Live prices from the AI Gateway · 178 models
AI Model Pricing Comparison
Compare the real per-token cost of every major AI model — GPT-5.5, Claude Opus & Sonnet, Gemini 3.5, DeepSeek, Qwen, Llama, Grok and more — side by side. Prices are USD per 1,000,000 tokens, with context window, reasoning support and cost class. Pulled live from the Vercel AI Gateway. Every model here is selectable per agent inside Agent Planners.
Cheapest models (output)
- Ministral 3b$0.10/1M
- Nova Micro$0.14/1M
- Trinity Mini$0.15/1M
- Ministral 8b$0.15/1M
- Mistral Nemo$0.15/1M
Flagship / most capable
- Gpt 5.4 Pro$180/1M
- GPT-5.5 Pro$180/1M
- Gpt 5.2 Pro$168/1M
- Gpt 5 Pro$120/1M
- O3 Pro$80.0/1M
Full price & capability comparison
| Model | Provider | Class | Context | Reasoning | Input /1M | Output /1M |
|---|---|---|---|---|---|---|
Ministral 3b mistral/ministral-3b | Mistral | $ Cheap | 128K | — | $0.10 | $0.10 |
Nova Micro amazon/nova-micro | Amazon | $$ Mid | 128K | — | $0.04 | $0.14 |
Trinity Mini arcee-ai/trinity-mini | Arcee-ai | $ Cheap | 131K | — | $0.04 | $0.15 |
Ministral 8b mistral/ministral-8b | Mistral | $ Cheap | 128K | — | $0.15 | $0.15 |
Mistral Nemo mistral/mistral-nemo | Mistral | $$ Mid | 128K | — | $0.15 | $0.15 |
Ministral 14b mistral/ministral-14b | Mistral | $ Cheap | 256K | — | $0.20 | $0.20 |
Gpt Oss 20b openai/gpt-oss-20b | OpenAI | $$ Mid | 131K | — | $0.05 | $0.20 |
Llama 3.1 8b meta/llama-3.1-8b | Meta (Llama) | $ Cheap | 128K | — | $0.22 | $0.22 |
Nemotron Nano 9b V2 nvidia/nemotron-nano-9b-v2 | Nvidia | $ Cheap | 131K | — | $0.06 | $0.23 |
Qwen 3 14b alibaba/qwen-3-14b | Alibaba (Qwen) | $$ Mid | 41K | — | $0.12 | $0.24 |
Nova Lite amazon/nova-lite | Amazon | $ Cheap | 300K | — | $0.06 | $0.24 |
Nemotron 3 Nano 30b A3b nvidia/nemotron-3-nano-30b-a3b | Nvidia | $ Cheap | 262K | — | $0.05 | $0.24 |
DeepSeek V4 Flash deepseek/deepseek-v4-flash | DeepSeek | $ Cheap | 1M | — | $0.14 | $0.28 |
Mimo V2.5 xiaomi/mimo-v2.5 | Xiaomi | $$ Mid | 1.1M | — | $0.14 | $0.28 |
Mistral Small mistral/mistral-small | Mistral | $ Cheap | 32K | — | $0.10 | $0.30 |
Step 3.5 Flash stepfun/step-3.5-flash | Stepfun | $ Cheap | 262K | — | $0.09 | $0.30 |
Qwen3.5 Flash alibaba/qwen3.5-flash | Alibaba (Qwen) | $ Cheap | 1M | — | $0.10 | $0.40 |
Gemini 2.5 Flash Lite google/gemini-2.5-flash-lite | $ Cheap | 1.0M | — | $0.10 | $0.40 | |
Gpt 4.1 Nano openai/gpt-4.1-nano | OpenAI | $ Cheap | 1.0M | — | $0.10 | $0.40 |
Gpt 5 Nano openai/gpt-5-nano | OpenAI | $ Cheap | 400K | Yes | $0.05 | $0.40 |
GLM-4.7 Flash zai/glm-4.7-flash | Zhipu (GLM) | $ Cheap | 200K | — | $0.07 | $0.40 |
