningToolsOpen |
| DeepSeek V4 Pro (Tencent Cloud)deepseek-thinking | tencent/deepseek-v4-pro | $0.43/MTok | $0.87/MTok | 1M | ReasoningToolsOpen |
| MiMo V2.5 Pro (Tencent Cloud)mimo | tencent/mimo-v2.5-pro | $0.43/MTok | $0.87/MTok | 1M | ReasoningToolsOpen |
| DeepSeek V4 Flash (Baidu)deepseek-flash | baidu/deepseek-v4-flash | $0.44/MTok | $1.32/MTok | 1.0M | ReasoningToolsOpen |
| DeepSeek V4 Flash (ByteDance)deepseek-flash | bytedance/deepseek-v4-flash | $0.44/MTok | $1.32/MTok | 1.0M | ReasoningToolsOpen |
| GLM 4.7 (Together AI)glm | together-ai/glm-4.7 | $0.45/MTok | $2/MTok | 202.8K | ReasoningOpen |
| MiniMax M2.7 (SCX.ai (Turbo))minimax | scx-ai/minimax-m2.7 | $0.48/MTok | $1.79/MTok | 196.6K | ReasoningToolsOpen |
| Gemini 3 Flash (Preview) (Google Vertex AI)gemini-flash | google-vertex/gemini-3-flash-preview | $0.50/MTok | $3/MTok | 1.0M | ReasoningTools |
| Qwen 3.6 Plus (Alibaba Cloud)qwen | alibaba/qwen3.6-plus | $0.50/MTok | $3/MTok | 1M | ReasoningTools |
| Gemini 3 Flash (Preview) (Google AI Studio)gemini-flash | google-ai-studio/gemini-3-flash-preview | $0.50/MTok | $3/MTok | 1.0M | ReasoningTools |
| Nemotron 3 Ultra 550B (DeepInfra)nemotron | deepinfra/nemotron-3-ultra-550b | $0.50/MTok | $2.20/MTok | 262.1K | Tools |
| GPT 3.5 Turbo (Azure)gpt | azure/gpt-3.5-turbo | $0.50/MTok | $1.50/MTok | 16.4K | Tools |
| GPT 3.5 Turbo (OpenAI)gpt | openai/gpt-3.5-turbo | $0.50/MTok | $1.50/MTok | 16.4K | Tools |
| Mistral Large 3 (Mistral AI)mistral-large | mistral/mistral-large-2512 | $0.50/MTok | $1.50/MTok | 262.1K | Open |
| Qwen Coder Plus (Alibaba Cloud)qwen | alibaba/qwen-coder-plus | $0.50/MTok | $1.00/MTok | 131.1K | Tools |
| Llama 3 70B Instruct (NovitaAI)llama | novita/llama-3-70b-instruct | $0.51/MTok | $0.74/MTok | 8.2K | |
| MiMo V2.5 Pro (NovitaAI)mimo | novita/mimo-v2.5-pro | $0.52/MTok | $1.04/MTok | 1.0M | ReasoningToolsOpen |
| Llama 4 Maverick 17B Instruct (SCX.ai (Turbo))llama | scx-ai/llama-4-maverick-17b-instruct | $0.53/MTok | $1.62/MTok | 131.1K | ToolsOpen |
| GLM 4.6 (NovitaAI)glm | novita/glm-4.6 | $0.55/MTok | $2.20/MTok | 204.8K | ReasoningToolsOpen |
| DeepSeek V3.2 (Vertex AI (OpenAI compatible))deepseek | vertex-openai/deepseek-v3.2 | $0.56/MTok | $1.68/MTok | 163.8K | ToolsOpen |
| Kimi K2 (NovitaAI)kimi-k2 | novita/kimi-k2 | $0.57/MTok | $2.30/MTok | 131.1K | Tools |
| GLM 5 (Alibaba Cloud)glm | alibaba/glm-5 | $0.57/MTok | $2.58/MTok | 202.8K | ReasoningToolsOpen |
| Kimi K2.5 (Alibaba Cloud)kimi-k2 | alibaba/kimi-k2.5 | $0.57/MTok | $3.01/MTok | 262.1K | ReasoningToolsOpen |
| GLM 4.7 (Vertex AI (OpenAI compatible))glm | vertex-openai/glm-4.7 | $0.60/MTok | $2.20/MTok | 202.8K | ReasoningToolsOpen |
| Kimi K2 Thinking (Vertex AI (OpenAI compatible))kimi-thinking | vertex-openai/kimi-k2-thinking | $0.60/MTok | $2.50/MTok | 262.1K | ReasoningToolsOpen |
| GLM 4.5 (EmberCloud)glm | embercloud/glm-4.5 | $0.60/MTok | $2.20/MTok | 131K | ToolsOpen |
| MiniMax M2.7 Highspeed (MiniMax)minimax | minimax/minimax-m2.7-highspeed | $0.60/MTok | $2.40/MTok | 204.8K | ReasoningToolsOpen |
| MiniMax M3 (MiniMax)minimax | minimax/minimax-m3 | $0.60/MTok | $2.40/MTok | 512K | ReasoningToolsOpen |
| MiniMax M2.5 Highspeed (MiniMax)minimax | minimax/minimax-m2.5-highspeed | $0.60/MTok | $2.40/MTok | 204.8K | ReasoningToolsOpen |
