What is the cheapest Chat API?
Chat models are from $0.03 per 1M input tokens. Prices for all 128 models are listed in the table above.
Task
Chat models available through the ScalingTensor API.
Every model below is available with the same API key. Open a model for its full parameter list and request examples.
| Model | Tasks | Billing | Price |
|---|---|---|---|
| alibaba/qwen2.5-vl-72b-instruct alibaba/qwen2.5-vl-72b-instruct | Per token | From $0.25 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3-32b alibaba/qwen3-32b | Per token | From $0.16 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.5-35b-a3b alibaba/qwen3.5-35b-a3b | Per token | From $0.25 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.6-27b alibaba/qwen3.6-27b | Per token | From $0.60 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.6-plus alibaba/qwen3.6-plus | Per token | From $0.50 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.7-flash alibaba/qwen3.7-flash | Per token | From $0.03 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.7-max alibaba/qwen3.7-max | Per token | From $2.50 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.7-plus alibaba/qwen3.7-plus | Per token | From $0.40 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.8-2.4t-a95b alibaba/qwen3.8-2.4t-a95b | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.8-27b alibaba/qwen3.8-27b | Per token | From $0.50 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.8-max alibaba/qwen3.8-max | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.8-max-0902 alibaba/qwen3.8-max-0902 | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.8-max-prime alibaba/qwen3.8-max-prime | Per token | From $4.00 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3.8-omni-flash alibaba/qwen3.8-omni-flash | Per token | From $0.15 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3-vl-235b-a22b-instruct alibaba/qwen3-vl-235b-a22b-instruct | Per token | From $0.40 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3-vl-30b-a3b-instruct alibaba/qwen3-vl-30b-a3b-instruct | Per token | From $0.13 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen3-vl-8b-instruct alibaba/qwen3-vl-8b-instruct | Per token | From $0.18 per 1M input tokens; output, cache and context tiers priced separately | |
| alibaba/qwen4-max alibaba/qwen4-max | Per token | From $1.67 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-fable-5 anthropic/claude-fable-5 | Per token | From $10.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-fable-5.1 anthropic/claude-fable-5.1 | Per token | From $10.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-fable-5.2 anthropic/claude-fable-5.2 | Per token | From $8.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-haiku-4.5 anthropic/claude-haiku-4.5 | Per token | From $1.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-haiku-5.5 anthropic/claude-haiku-5.5 | Per token | From $0.10 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-opus-4.5 anthropic/claude-opus-4.5 | Per token | From $5.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-opus-4.6 anthropic/claude-opus-4.6 | Per token | From $5.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-opus-4.7 anthropic/claude-opus-4.7 | Per token | From $5.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-opus-4.8 anthropic/claude-opus-4.8 | Per token | From $5.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-opus-5 anthropic/claude-opus-5 | Per token | From $5.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-opus-5.5 anthropic/claude-opus-5.5 | Per token | From $4.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-sonnet-4.5 anthropic/claude-sonnet-4.5 | Per token | From $3.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-sonnet-4.6 anthropic/claude-sonnet-4.6 | Per token | From $3.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-sonnet-5 anthropic/claude-sonnet-5 | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| anthropic/claude-sonnet-5.5 anthropic/claude-sonnet-5.5 | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| bytedance/seed-2.1-pro bytedance/seed-2.1-pro | Per token | From $0.8902 per 1M input tokens; output, cache and context tiers priced separately | |
| deepseek/deepseek-chat deepseek/deepseek-chat | Per token | From $0.32 per 1M input tokens; output, cache and context tiers priced separately | |
| deepseek/deepseek-v3.2 deepseek/deepseek-v3.2 | Per token | From $0.252 per 1M input tokens; output, cache and context tiers priced separately | |
| deepseek/deepseek-v4.1-flash deepseek/deepseek-v4.1-flash | Per token | From $0.30 per 1M input tokens; output, cache and context tiers priced separately | |
| deepseek/deepseek-v4.1-flash-economy deepseek/deepseek-v4.1-flash-economy | Per token | From $0.30 per 1M input tokens; output, cache and context tiers priced separately | |
| deepseek/deepseek-v4-flash deepseek/deepseek-v4-flash | Per token | From $0.30 per 1M input tokens; output, cache and context tiers priced separately | |
| deepseek/deepseek-v4-flash-0731 deepseek/deepseek-v4-flash-0731 | Per token | From $0.30 per 1M input tokens; output, cache and context tiers priced separately | |
| deepseek/deepseek-v4-flash-vision-exp deepseek/deepseek-v4-flash-vision-exp | Per token | From $0.30 per 1M input tokens; output, cache and context tiers priced separately | |