Glm 4.7 Flashx zai/glm-4.7-flashx | Zhipu (GLM) | $ Cheap | 200K | — | $0.06 | $0.40 |
DeepSeek V3.2 deepseek/deepseek-v3.2 | DeepSeek | $$ Mid | 128K | — | $0.28 | $0.42 |
Qwen 3 30b alibaba/qwen-3-30b | Alibaba (Qwen) | $$ Mid | 41K | — | $0.12 | $0.50 |
Gpt Oss 120b openai/gpt-oss-120b | OpenAI | $$ Mid | 131K | — | $0.10 | $0.50 |
Grok 4.1 Fast Non Reasoning xai/grok-4.1-fast-non-reasoning | xAI | $ Cheap | 1M | Yes | $0.20 | $0.50 |
Grok 4.1 Fast xai/grok-4.1-fast-reasoning | xAI | $ Cheap | 1M | Yes | $0.20 | $0.50 |
Nemotron Nano 12b V2 Vl nvidia/nemotron-nano-12b-v2-vl | Nvidia | $ Cheap | 131K | — | $0.20 | $0.60 |
Gpt 4o Mini openai/gpt-4o-mini | OpenAI | $ Cheap | 128K | — | $0.15 | $0.60 |
Gpt 4o Mini Search Preview openai/gpt-4o-mini-search-preview | OpenAI | $ Cheap | 128K | — | $0.15 | $0.60 |
Qwen 3 32b alibaba/qwen-3-32b | Alibaba (Qwen) | $$ Mid | 128K | — | $0.16 | $0.64 |
Nemotron 3 Super 120b A12b nvidia/nemotron-3-super-120b-a12b | Nvidia | $$ Mid | 256K | — | $0.15 | $0.65 |
Llama 4 Scout meta/llama-4-scout | Meta (Llama) | $$ Mid | 128K | — | $0.17 | $0.66 |
Llama 3.1 70b meta/llama-3.1-70b | Meta (Llama) | $$ Mid | 128K | — | $0.72 | $0.72 |
Llama 3.3 70B meta/llama-3.3-70b | Meta (Llama) | $ Cheap | 128K | — | $0.72 | $0.72 |
Mercury 2 inception/mercury-2 | Inception | $$ Mid | 128K | — | $0.25 | $0.75 |
DeepSeek V4 Pro deepseek/deepseek-v4-pro | DeepSeek | $$ Mid | 1M | — | $0.43 | $0.87 |
Mimo V2.5 Pro xiaomi/mimo-v2.5-pro | Xiaomi | $$$ Premium | 1.1M | — | $0.43 | $0.87 |
Qwen 3 235b alibaba/qwen-3-235b | Alibaba (Qwen) | $$ Mid | 262K | — | $0.22 | $0.88 |
Trinity Large Thinking arcee-ai/trinity-large-thinking | Arcee-ai | $$ Mid | 262K | Yes | $0.25 | $0.90 |
Glm 4.6v zai/glm-4.6v | Zhipu (GLM) | $$ Mid | 128K | — | $0.30 | $0.90 |
Deepseek V3.1 deepseek/deepseek-v3.1 | DeepSeek | $$ Mid | 164K | — | $0.25 | $0.95 |
Llama 4 Maverick meta/llama-4-maverick | Meta (Llama) | $$ Mid | 128K | — | $0.24 | $0.97 |
Deepseek V3.1 Terminus deepseek/deepseek-v3.1-terminus | DeepSeek | $$ Mid | 131K | — | $0.27 | $1.00 |
Glm 4.5 Air zai/glm-4.5-air | Zhipu (GLM) | $$ Mid | 128K | — | $0.20 | $1.10 |
Deepseek V3 deepseek/deepseek-v3 | DeepSeek | $$ Mid | 164K | — | $0.27 | $1.12 |
Step 3.7 Flash stepfun/step-3.7-flash | Stepfun | $ Cheap | 256K | — | $0.20 | $1.15 |
Qwen3 Next 80b A3b Instruct alibaba/qwen3-next-80b-a3b-instruct | Alibaba (Qwen) | $$ Mid | 131K | — | $0.15 | $1.20 |
Qwen3 Next 80b A3b Thinking alibaba/qwen3-next-80b-a3b-thinking | Alibaba (Qwen) | $$ Mid | 131K | Yes | $0.15 | $1.20 |