| Qwen 3.5 397B A17B (Alibaba Cloud)qwen3.5 | alibaba/qwen35-397b-a17b | $0.60/MTok | $3.60/MTok | 262.1K | ReasoningTools |
| GLM 4.7 (ByteDance)glm | bytedance/glm-4.7 | $0.60/MTok | $2.20/MTok | 200K | ReasoningToolsOpen |
| GLM 4.7 (NovitaAI)glm | novita/glm-4.7 | $0.60/MTok | $2.20/MTok | 204.8K | ReasoningToolsOpen |
| Qwen 3.5 397B A17B (NovitaAI)qwen3.5 | novita/qwen35-397b-a17b | $0.60/MTok | $3.60/MTok | 262.1K | ReasoningTools |
| GLM 4.5V (NovitaAI)glm | novita/glm-4.5v | $0.60/MTok | $1.80/MTok | 65.5K | ReasoningToolsOpen |
| Kimi K2.5 (Moonshot AI)kimi-k2 | moonshot/kimi-k2.5 | $0.60/MTok | $3/MTok | 262.1K | ReasoningToolsOpen |
| GLM 4.7 (Z AI)glm | zai/glm-4.7 | $0.60/MTok | $2.20/MTok | 200K | ReasoningToolsOpen |
| GLM 4.6 (Z AI)glm | zai/glm-4.6 | $0.60/MTok | $2.20/MTok | 200K | ReasoningToolsOpen |
| GLM 4.5 (Z AI)glm | zai/glm-4.5 | $0.60/MTok | $2.20/MTok | 128K | ReasoningToolsOpen |
| GLM 4.5V (Z AI)glm | zai/glm-4.5v | $0.60/MTok | $1.80/MTok | 128K | ReasoningToolsOpen |
| Qwen3 235B A22B Instruct 2507 (Cerebras)qwen | cerebras/qwen3-235b-a22b-instruct-2507 | $0.60/MTok | $1.20/MTok | 262K | ToolsOpen |
| Kimi K2.6 (Runware)kimi-k2 | runware/kimi-k2.6 | $0.60/MTok | $3.05/MTok | 262.1K | ReasoningToolsOpen |
| GLM 5 (EmberCloud)glm | embercloud/glm-5 | $0.72/MTok | $2.30/MTok | 203K | ReasoningToolsOpen |
| Llama 3.1 70B Instruct (AWS Bedrock)llama | aws-bedrock/llama-3.1-70b-instruct | $0.72/MTok | $0.72/MTok | 128K | |
| Gemini 3.6 Flash (Google Vertex AI)gemini-flash | google-vertex/gemini-3.6-flash | $0.75/MTok | $3.75/MTok | 1.0M | ReasoningTools |
| Gemini 3.8 Flash (Google Vertex AI)gemini | google-vertex/gemini-3.8-flash | $0.75/MTok | $3.75/MTok | 1.0M | ReasoningTools |
| Gemini 3.7 Flash (Google Vertex AI)gemini-flash | google-vertex/gemini-3.7-flash | $0.75/MTok | $3.75/MTok | 1.0M | ReasoningTools |
| Gemini 3.6 Flash (Google AI Studio)gemini-flash | google-ai-studio/gemini-3.6-flash | $0.75/MTok | $3.75/MTok | 1.0M | ReasoningTools |
| Gemini 3.8 Flash (Google AI Studio)gemini-flash | google-ai-studio/gemini-3.8-flash | $0.75/MTok | $3.75/MTok | 1.0M | ReasoningTools |
| Gemini 3.7 Flash (Google AI Studio)gemini-flash | google-ai-studio/gemini-3.7-flash | $0.75/MTok | $3.75/MTok | 1.0M | ReasoningTools |
| GPT 5.4 Mini (Azure)gpt-mini | azure/gpt-5.4-mini | $0.75/MTok | $4.50/MTok | 400K | ReasoningTools |
| GPT 5.4 Mini (OpenAI)gpt-mini | openai/gpt-5.4-mini | $0.75/MTok | $4.50/MTok | 400K | ReasoningTools |
| Kimi K2.6 (NovitaAI)kimi-k2 | novita/kimi-k2.6 | $0.80/MTok | $3.40/MTok | 262.1K | ReasoningToolsOpen |
| GLM 5.2 (Runware)glm | runware/glm-5.2 | $0.80/MTok | $2.55/MTok | 1.0M | ReasoningToolsOpen |
| Hy4 Preview (Tencent Cloud)Hy | tencent/hy4-preview | $0.83/MTok | $2.50/MTok | 1M | ReasoningToolsOpen |
| Qwen3 Max (NovitaAI)qwen | novita/qwen3-max | $0.84/MTok | $3.38/MTok | 262.1K | Tools |
| Llama 3.3 70B Instruct (Cerebras)llama | cerebras/llama-3.3-70b-instruct | $0.85/MTok | $1.20/MTok | 128K | ToolsOpen |
| Kimi K2.6 (Tencent Cloud)kimi-k2 | tencent/kimi-k2.6 | $0.86/MTok | $3.57/MTok | 262.1K | ReasoningToolsOpen |
| GLM 5.2 (SCX.ai)glm | scx-ai-gp/glm-5.2 | $0.88/MTok | $2.55/MTok | 1M | ReasoningToolsOpen |
| GLM 5.1 (EmberCloud)glm | embercloud/glm-5.1 | $0.93/MTok | $2.93/MTok | 203K | ReasoningToolsOpen |