| deepseek/deepseek-v4-pro deepseek/deepseek-v4-pro | Per token | From $1.32 per 1M input tokens; output, cache and context tiers priced separately | |
| deepseek/deepseek-v4-pro-0813 deepseek/deepseek-v4-pro-0813 | Per token | From $1.32 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-2.5-flash google/gemini-2.5-flash | Per token | From $0.30 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-2.5-flash-lite google/gemini-2.5-flash-lite | Per token | From $0.10 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-2.5-pro google/gemini-2.5-pro | Per token | From $1.25 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3.1-flash-image google/gemini-3.1-flash-image | Per token | From $0.50 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3.1-flash-lite google/gemini-3.1-flash-lite | Per token | From $0.25 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3.1-flash-lite-preview google/gemini-3.1-flash-lite-preview | Per token | From $0.25 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3.1-pro-preview google/gemini-3.1-pro-preview | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3.1-pro-preview-customtools google/gemini-3.1-pro-preview-customtools | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3.5-flash google/gemini-3.5-flash | Per token | From $1.50 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3.5-flash-lite google/gemini-3.5-flash-lite | Per token | From $0.30 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3.6-flash google/gemini-3.6-flash | Per token | From $1.50 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3.7-flash google/gemini-3.7-flash | Per token | From $1.50 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3.8-flash google/gemini-3.8-flash | Per token | From $1.50 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3-flash-preview google/gemini-3-flash-preview | Per token | From $0.50 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-3-pro-image google/gemini-3-pro-image | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-4-argon google/gemini-4-argon | Per token | From $4.00 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-4-carbon google/gemini-4-carbon | Per token | From $4.00 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-4-hydrogen google/gemini-4-hydrogen | Per token | From $1.50 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-4-neon google/gemini-4-neon | Per token | From $3.00 per 1M input tokens; output, cache and context tiers priced separately | |
| google/gemini-nano-banana-2.1 google/gemini-nano-banana-2.1 | Per token | From $1.50 per 1M input tokens; output, cache and context tiers priced separately | |
| meta/llama-3.3-70b-instruct meta/llama-3.3-70b-instruct | Per token | From $0.10 per 1M input tokens; output, cache and context tiers priced separately | |
| minimax/minimax-m2.5 minimax/minimax-m2.5 | Per token | From $0.30 per 1M input tokens; output, cache and context tiers priced separately | |
| minimax/minimax-m2.7 minimax/minimax-m2.7 | Per token | From $0.30 per 1M input tokens; output, cache and context tiers priced separately | |
| minimax/minimax-m3 minimax/minimax-m3 | Per token | From $0.30 per 1M input tokens; output, cache and context tiers priced separately | |
| minimax/minimax-m3.1-flash minimax/minimax-m3.1-flash | Per token | From $0.15 per 1M input tokens; output, cache and context tiers priced separately | |
| moonshotai/kimi-k2.5 moonshotai/kimi-k2.5 | Per token | From $0.60 per 1M input tokens; output, cache and context tiers priced separately | |
| moonshotai/kimi-k2.6 moonshotai/kimi-k2.6 | Per token | From $0.95 per 1M input tokens; output, cache and context tiers priced separately | |
| moonshotai/kimi-k3 moonshotai/kimi-k3 | Per token | From $3.00 per 1M input tokens; output, cache and context tiers priced separately | |
| moonshotai/kimi-k3.1-pro moonshotai/kimi-k3.1-pro | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-4.1 openai/gpt-4.1 | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-4.1-mini openai/gpt-4.1-mini | Per token | From $0.40 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-4.1-nano openai/gpt-4.1-nano | Per token | From $0.10 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-4o-2024-05-13 openai/gpt-4o-2024-05-13 | Per token | From $5.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-4o-2024-08-06 openai/gpt-4o-2024-08-06 | Per token | From $2.50 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-4o-2024-11-20 openai/gpt-4o-2024-11-20 | Per token | From $2.50 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5 openai/gpt-5 | Per token | From $1.25 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.1 openai/gpt-5.1 | Per token | From $1.25 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.1-codex openai/gpt-5.1-codex | Per token | From $1.25 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.2 openai/gpt-5.2 | Per token | From $1.75 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.3-codex openai/gpt-5.3-codex | Per token | From $1.75 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.4 openai/gpt-5.4 | Per token | From $2.50 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.4-mini openai/gpt-5.4-mini | Per token | From $0.75 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.4-nano openai/gpt-5.4-nano | Per token | From $0.20 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.5 openai/gpt-5.5 | Per token | From $5.