Minimax M2 minimax/minimax-m2 | MiniMax | $ Cheap | 205K | — | $0.30 | $1.20 |
Minimax M2.1 minimax/minimax-m2.1 | MiniMax | $ Cheap | 205K | — | $0.30 | $1.20 |
Minimax M2.5 minimax/minimax-m2.5 | MiniMax | $ Cheap | 205K | — | $0.30 | $1.20 |
MiniMax M2.7 minimax/minimax-m2.7 | MiniMax | $$ Mid | 205K | — | $0.30 | $1.20 |
MiniMax M3 minimax/minimax-m3 | MiniMax | $$ Mid | 1M | — | $0.30 | $1.20 |
Morph V3 Fast morph/morph-v3-fast | Morph | $ Cheap | 82K | — | $0.80 | $1.20 |
Claude 3 Haiku anthropic/claude-3-haiku | Anthropic | $ Cheap | 200K | — | $0.25 | $1.25 |
Gpt 5.4 Nano openai/gpt-5.4-nano | OpenAI | $ Cheap | 400K | Yes | $0.20 | $1.25 |
Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | $ Cheap | 1M | — | $0.25 | $1.50 | |
Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview | $ Cheap | 1M | — | $0.25 | $1.50 | |
Magistral Small mistral/magistral-small | Mistral | $ Cheap | 128K | Yes | $0.50 | $1.50 |
Mistral Large 3 mistral/mistral-large-3 | Mistral | $$ Mid | 256K | — | $0.50 | $1.50 |
Gpt 3.5 Turbo openai/gpt-3.5-turbo | OpenAI | $$ Mid | 16K | — | $0.50 | $1.50 |
Qwen3.7 Plus alibaba/qwen3.7-plus | Alibaba (Qwen) | $$ Mid | 1M | — | $0.40 | $1.60 |
Gpt 4.1 Mini openai/gpt-4.1-mini | OpenAI | $ Cheap | 1.0M | — | $0.40 | $1.60 |
Glm 4.5v zai/glm-4.5v | Zhipu (GLM) | $$ Mid | 66K | — | $0.60 | $1.80 |
DeepSeek V3.2 Thinking deepseek/deepseek-v3.2-thinking | DeepSeek | $$ Mid | 128K | Yes | $0.62 | $1.85 |
Morph V3 Large morph/morph-v3-large | Morph | $$ Mid | 82K | — | $0.90 | $1.90 |
Seed 1.6 bytedance/seed-1.6 | Bytedance | $$ Mid | 256K | — | $0.25 | $2.00 |
Seed 1.8 bytedance/seed-1.8 | Bytedance | $$ Mid | 256K | — | $0.25 | $2.00 |
Mistral Medium mistral/mistral-medium | Mistral | $$ Mid | 128K | — | $0.40 | $2.00 |
Kimi K2 Thinking moonshotai/kimi-k2-thinking | Moonshot (Kimi) | $$ Mid | 216K | Yes | $0.47 | $2.00 |
GPT-5 mini openai/gpt-5-mini | OpenAI | $ Cheap | 400K | Yes | $0.25 | $2.00 |
Gpt 5.1 Codex Mini openai/gpt-5.1-codex-mini | OpenAI | $ Cheap | 400K | Yes | $0.25 | $2.00 |
Grok Build 0.1 xai/grok-build-0.1 | xAI | $$ Mid | 256K | — | $1.00 | $2.00 |
Glm 4.5 zai/glm-4.5 | Zhipu (GLM) | $$ Mid | 128K | — | $0.60 | $2.20 |
Glm 4.6 zai/glm-4.6 | Zhipu (GLM) | $$ Mid | 200K | — | $0.60 | $2.20 |
Glm 4.7 zai/glm-4.7 | Zhipu (GLM) | $$ Mid | 200K | — | $0.60 | $2.20 |
Kimi K2 moonshotai/kimi-k2 | Moonshot (Kimi) | $$ Mid | 131K | — | $0.57 | $2.30 |
Qwen3.5 Plus alibaba/qwen3.5-plus | Alibaba (Qwen) | $$ Mid | 1M | — | $0.40 | $2.40 |