| Kimi K2.6 (Baidu)kimi-k2 | baidu/kimi-k2.6 | $0.95/MTok | $4/MTok | 262.1K | ReasoningToolsOpen |
| Kimi K2.7 Code (SCX.ai)kimi-k2 | scx-ai-gp/kimi-k2.7-code | $0.95/MTok | $4/MTok | 262.1K | ReasoningToolsOpen |
| Kimi K2.6 (CanopyWave)kimi-k2 | canopywave/kimi-k2.6 | $0.95/MTok | $4/MTok | 262.1K | ReasoningToolsOpen |
| Kimi K2.7 Code (NovitaAI)kimi-k2 | novita/kimi-k2.7-code | $0.95/MTok | $4/MTok | 262.1K | ReasoningToolsOpen |
| Kimi K2.6 (Moonshot AI)kimi-k2 | moonshot/kimi-k2.6 | $0.95/MTok | $4/MTok | 262.1K | ReasoningToolsOpen |
| Kimi K2.7 Code (Moonshot AI)kimi-k2 | moonshot/kimi-k2.7-code | $0.95/MTok | $4/MTok | 262.1K | ReasoningToolsOpen |
| Kimi K2.7 Code (Tencent Cloud)kimi-k2 | tencent/kimi-k2.7-code | $0.95/MTok | $4/MTok | 262.1K | ReasoningToolsOpen |
| DeepSeek V4 Pro (Runware)deepseek-thinking | runware/deepseek-v4-pro | $0.96/MTok | $1.92/MTok | 1.0M | ReasoningToolsOpen |
| Qwen3 VL 235B A22B Thinking (NovitaAI)qwen | novita/qwen3-vl-235b-a22b-thinking | $0.98/MTok | $3.95/MTok | 131.1K | ReasoningOpen |
| Gemma 4 31B IT (Cerebras)gemma | cerebras/gemma-4-31b-it | $0.99/MTok | $1.49/MTok | 131.1K | ReasoningToolsOpen |
| GLM 5 (Vertex AI (OpenAI compatible))glm | vertex-openai/glm-5 | $1/MTok | $3.20/MTok | 202.8K | ReasoningToolsOpen |
| GLM 5 (Baidu)glm | baidu/glm-5 | $1/MTok | $3.20/MTok | 202.8K | ReasoningToolsOpen |
| Claude Haiku 4.5 (Vertex AI (Anthropic))claude-haiku | vertex-anthropic/claude-haiku-4-5 | $1/MTok | $5/MTok | 200K | ReasoningTools |
| Qwen3 Coder Plus (Alibaba Cloud)qwen | alibaba/qwen3-coder-plus | $1/MTok | $5/MTok | 1M | Tools |
| Claude Haiku 4.5 (2025 10 01) (AWS Bedrock)claude-haiku | aws-bedrock/claude-haiku-4-5-20251001 | $1/MTok | $5/MTok | 200K | ReasoningTools |
| Claude Haiku 4.5 (AWS Bedrock)claude-haiku | aws-bedrock/claude-haiku-4-5 | $1/MTok | $5/MTok | 200K | ReasoningTools |
| Claude Haiku 4.5 (2025 10 01) (Anthropic)claude-haiku | anthropic/claude-haiku-4-5-20251001 | $1/MTok | $5/MTok | 200K | ReasoningTools |
| Claude Haiku 4.5 (Anthropic)claude-haiku | anthropic/claude-haiku-4-5 | $1/MTok | $5/MTok | 200K | ReasoningTools |
| GLM 5 (NovitaAI)glm | novita/glm-5 | $1/MTok | $3.20/MTok | 202.8K | ReasoningToolsOpen |
| MiMo V2.5 Pro (DeepInfra)mimo | deepinfra/mimo-v2.5-pro | $1/MTok | $3/MTok | 1.0M | ReasoningOpen |
| GLM 5 (Tencent Cloud)glm | tencent/glm-5 | $1/MTok | $3.20/MTok | 200K | ReasoningToolsOpen |
| Grok Build 0.1 (xAI)grok-build | xai/grok-build-0-1 | $1/MTok | $2/MTok | 256K | ReasoningTools |
| GLM 5 (Z AI)glm | zai/glm-5 | $1/MTok | $3.20/MTok | 202.8K | ReasoningToolsOpen |
| Sonar (Perplexity)sonar | perplexity/sonar | $1/MTok | $1/MTok | 130K | |
| GLM 5.1 (DeepInfra)glm | deepinfra/glm-5.1 | $1.05/MTok | $3.50/MTok | 198K | ReasoningToolsOpen |
| o4 Mini (Azure)o-mini | azure/o4-mini | $1.10/MTok | $4.40/MTok | 200K | ReasoningTools |
| o3 Mini (Azure)o-mini | azure/o3-mini | $1.10/MTok | $4.40/MTok | 200K | |
| o4 Mini (OpenAI)o-mini | openai/o4-mini | $1.10/MTok | $4.40/MTok | 200K | ReasoningTools |
| o3 Mini (OpenAI)o-mini | openai/o3-mini | $1.10/MTok | $4.40/MTok | 200K | |
| GLM 4.5 AirX (Z AI)glm | zai/glm-4.5-airx | $1.10/MTok | $4.50/MTok | 128K | Tools |
| Qwen3 Max (Alibaba Cloud)qwen | alibaba/qwen3-max | $1.20/MTok | $6/MTok | 256K | ReasoningTools |