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.5-pro openai/gpt-5.5-pro | Per token | From $30.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.6-luna openai/gpt-5.6-luna | Per token | From $0.20 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.6-luna-pro openai/gpt-5.6-luna-pro | Per token | From $0.20 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.6-sol openai/gpt-5.6-sol | Per token | From $4.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.6-sol-pro openai/gpt-5.6-sol-pro | Per token | From $4.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.6-terra openai/gpt-5.6-terra | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5.6-terra-pro openai/gpt-5.6-terra-pro | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-5-mini openai/gpt-5-mini | Per token | From $0.25 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6.1-sol openai/gpt-6.1-sol | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6.1-sol-pro openai/gpt-6.1-sol-pro | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6.1-terra openai/gpt-6.1-terra | Per token | From $1.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6.1-terra-pro openai/gpt-6.1-terra-pro | Per token | From $1.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6.2-astra openai/gpt-6.2-astra | Per token | From $8.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6.2-astra-pro openai/gpt-6.2-astra-pro | Per token | From $8.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6.2-sol openai/gpt-6.2-sol | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6.2-sol-pro openai/gpt-6.2-sol-pro | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6-astra openai/gpt-6-astra | Per token | From $10.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6-astra-pro openai/gpt-6-astra-pro | Per token | From $10.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6-luna openai/gpt-6-luna | Per token | From $0.10 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6-luna-pro openai/gpt-6-luna-pro | Per token | From $0.10 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6-sol openai/gpt-6-sol | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-6-sol-pro openai/gpt-6-sol-pro | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| openai/gpt-oss-120b openai/gpt-oss-120b | Per token | From $0.039 per 1M input tokens; output, cache and context tiers priced separately | |
| stepfun/step-5-preview stepfun/step-5-preview | Per token | From $1.00 per 1M input tokens; output, cache and context tiers priced separately | |
| tencent/hy3 tencent/hy3 | Per token | From $0.132 per 1M input tokens; output, cache and context tiers priced separately | |
| tencent/hy4 tencent/hy4 | Per token | From $0.834 per 1M input tokens; output, cache and context tiers priced separately | |
| tencent/hy4-flash tencent/hy4-flash | Per token | From $0.07 per 1M input tokens; output, cache and context tiers priced separately | |
| tencent/hy4-preview tencent/hy4-preview | Per token | From $0.834 per 1M input tokens; output, cache and context tiers priced separately | |
| typesafe/jev-1.13 typesafe/jev-1.13 | Per token | From $0.042 per 1M input tokens; output, cache and context tiers priced separately | |
| typesafe/jev-1.14 typesafe/jev-1.14 | Per token | From $0.042 per 1M input tokens; output, cache and context tiers priced separately | |
| x-ai/grok-4.3 x-ai/grok-4.3 | Per token | From $1.25 per 1M input tokens; output, cache and context tiers priced separately | |
| x-ai/grok-4.5 x-ai/grok-4.5 | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| x-ai/grok-4.6 x-ai/grok-4.6 | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| x-ai/grok-4.7 x-ai/grok-4.7 | Per token | From $2.00 per 1M input tokens; output, cache and context tiers priced separately | |
| xiaomi/mimo-v2.6-flash xiaomi/mimo-v2.6-flash | Per token | From $0.14 per 1M input tokens; output, cache and context tiers priced separately | |
| xiaomi/mimo-v2.6-pro xiaomi/mimo-v2.6-pro | Per token | From $0.435 per 1M input tokens; output, cache and context tiers priced separately | |
| z-ai/glm-4.5-air z-ai/glm-4.5-air | Per token | From $0.20 per 1M input tokens; output, cache and context tiers priced separately | |
| z-ai/glm-5.2 z-ai/glm-5.2 | Per token | From $1.40 per 1M input tokens; output, cache and context tiers priced separately | |
| z-ai/glm-5.3 z-ai/glm-5.3 | Per token | From $1.40 per 1M input tokens; output, cache and context tiers priced separately | |
| z-ai/glm-5.3-flash z-ai/glm-5.3-flash | Per token | From $0.15 per 1M input tokens; output, cache and context tiers priced separately | |
| z-ai/glm-5.3-flashx z-ai/glm-5.3-flashx | Per token | From $0.37 per 1M input tokens; output, cache and context tiers priced separately |
Chat models are from $0.03 per 1M input tokens. Prices for all 128 models are listed in the table above.
ScalingTensor currently offers 128 chat models: alibaba/qwen2.5-vl-72b-instruct, alibaba/qwen3-32b, alibaba/qwen3.5-35b-a3b, alibaba/qwen3.6-27b, alibaba/qwen3.6-plus, alibaba/qwen3.7-flash, alibaba/qwen3.7-max, alibaba/qwen3.7-plus and 120 more.
Sign up with Google or email, top up your wallet from $10 and create an API key. The same key works for every model in the catalog.