Minimax M2.1 Lightning minimax/minimax-m2.1-lightning | MiniMax | $ Cheap | 205K | — | $0.30 | $2.40 |
Minimax M2.5 Highspeed minimax/minimax-m2.5-highspeed | MiniMax | $ Cheap | 205K | — | $0.60 | $2.40 |
Minimax M2.7 Highspeed minimax/minimax-m2.7-highspeed | MiniMax | $ Cheap | 205K | — | $0.60 | $2.40 |
Nemotron 3 Ultra 550b A55b nvidia/nemotron-3-ultra-550b-a55b | Nvidia | $$$ Premium | 1M | — | $0.60 | $2.40 |
Gpt Realtime Mini openai/gpt-realtime-mini | OpenAI | $ Cheap | — | — | $0.60 | $2.40 |
Nova 2 Lite amazon/nova-2-lite | Amazon | $ Cheap | 1M | — | $0.30 | $2.50 |
Gemini 2.5 Flash google/gemini-2.5-flash | $ Cheap | 1M | — | $0.30 | $2.50 | |
Grok 4.20 Multi Agent xai/grok-4.20-multi-agent | xAI | $$$ Premium | 2M | — | $1.25 | $2.50 |
Grok 4.20 Multi Agent Beta xai/grok-4.20-multi-agent-beta | xAI | $$$ Premium | 2M | — | $1.25 | $2.50 |
Grok 4.20 Non Reasoning xai/grok-4.20-non-reasoning | xAI | $$$ Premium | 2M | Yes | $1.25 | $2.50 |
Grok 4.20 Non Reasoning Beta xai/grok-4.20-non-reasoning-beta | xAI | $$$ Premium | 2M | Yes | $1.25 | $2.50 |
Grok 4.20 Reasoning xai/grok-4.20-reasoning | xAI | $$$ Premium | 2M | Yes | $1.25 | $2.50 |
Grok 4.20 Reasoning Beta xai/grok-4.20-reasoning-beta | xAI | $$$ Premium | 2M | Yes | $1.25 | $2.50 |
Grok 4.3 xai/grok-4.3 | xAI | $$ Mid | 1M | — | $1.25 | $2.50 |
Qwen3.6 Plus alibaba/qwen3.6-plus | Alibaba (Qwen) | $$ Mid | 1M | — | $0.50 | $3.00 |
Gemini 3 Flash google/gemini-3-flash | $ Cheap | 1M | — | $0.50 | $3.00 | |
Kimi K2.5 moonshotai/kimi-k2.5 | Moonshot (Kimi) | $$ Mid | 262K | — | $0.60 | $3.00 |
Glm 5 zai/glm-5 | Zhipu (GLM) | $$ Mid | 203K | — | $0.95 | $3.15 |
Nova Pro amazon/nova-pro | Amazon | $$$ Premium | 300K | — | $0.80 | $3.20 |
Interfaze Beta interfaze/interfaze-beta | Interfaze | $$ Mid | 1M | — | $1.50 | $3.50 |
Qwen3.6 27b alibaba/qwen3.6-27b | Alibaba (Qwen) | $$ Mid | 256K | — | $0.60 | $3.60 |
Qwen3.7 Max alibaba/qwen3.7-max | Alibaba (Qwen) | $$ Mid | 991K | — | $1.25 | $3.75 |
Qwen3 235b A22b Thinking alibaba/qwen3-235b-a22b-thinking | Alibaba (Qwen) | $$ Mid | 131K | Yes | $0.40 | $4.00 |
Kimi K2.6 moonshotai/kimi-k2.6 | Moonshot (Kimi) | $$ Mid | 262K | — | $0.95 | $4.00 |
Kimi K2.7 Code moonshotai/kimi-k2.7-code | Moonshot (Kimi) | $$ Mid | 256K | — | $0.95 | $4.00 |
Glm 5 Turbo zai/glm-5-turbo | Zhipu (GLM) | $$ Mid | 203K | — | $1.20 | $4.00 |
Glm 5v Turbo zai/glm-5v-turbo | Zhipu (GLM) | $$ Mid | 200K | — | $1.20 | $4.00 |
Inkling thinkingmachines/inkling | Thinkingmachines | $$ Mid | 256K | Yes | $1.00 | $4.05 |