| GLM 5 Turbo (Tencent Cloud)glm | tencent/glm-5-turbo | $1.20/MTok | $4/MTok | 200K | ReasoningTools |
| GLM 5V Turbo (Tencent Cloud)glm | tencent/glm-5v-turbo | $1.20/MTok | $4/MTok | 200K | ReasoningTools |
| GLM 5.3 (Runware)glm | runware/glm-5.3 | $1.20/MTok | $4/MTok | 1M | ReasoningToolsOpen |
| Grok 4.20 Non Reasoning (Vertex AI (OpenAI compatible))grok | vertex-openai/grok-4-20-non-reasoning | $1.25/MTok | $2.50/MTok | 2M | Tools |
| Grok 4.20 Reasoning (Vertex AI (OpenAI compatible))grok | vertex-openai/grok-4-20-reasoning | $1.25/MTok | $2.50/MTok | 2M | ReasoningTools |
| Gemini 2.5 Pro (Google Vertex AI)gemini-pro | google-vertex/gemini-2.5-pro | $1.25/MTok | $10/MTok | 1.0M | ReasoningTools |
| Grok 4.3 (AWS Bedrock)grok | aws-bedrock/grok-4-3 | $1.25/MTok | $2.50/MTok | 1M | ReasoningTools |
| Muse Spark 1.3 (Meta)muse | meta/muse-spark-1.3 | $1.25/MTok | $4.25/MTok | 1.0M | ReasoningTools |
| Muse Spark 1.2 (Meta)muse | meta/muse-spark-1.2 | $1.25/MTok | $4.25/MTok | 1.0M | ReasoningTools |
| Muse Spark 1.1 (Meta)muse | meta/muse-spark-1.1 | $1.25/MTok | $4.25/MTok | 1.0M | ReasoningTools |
| Gemini 2.5 Pro (Google AI Studio)gemini-pro | google-ai-studio/gemini-2.5-pro | $1.25/MTok | $10/MTok | 1.0M | ReasoningTools |
| Qwen 3.7 Max (NovitaAI)qwen | novita/qwen3.7-max | $1.25/MTok | $3.75/MTok | 1M | ReasoningTools |
| Grok 4.3 (Azure AI Foundry)grok | azure-ai-foundry/grok-4-3 | $1.25/MTok | $2.50/MTok | 20K | ReasoningTools |
| GPT 5.1 Codex (Azure)gpt-codex | azure/gpt-5.1-codex | $1.25/MTok | $10/MTok | 400K | ReasoningTools |
| GPT 5.1 (Azure)gpt | azure/gpt-5.1 | $1.25/MTok | $10/MTok | 400K | ReasoningTools |
| GPT 5 (Azure)gpt | azure/gpt-5 | $1.25/MTok | $10/MTok | 400K | ReasoningTools |
| GPT 4o Mini Transcribe (OpenAI)gpt | openai/gpt-4o-mini-transcribe | $1.25/MTok | $5/MTok | 16K | |
| GPT 5.1 (OpenAI)gpt | openai/gpt-5.1 | $1.25/MTok | $10/MTok | 400K | ReasoningTools |
| GPT 5 (OpenAI)gpt | openai/gpt-5 | $1.25/MTok | $10/MTok | 400K | ReasoningTools |
| Grok 4.3 (xAI)grok | xai/grok-4-3 | $1.25/MTok | $2.50/MTok | 1M | ReasoningTools |
| GLM 5.2 (EmberCloud)glm | embercloud/glm-5.2 | $1.26/MTok | $3.96/MTok | 203K | ReasoningToolsOpen |
| Qwen 3.6 Max Preview (Alibaba Cloud)qwen | alibaba/qwen3.6-max-preview | $1.30/MTok | $7.80/MTok | 262.1K | ReasoningTools |
| DeepSeek V4 Pro (DeepInfra)deepseek-thinking | deepinfra/deepseek-v4-pro | $1.30/MTok | $2.60/MTok | 1.0M | ReasoningToolsOpen |
| DeepSeek V4 Pro (Baidu)deepseek-thinking | baidu/deepseek-v4-pro | $1.32/MTok | $3.96/MTok | 1.0M | ReasoningToolsOpen |
| DeepSeek V4 Pro (Together AI)deepseek-thinking | together-ai/deepseek-v4-pro | $1.32/MTok | $3.96/MTok | 1.0M | ReasoningToolsOpen |
| DeepSeek V4 Pro (ByteDance)deepseek-thinking | bytedance/deepseek-v4-pro | $1.32/MTok | $3.96/MTok | 1.0M | ReasoningToolsOpen |
| DeepSeek V4 Pro (Fireworks AI)deepseek-thinking | fireworks/deepseek-v4-pro | $1.32/MTok | $3.96/MTok | 1.0M | ReasoningToolsOpen |
| GLM 5.1 (NovitaAI)glm | novita/glm-5.1 | $1.38/MTok | $4.40/MTok | 204.8K | ReasoningToolsOpen |
| GLM 5.2 (Baidu)glm | baidu/glm-5.2 | $1.40/MTok | $4.40/MTok | 1.0M | ReasoningToolsOpen |
| GLM 5.1 (Baidu)glm | baidu/glm-5.1 | $1.40/MTok | $4.40/MTok | 202.8K | ReasoningToolsOpen |
| GLM 5.3 (Baidu)glm | baidu/glm-5.3 | $1.40/MTok | $4.40/MTok | 1.0M | ReasoningToolsOpen |
| GLM 5.2 (Alibaba Cloud)glm | alibaba/glm-5.2 | $1.40/MTok | $4.40/MTok | 1M | ReasoningToolsOpen |
| GLM 5.3 (Alibaba Cloud)glm | alibaba/glm-5.3 | $1.40/MTok | $4.40/MTok | 1.0M | ReasoningToolsOpen |
| GLM 5.3 (SCX.ai)glm | scx-ai-gp/glm-5.3 | $1.40/MTok | $4.40/MTok | 1M | ReasoningToolsOpen |
| GLM 5.2 (CanopyWave)glm | canopywave/glm-5.2 | $1.40/MTok | $4.40/MTok | 200K | ReasoningToolsOpen |
| GLM 5.2 (ByteDance)glm | bytedance/glm-5.2 | $1.40/MTok | $4.40/MTok | 1.0M | ReasoningToolsOpen |
| GLM 5.2 (NovitaAI)glm | novita/glm-5.2 | $1.40/MTok | $4.40/MTok | 1.0M | ReasoningToolsOpen |
| GLM 5.3 (NovitaAI)glm | novita/glm-5.3 | $1.40/MTok | $4.40/MTok | 1.0M | ReasoningToolsOpen |
| GLM 5.2 (Tencent Cloud)glm | tencent/glm-5.2 | $1.40/MTok | $4.40/MTok | 1M | ReasoningToolsOpen |
| GLM 5.1 (Tencent Cloud)glm | tencent/glm-5.1 | $1.40/MTok | $4.40/MTok | 200K | ReasoningToolsOpen |
| GLM 5.2 (Z AI)glm | zai/glm-5.2 | $1.40/MTok | $4.40/MTok | 1M | ReasoningToolsOpen |
| GLM 5.1 (Z AI)glm | zai/glm-5.1 | $1.40/MTok | $4.40/MTok | 200K | ReasoningToolsOpen |
| GLM 5.3 (Z AI)glm | zai/glm-5.3 | $1.40/MTok | $4.40/MTok | 1M | ReasoningToolsOpen |
| Gemini 3.5 Flash (Google Vertex AI)gemini-flash | google-vertex/gemini-3.5-flash | $1.50/MTok | $9/MTok | 1.0M | ReasoningTools |
| Gemini 3.5 Flash (Google AI Studio)gemini-flash | google-ai-studio/gemini-3.5-flash | $1.50/MTok | $9/MTok | 1.0M | ReasoningTools |
| Qwen Max (Alibaba Cloud)qwen | alibaba/qwen-max | $1.60/MTok | $6.40/MTok | 32.8K | Tools |
| DeepSeek V4 Pro (CanopyWave)deepseek-thinking | canopywave/deepseek-v4-pro | $1.74/MTok | $3.48/MTok | 1M | ReasoningToolsOpen |
| GPT 5.2 Codex (Azure)gpt-codex | azure/gpt-5.2-codex | $1.75/MTok | $14/MTok | 400K | ReasoningTools |
| GPT 5.3 Codex (Azure)gpt-codex | azure/gpt-5.3-codex | $1.75/MTok | $14/MTok | 400K | ReasoningTools |
| GPT 5.2 (Azure)gpt | azure/gpt-5.2 | $1.75/MTok | $14/MTok | 400K | ReasoningTools |
| GPT 5.3 Codex (OpenAI)gpt-codex | openai/gpt-5.3-codex | $1.75/MTok | $14/MTok | 400K | ReasoningTools |
| GPT 5.2 (OpenAI)gpt | openai/gpt-5.2 | $1.75/MTok | $14/MTok | 400K | ReasoningTools |
| Kimi K2.7 Code Highspeed (Moonshot AI)kimi-k2 | moonshot/kimi-k2.7-code-highspeed | $1.90/MTok | $8/MTok | 262.1K | ReasoningToolsOpen |
| Kimi K2.7 Code Highspeed (Tencent Cloud)kimi-k2 | tencent/kimi-k2.7-code-highspeed | $1.90/MTok | $8/MTok | 262.1K | ReasoningToolsOpen |
| Grok 4.6 (Vertex AI (OpenAI compatible))grok | vertex-openai/grok-4-6 | $2/MTok | $6/MTok | 500K | ReasoningTools |
| Gemini 3.1 Pro (Preview) (Google Vertex AI)gemini-pro | google-vertex/gemini-3.1-pro-preview | $2/MTok | $12/MTok | 1.0M | ReasoningTools |
| Gemini 3.1 Pro (Preview) (Quartz)gemini-pro | quartz/gemini-3.1-pro-preview | $2/MTok | $12/MTok | 1.0M | ReasoningTools |
| Claude Sonnet 5 (Vertex AI (Anthropic))claude-sonnet | vertex-anthropic/claude-sonnet-5 | $2/MTok | $10/MTok | 1M | ReasoningTools |
| Qwen 3.8 Max (Alibaba Cloud)qwen | alibaba/qwen3.8-max | $2/MTok | $6/MTok | 1M | ReasoningTools |
| Qwen 3.8 Max (SCX.ai)qwen | scx-ai-gp/qwen3.8-max | $2/MTok | $6/MTok | 1M | ReasoningTools |
| Grok 4.6 (AWS Bedrock)grok | aws-bedrock/grok-4-6 | $2/MTok | $6/MTok | 500K | ReasoningTools |
| Claude Sonnet 5 (AWS Bedrock)claude-sonnet | aws-bedrock/claude-sonnet-5 | $2/MTok | $10/MTok | 1M | ReasoningTools |