Muse Spark 1.1 meta/muse-spark-1.1 | Meta (Llama) | $$ Mid | 1.0M | — | $1.25 | $4.25 |
GLM-5.1 zai/glm-5.1 | Zhipu (GLM) | $$ Mid | 202K | — | $1.30 | $4.30 |
O3 Mini openai/o3-mini | OpenAI | $ Cheap | 200K | Yes | $1.10 | $4.40 |
O4 Mini openai/o4-mini | OpenAI | $ Cheap | 200K | Yes | $1.10 | $4.40 |
GLM-5.2 zai/glm-5.2 | Zhipu (GLM) | $$ Mid | 1.0M | — | $1.40 | $4.40 |
GPT-5.4 mini openai/gpt-5.4-mini | OpenAI | $ Cheap | 400K | Yes | $0.75 | $4.50 |
Claude Haiku 4.5 anthropic/claude-haiku-4.5 | Anthropic | $ Cheap | 200K | — | $1.00 | $5.00 |
Magistral Medium mistral/magistral-medium | Mistral | $$ Mid | 128K | Yes | $2.00 | $5.00 |
Gpt 4o Mini Transcribe openai/gpt-4o-mini-transcribe | OpenAI | $ Cheap | — | — | $1.25 | $5.00 |
DeepSeek R1 deepseek/deepseek-r1 | DeepSeek | $$ Mid | 128K | Yes | $1.35 | $5.40 |
Qwen3 Max alibaba/qwen3-max | Alibaba (Qwen) | $$$ Premium | 262K | — | $1.20 | $6.00 |
Qwen3 Max Preview alibaba/qwen3-max-preview | Alibaba (Qwen) | $$$ Premium | 262K | — | $1.20 | $6.00 |
Qwen3 Max Thinking alibaba/qwen3-max-thinking | Alibaba (Qwen) | $$ Mid | 256K | Yes | $1.20 | $6.00 |
Gpt 5.6 Luna openai/gpt-5.6-luna | OpenAI | $$ Mid | 1.1M | Yes | $1.00 | $6.00 |
Grok 4.5 xai/grok-4.5 | xAI | $$$ Premium | 500K | — | $2.00 | $6.00 |
Glm 5.2 Fast zai/glm-5.2-fast | Zhipu (GLM) | $ Cheap | 1M | — | $2.10 | $6.60 |
Mistral Medium 3.5 mistral/mistral-medium-3.5 | Mistral | $$ Mid | 256K | — | $1.50 | $7.50 |
Qwen 3.6 Max Preview alibaba/qwen-3.6-max-preview | Alibaba (Qwen) | $$$ Premium | 240K | — | $1.30 | $7.80 |
Kimi K2.7 Code Highspeed moonshotai/kimi-k2.7-code-highspeed | Moonshot (Kimi) | $ Cheap | 262K | — | $1.90 | $8.00 |
Gpt 4.1 openai/gpt-4.1 | OpenAI | $$ Mid | 1.0M | — | $2.00 | $8.00 |
O3 openai/o3 | OpenAI | $$ Mid | 200K | Yes | $2.00 | $8.00 |
Gemini 3.5 Flash google/gemini-3.5-flash | $ Cheap | 1M | — | $1.50 | $9.00 | |
Gemini Omni Flash Preview google/gemini-omni-flash-preview | $ Cheap | 1M | — | $1.50 | $9.00 | |
Claude Sonnet 5 anthropic/claude-sonnet-5 | Anthropic | $$ Mid | 1M | — | $2.00 | $10.0 |
Command A cohere/command-a | Cohere | $$ Mid | 256K | — | $2.50 | $10.0 |
Gemini 2.5 Pro google/gemini-2.5-pro | $$ Mid | 1.0M | — | $1.25 | $10.0 | |
Gpt 4o openai/gpt-4o | OpenAI | $$ Mid | 128K | — | $2.50 | $10.0 |
Gpt 4o Transcribe openai/gpt-4o-transcribe | OpenAI | $$ Mid | — | — | $2.50 | $10.0 |
GPT-5 openai/gpt-5 | OpenAI | $$ Mid | 400K | Yes | $1.25 | $10.0 |
Gpt 5 Chat openai/gpt-5-chat | OpenAI | $$ Mid | 128K | Yes | $1.25 | $10.0 |
Gpt 5 Codex openai/gpt-5-codex | OpenAI | $$ Mid | 400K | Yes | $1.25 | $10.0 |