| Claude Sonnet 5 (Anthropic)claude-sonnet | anthropic/claude-sonnet-5 | $2/MTok | $10/MTok | 1M | ReasoningTools |
| Gemini Pro Latest (Google AI Studio)gemini-pro | google-ai-studio/gemini-pro-latest | $2/MTok | $12/MTok | 1.0M | ReasoningTools |
| Gemini 3.1 Pro (Preview) (Google AI Studio)gemini-pro | google-ai-studio/gemini-3.1-pro-preview | $2/MTok | $12/MTok | 1.0M | ReasoningTools |
| Qwen 3.8 Max (NovitaAI)qwen | novita/qwen3.8-max | $2/MTok | $6/MTok | 1M | ReasoningTools |
| Fugu Max (Sakana AI)fugu | sakana/fugu-max | $2/MTok | $6/MTok | 1M | ReasoningTools |
| GPT 4.1 (Azure)gpt | azure/gpt-4.1 | $2/MTok | $8/MTok | 1M | Tools |
| GPT 5.6 Terra (Azure)gpt-terra | azure/gpt-5.6-terra | $2/MTok | $12/MTok | 1.1M | ReasoningTools |
| o3 (Azure)o | azure/o3 | $2/MTok | $8/MTok | 200K | |
| GPT 4.1 (OpenAI)gpt | openai/gpt-4.1 | $2/MTok | $8/MTok | 1M | Tools |
| GPT 5.6 Terra (OpenAI)gpt-terra | openai/gpt-5.6-terra | $2/MTok | $12/MTok | 1.1M | ReasoningTools |
| o3 (OpenAI)o | openai/o3 | $2/MTok | $8/MTok | 200K | |
| Grok 4.5 (xAI)grok | xai/grok-4-5 | $2/MTok | $6/MTok | 500K | ReasoningTools |
| Grok 4.20 Beta Reasoning (0309) (xAI)grok | xai/grok-4-20-beta-0309-reasoning | $2/MTok | $6/MTok | 2M | ReasoningTools |
| Grok 4.6 (xAI)grok | xai/grok-4-6 | $2/MTok | $6/MTok | 500K | ReasoningTools |
| Grok 4.20 Beta Non Reasoning (0309) (xAI)grok | xai/grok-4-20-beta-0309-non-reasoning | $2/MTok | $6/MTok | 2M | Tools |
| Claude Sonnet 5 (Azure Anthropic)claude-sonnet | azure-anthropic/claude-sonnet-5 | $2/MTok | $10/MTok | 1M | ReasoningTools |
| Sonar Reasoning Pro (Perplexity)sonar-reasoning | perplexity/sonar-reasoning-pro | $2/MTok | $8/MTok | 128K | |
| GPT 5.6 Terra (AWS Mantle)gpt-terra | aws-mantle/gpt-5.6-terra | $2.20/MTok | $13.20/MTok | 921.6K | ReasoningTools |
| GLM 5.2 Turbo (SCX.ai)glm | scx-ai-gp/glm-5.2-fast | $2.20/MTok | $6.50/MTok | 1M | ReasoningToolsOpen |
| GLM 4.5 X (Z AI)glm | zai/glm-4.5-x | $2.20/MTok | $8.90/MTok | 128K | ReasoningTools |
| GLM 4.7 (Cerebras)glm | cerebras/glm-4.7 | $2.25/MTok | $2.75/MTok | 200K | ReasoningToolsOpen |
| DeepSeek V4 Pro (Alibaba Cloud)deepseek-thinking | alibaba/deepseek-v4-pro | $2.40/MTok | $4.80/MTok | 1M | ReasoningToolsOpen |
| Qwen 3.7 Max (Alibaba Cloud)qwen | alibaba/qwen3.7-max | $2.50/MTok | $7.50/MTok | 1M | ReasoningTools |
| GPT 5.4 (Azure)gpt | azure/gpt-5.4 | $2.50/MTok | $15/MTok | 1.1M | ReasoningTools |
| GPT 4o (Azure)gpt | azure/gpt-4o | $2.50/MTok | $10/MTok | 128K | Tools |
| GPT 5.4 (OpenAI)gpt | openai/gpt-5.4 | $2.50/MTok | $15/MTok | 1.1M | ReasoningTools |
| GPT 4o Transcribe (OpenAI)gpt | openai/gpt-4o-transcribe | $2.50/MTok | $10/MTok | 16K | |
| GPT 4o (OpenAI)gpt | openai/gpt-4o | $2.50/MTok | $10/MTok | 128K | Tools |
| Claude Sonnet 4.6 (Vertex AI (Anthropic))claude-sonnet | vertex-anthropic/claude-sonnet-4-6 | $3/MTok | $15/MTok | 1M | ReasoningTools |
| Claude Sonnet 4.5 (Vertex AI (Anthropic))claude-sonnet | vertex-anthropic/claude-sonnet-4-5 | $3/MTok | $15/MTok | 200K | ReasoningTools |
| Kimi K3 (Alibaba Cloud)kimi-k3 | alibaba/kimi-k3 | $3/MTok | $15/MTok | 1.0M | ReasoningToolsOpen |
| Kimi K3 (Runpod)kimi-k3 | runpod/kimi-k3 | $3/MTok | $15/MTok | 1.0M | ReasoningToolsOpen |
| Claude Sonnet 4.6 (AWS Bedrock)claude-sonnet | aws-bedrock/claude-sonnet-4-6 | $3/MTok | $15/MTok | 1M | ReasoningTools |