Gpt 5.1 Codex openai/gpt-5.1-codex | OpenAI | $$ Mid | 400K | Yes | $1.25 | $10.0 |
Gpt 5.1 Codex Max openai/gpt-5.1-codex-max | OpenAI | $$$ Premium | 400K | Yes | $1.25 | $10.0 |
Gpt 5.1 Instant openai/gpt-5.1-instant | OpenAI | $$ Mid | 128K | Yes | $1.25 | $10.0 |
Gpt 5.1 Thinking openai/gpt-5.1-thinking | OpenAI | $$ Mid | 400K | Yes | $1.25 | $10.0 |
Gemini 3 Pro google/gemini-3-pro-preview | $$$ Premium | 1M | — | $2.00 | $12.0 | |
Gemini 3.1 Pro google/gemini-3.1-pro-preview | $$$ Premium | 1M | — | $2.00 | $12.0 | |
GPT-5.2 openai/gpt-5.2 | OpenAI | $$ Mid | 400K | Yes | $1.75 | $14.0 |
Gpt 5.2 Chat openai/gpt-5.2-chat | OpenAI | $$ Mid | 128K | Yes | $1.75 | $14.0 |
Gpt 5.2 Codex openai/gpt-5.2-codex | OpenAI | $$ Mid | 400K | Yes | $1.75 | $14.0 |
Gpt 5.3 Chat openai/gpt-5.3-chat | OpenAI | $$ Mid | 128K | Yes | $1.75 | $14.0 |
Gpt 5.3 Codex openai/gpt-5.3-codex | OpenAI | $$ Mid | 400K | Yes | $1.75 | $14.0 |
Claude Sonnet 4 anthropic/claude-sonnet-4 | Anthropic | $$ Mid | 1M | Yes | $3.00 | $15.0 |
Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | Anthropic | $$ Mid | 1M | Yes | $3.00 | $15.0 |
Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | Anthropic | $$ Mid | 1M | Yes | $3.00 | $15.0 |
Kimi K3 moonshotai/kimi-k3 | Moonshot (Kimi) | $$ Mid | 1M | — | $3.00 | $15.0 |
GPT-5.4 openai/gpt-5.4 | OpenAI | $$ Mid | 1.1M | Yes | $2.50 | $15.0 |
Gpt 5.6 Terra openai/gpt-5.6-terra | OpenAI | $$ Mid | 1.1M | Yes | $2.50 | $15.0 |
Gpt Realtime 1.5 openai/gpt-realtime-1.5 | OpenAI | $$ Mid | — | — | $4.00 | $16.0 |
Gpt Realtime 2 openai/gpt-realtime-2 | OpenAI | $$ Mid | — | — | $4.00 | $24.0 |
Gpt Realtime 2.1 openai/gpt-realtime-2.1 | OpenAI | $$ Mid | 128K | — | $4.00 | $24.0 |
Claude Opus 4.5 anthropic/claude-opus-4.5 | Anthropic | $$$ Premium | 200K | Yes | $5.00 | $25.0 |
Claude Opus 4.6 anthropic/claude-opus-4.6 | Anthropic | $$ Mid | 1M | Yes | $5.00 | $25.0 |
Claude Opus 4.7 anthropic/claude-opus-4.7 | Anthropic | $$$ Premium | 1M | Yes | $5.00 | $25.0 |
Claude Opus 4.8 anthropic/claude-opus-4.8 | Anthropic | $$$ Premium | 1M | Yes | $5.00 | $25.0 |
Gpt 4 Turbo openai/gpt-4-turbo | OpenAI | $$ Mid | 128K | — | $10.0 | $30.0 |
GPT-5.5 openai/gpt-5.5 | OpenAI | $$ Mid | 1M | Yes | $5.00 | $30.0 |
Gpt 5.6 Sol openai/gpt-5.6-sol | OpenAI | $$ Mid | 1.1M | Yes | $5.00 | $30.0 |
Fugu Ultra sakana/fugu-ultra | Sakana | $$$ Premium | 1M | — | $5.00 | $30.0 |
O3 Deep Research openai/o3-deep-research | OpenAI | $$ Mid | 200K | Yes | $10.0 | $40.0 |
Claude Fable 5 anthropic/claude-fable-5 | Anthropic | $$ Mid | 1M | — | $10.0 | $50.0 |