| Claude Sonnet 4.5 (2025 09 29) (AWS Bedrock)claude-sonnet | aws-bedrock/claude-sonnet-4-5-20250929 | $3/MTok | $15/MTok | 200K | ReasoningTools |
| Claude Sonnet 4.5 (AWS Bedrock)claude-sonnet | aws-bedrock/claude-sonnet-4-5 | $3/MTok | $15/MTok | 200K | ReasoningTools |
| Claude Sonnet 4.6 (Anthropic)claude-sonnet | anthropic/claude-sonnet-4-6 | $3/MTok | $15/MTok | 1M | ReasoningTools |
| Claude Sonnet 4.5 (2025 09 29) (Anthropic)claude-sonnet | anthropic/claude-sonnet-4-5-20250929 | $3/MTok | $15/MTok | 200K | ReasoningTools |
| Claude Sonnet 4.5 (Anthropic)claude-sonnet | anthropic/claude-sonnet-4-5 | $3/MTok | $15/MTok | 200K | ReasoningTools |
| Kimi K3 (CanopyWave)kimi-k3 | canopywave/kimi-k3 | $3/MTok | $15/MTok | 1.0M | ReasoningToolsOpen |
| Kimi K3 (Together AI)kimi-k3 | together-ai/kimi-k3 | $3/MTok | $15/MTok | 1M | ReasoningToolsOpen |
| Kimi K3 (NovitaAI)kimi-k3 | novita/kimi-k3 | $3/MTok | $15/MTok | 1.0M | ReasoningToolsOpen |
| Kimi K3 (Moonshot AI)kimi-k3 | moonshot/kimi-k3 | $3/MTok | $15/MTok | 1.0M | ReasoningToolsOpen |
| Kimi K3 (Tencent Cloud)kimi-k3 | tencent/kimi-k3 | $3/MTok | $15/MTok | 1.0M | ReasoningToolsOpen |
| Grok 4 (xAI)grok | xai/grok-4 | $3/MTok | $15/MTok | 256K | ReasoningTools |
| Kimi K3 (Fireworks AI)kimi-k3 | fireworks/kimi-k3 | $3/MTok | $15/MTok | 1.0M | ReasoningToolsOpen |
| Sonar Pro (Perplexity)sonar-pro | perplexity/sonar-pro | $3/MTok | $15/MTok | 200K | |
| Kimi K3 (Runware)kimi-k3 | runware/kimi-k3 | $3/MTok | $15/MTok | 1.0M | ReasoningToolsOpen |
| Kimi K3 (SCX.ai)kimi-k3 | scx-ai-gp/kimi-k3 | $3.50/MTok | $18/MTok | 1.0M | ReasoningToolsOpen |
| GPT 5.6 Sol (Azure)gpt-sol | azure/gpt-5.6-sol | $4/MTok | $20/MTok | 1.1M | ReasoningTools |
| GPT 5.6 Sol (OpenAI)gpt-sol | openai/gpt-5.6-sol | $4/MTok | $20/MTok | 1.1M | ReasoningTools |
| Mistral Large Latest (Mistral AI)mistral-large | mistral/mistral-large-latest | $4/MTok | $12/MTok | 128K | Open |
| GPT 5.6 Sol (AWS Mantle)gpt-sol | aws-mantle/gpt-5.6-sol | $4.40/MTok | $22/MTok | 921.6K | ReasoningTools |
| Kimi K3 Fast (Fireworks AI)kimi-k3 | fireworks/kimi-k3-fast | $4.50/MTok | $22.50/MTok | 1.0M | ReasoningToolsOpen |
| Claude Opus 4.6 (Vertex AI (Anthropic))claude-opus | vertex-anthropic/claude-opus-4-6 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.7 (Vertex AI (Anthropic))claude-opus | vertex-anthropic/claude-opus-4-7 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.5 (Vertex AI (Anthropic))claude-opus | vertex-anthropic/claude-opus-4-5-20251101 | $5/MTok | $25/MTok | 200K | ReasoningTools |
| Claude Opus 5 (AWS Bedrock)claude-opus | aws-bedrock/claude-opus-5 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.6 (AWS Bedrock)claude-opus | aws-bedrock/claude-opus-4-6 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.7 (AWS Bedrock)claude-opus | aws-bedrock/claude-opus-4-7 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.8 (AWS Bedrock)claude-opus | aws-bedrock/claude-opus-4-8 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.5 (AWS Bedrock)claude-opus | aws-bedrock/claude-opus-4-5-20251101 | $5/MTok | $25/MTok | 200K | ReasoningTools |
| Claude Opus 5 (Anthropic)claude-opus | anthropic/claude-opus-5 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.6 (Anthropic)claude-opus | anthropic/claude-opus-4-6 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.7 (Anthropic)claude-opus | anthropic/claude-opus-4-7 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.8 (Anthropic)claude-opus | anthropic/claude-opus-4-8 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.5 (Anthropic)claude-opus | anthropic/claude-opus-4-5-20251101 | $5/MTok | $25/MTok | 200K | ReasoningTools |
| Fugu Ultra (Sakana AI)fugu | sakana/fugu-ultra | $5/MTok | $30/MTok | 1M | ReasoningTools |
| Fugu Ultra v2.0 (Sakana AI)fugu | sakana/fugu-ultra-v2.0 | $5/MTok | $30/MTok | 1M | ReasoningTools |
| GPT 5.5 (Azure)gpt | azure/gpt-5.5 | $5/MTok | $30/MTok | 1.1M | ReasoningTools |
| GPT 5.5 (OpenAI)gpt | openai/gpt-5.5 | $5/MTok | $30/MTok | 1.1M | ReasoningTools |
| Claude Opus 5 (Azure Anthropic)claude-opus | azure-anthropic/claude-opus-5 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.6 (Azure Anthropic)claude-opus | azure-anthropic/claude-opus-4-6 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.7 (Azure Anthropic)claude-opus | azure-anthropic/claude-opus-4-7 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| Claude Opus 4.8 (Azure Anthropic)claude-opus | azure-anthropic/claude-opus-4-8 | $5/MTok | $25/MTok | 1M | ReasoningTools |
| GPT 6 Astra (AWS Mantle)gpt-astra | aws-mantle/gpt-6-astra | $10/MTok | $50/MTok | 1.1M | ReasoningTools |
| Claude Fable 5.1 (AWS Bedrock)claude-fable | aws-bedrock/claude-fable-5-1 | $10/MTok | $50/MTok | 1M | ReasoningTools |
| Claude Fable 5 (AWS Bedrock)claude-fable | aws-bedrock/claude-fable-5 | $10/MTok | $50/MTok | 1M | ReasoningTools |
| Claude Fable 5.1 (Anthropic)claude-fable | anthropic/claude-fable-5-1 | $10/MTok | $50/MTok | 1M | ReasoningTools |
| Claude Fable 5 (Anthropic)claude-fable | anthropic/claude-fable-5 | $10/MTok | $50/MTok | 1M | ReasoningTools |
| GPT 6 Astra (Azure)gpt-astra | azure/gpt-6-astra | $10/MTok | $50/MTok | 1.1M | ReasoningTools |
| GPT 4 Turbo (Azure)gpt | azure/gpt-4-turbo | $10/MTok | $30/MTok | 128K | Tools |
| GPT 6 Astra (OpenAI)gpt | openai/gpt-6-astra | $10/MTok | $50/MTok | 1.1M | ReasoningTools |
| GPT 4 Turbo (OpenAI)gpt | openai/gpt-4-turbo | $10/MTok | $30/MTok | 128K | Tools |
| Claude Fable 5 (Azure Anthropic)claude-fable | azure-anthropic/claude-fable-5 | $10/MTok | $50/MTok | 1M | ReasoningTools |
| Claude Opus 4.1 (AWS Bedrock)claude-opus | aws-bedrock/claude-opus-4-1-20250805 | $15/MTok | $75/MTok | 200K | ReasoningTools |
| o1 (Azure)o | azure/o1 | $15/MTok | $60/MTok | 200K | Reasoning |
| GPT 5 Pro (OpenAI)gpt-pro | openai/gpt-5-pro | $15/MTok | $120/MTok | 400K | ReasoningTools |
| o1 (OpenAI)o | openai/o1 | $15/MTok | $60/MTok | 200K | Reasoning |
| GPT 5.2 Pro (Azure)gpt-pro | azure/gpt-5.2-pro | $21/MTok | $168/MTok | 400K | ReasoningTools |
| GPT 5.2 Pro (OpenAI)gpt-pro | openai/gpt-5.2-pro | $21/MTok | $168/MTok | 400K | ReasoningTools |
| GPT 5.4 Pro (Azure)gpt-pro | azure/gpt-5.4-pro | $30/MTok | $180/MTok | 1.1M | ReasoningTools |
| GPT 4 (Azure)gpt | azure/gpt-4 | $30/MTok | $60/MTok | 8.2K | Tools |
| GPT 5.5 Pro (OpenAI)gpt-pro | openai/gpt-5.5-pro | $30/MTok | $180/MTok | 1.1M | ReasoningTools |
| GPT 5.4 Pro (OpenAI)gpt-pro | openai/gpt-5.4-pro | $30/MTok | $180/MTok | 1.1M | ReasoningTools |
| GPT 4 (OpenAI)gpt | openai/gpt-4 | $30/MTok | $60/MTok | 8.2K | Tools |