Claude Opus 4.8 Fast anthropic/claude-opus-4.8-fast | Anthropic | $ Cheap | 1M | Yes | $10.0 | $50.0 |
O1 openai/o1 | OpenAI | $$ Mid | 200K | Yes | $15.0 | $60.0 |
Claude Opus 4 anthropic/claude-opus-4 | Anthropic | $$$ Premium | 200K | Yes | $15.0 | $75.0 |
Claude Opus 4.1 anthropic/claude-opus-4.1 | Anthropic | $$$ Premium | 200K | Yes | $15.0 | $75.0 |
O3 Pro openai/o3-pro | OpenAI | $$$ Premium | 200K | Yes | $20.0 | $80.0 |
Gpt 5 Pro openai/gpt-5-pro | OpenAI | $$$ Premium | 400K | Yes | $15.0 | $120 |
Claude Opus 4.7 Fast anthropic/claude-opus-4.7-fast | Anthropic | $ Cheap | 1M | Yes | $30.0 | $150 |
Gpt 5.2 Pro openai/gpt-5.2-pro | OpenAI | $$$ Premium | 400K | Yes | $21.0 | $168 |
Gpt 5.4 Pro openai/gpt-5.4-pro | OpenAI | $$$ Premium | 1.1M | Yes | $30.0 | $180 |
GPT-5.5 Pro openai/gpt-5.5-pro | OpenAI | $$$ Premium | 1M | Yes | $30.0 | $180 |
Seedream 4.0 bytedance/seedream-4.0 | Bytedance | $$ Mid | — | — | — | — |
Seedream 4.5 bytedance/seedream-4.5 | Bytedance | $$ Mid | — | — | — | — |
Seedream 5.0 Lite bytedance/seedream-5.0-lite | Bytedance | $ Cheap | — | — | — | — |
Seedream 5.0 Pro bytedance/seedream-5.0-pro | Bytedance | $$$ Premium | — | — | $0.00 | — |
Kling V2.5 Turbo I2v klingai/kling-v2.5-turbo-i2v | Klingai | $$ Mid | — | — | — | — |
Kling V2.5 Turbo T2v klingai/kling-v2.5-turbo-t2v | Klingai | $$ Mid | — | — | — | — |
Kling V2.6 I2v klingai/kling-v2.6-i2v | Klingai | $$ Mid | — | — | — | — |
Kling V2.6 Motion Control klingai/kling-v2.6-motion-control | Klingai | $$ Mid | — | — | — | — |
Kling V2.6 T2v klingai/kling-v2.6-t2v | Klingai | $$ Mid | — | — | — | — |
Kling V3.0 I2v klingai/kling-v3.0-i2v | Klingai | $$ Mid | — | — | — | — |
Kling V3.0 Motion Control klingai/kling-v3.0-motion-control | Klingai | $$ Mid | — | — | — | — |
Kling V3.0 T2v klingai/kling-v3.0-t2v | Klingai | $$ Mid | — | — | — | — |
Tts 1 openai/tts-1 | OpenAI | $$ Mid | — | — | $15.0 | — |
Tts 1 Hd openai/tts-1-hd | OpenAI | $$ Mid | — | — | $30.0 | — |
Sonar perplexity/sonar | Perplexity | $$ Mid | 127K | — | — | — |
Sonar Pro perplexity/sonar-pro | Perplexity | $$$ Premium | 200K | — | — | — |
Sonar Reasoning Pro perplexity/sonar-reasoning-pro | Perplexity | $$$ Premium | 127K | Yes | — | — |
Arrow 1.1 quiverai/arrow-1.1 | Quiverai | $$ Mid | 131K | — | — | — |
Voyage 3 Large voyage/voyage-3-large | Voyage | $$ Mid | — | — | $0.18 | — |
Voyage 3.5 voyage/voyage-3.5 | Voyage | $$ Mid | — | — | $0.06 | — |
Voyage 3.5 Lite voyage/voyage-3.5-lite | Voyage | $ Cheap | — | — | $0.02 | — |
Voyage 4 voyage/voyage-4 | Voyage | $$ Mid | 32K | — | $0.06 | — |
Voyage 4 Large voyage/voyage-4-large | Voyage | $$ Mid | 32K | — | $0.12 | — |
Voyage 4 Lite voyage/voyage-4-lite | Voyage | $ Cheap | 32K | — | $0.02 | — |
Voyage Code 2 voyage/voyage-code-2 | Voyage | $$ Mid | — | — | $0.12 | — |
Voyage Code 3 voyage/voyage-code-3 | Voyage | $$ Mid | — | — | $0.18 | — |
Voyage Finance 2 voyage/voyage-finance-2 | Voyage | $$ Mid | — | — | $0.12 | — |
Voyage Law 2 voyage/voyage-law-2 | Voyage | $$ Mid | — | — | $0.12 | — |
Grok Stt xai/grok-stt | xAI | $$ Mid | — | — | — | — |
Grok Voice Think Fast 1.0 xai/grok-voice-think-fast-1.0 | xAI | $ Cheap | — | — | — | — |
Glm 4.6v Flash zai/glm-4.6v-flash | Zhipu (GLM) | $ Cheap | 128K | — | — | — |
Prices are USD per 1,000,000 tokens, shown separately for input and output, sorted cheapest output first. Sourced live from the Vercel AI Gateway catalog and refreshed every few hours. Figures are the providers' own published rates (no markup) and can change — verify before budgeting. Non-text models (image, video, embeddings, audio) are excluded. See the credit-cost ranking for how these map to Agent Planners credits.
Frequently asked questions
Which AI model is the cheapest?
As of the latest gateway sync, the cheapest models by output price are Ministral 3b ($0.10/1M output), Nova Micro ($0.14/1M output), Trinity Mini ($0.15/1M output). Fast "Cheap"-class models like Gemini Flash, DeepSeek and Llama are typically 20–30× cheaper per token than premium frontier models.
How is AI model pricing calculated?
Providers charge per token — separately for input (your prompt) and output (the model's reply). Output tokens usually cost 3–5× more than input, and dominate the bill on generative work. Prices here are shown per 1,000,000 tokens so models are directly comparable.
What's the difference between the cost classes?
$ Cheap = fast, low-cost models for high-volume execution; $$ Mid = balanced quality and cost; $$$ Premium = frontier/flagship models for the hardest reasoning. Pick the cheapest class that still does the job.
Are these prices live?
Yes — prices are pulled from the live Vercel AI Gateway catalog and refreshed every few hours. They reflect each provider's own published per-token rate, not a markup.
Can I use these models in Agent Planners?
Yes. Every chat model here is selectable per agent inside Agent Planners through the built-in AI Gateway — mix a strong model for planning with cheap models for execution. Usage is metered in credits at the provider's real per-token cost.