Large Model API Pricing
Explore the pricing for our model API. With transparent rates and flexible options, find the right plan to meet your needs.
Anthropic
Anthropic's Claude model offers advanced AI safety capabilities, focusing on useful, harmless, and honest AI assistants with powerful reasoning and conversational abilities.
| Model Name | Input Token Range | Context | Input (/Mt) | Cache Write (/Mt) | Cache read (/Mt) | Output (/Mt) | Operation |
|---|---|---|---|---|---|---|---|
| claude-fable-5-1Official resource | - | 1M | $10 | $12.5(5m)·$20(1h) | $0.25 | $50 | |
| claude-fable-5Official resource | - | 1M | $10 | $12.5(5m)·$20(1h) | $1 | $50 | |
| claude-opus-4-7Official resource | - | 1M | $4.75 $5 | $5.9375 (5 min) · $9.50 (1 hr) $6.25 (5 min) × $10 (1 hr) | $0.475 $0.5 | $23.75 $25 | |
| claude-opus-5Official resource | - | 1M | $5 | $6.25 (5 min) · $10 (1 hr) | $0.5 | $25 | |
| claude-sonnet-5Official resource | - | 1M | $2 | $2.5(5m)·$4(1h) | $0.2 | $10 | |
| claude-opus-4-8Official resource | - | 1M | $4.75 $5 | $5.9375 (5 min) · $9.50 (1 hr) $6.25 (5 min) × $10 (1 hr) | $0.475 $0.5 | $23.75 $25 | |
| claude-opus-4-8-rValue zone | - | 1M | $1$5 | $1.25(5m)·$2(1h)$6.25(5m)·$10(1h) | $0.1$0.5 | $5$25 | |
| claude-opus-4-7-rValue zone | - | 1M | $1$5 | $1.25(5m)·$2(1h)$6.25(5m)·$10(1h) | $0.1$0.5 | $5$25 | |
| claude-opus-4-6-ddValue zone | - | 1M | $2.75$5 | $3.4375(5m)·$5.5(1h)$6.25(5m)·$10(1h) | $0.275$0.5 | $13.75$25 | |
| claude-opus-4-6Official resource | 1-200K | 1M | $5 | $6.25 (5 min) · $10 (1 hr) | $0.5 | $25 | |
| 200K-1M | 1M | $5 | $6.25 (5 min) · $10 (1 hr) | $0.5 | $25 | ||
| claude-opus-4-6-rValue zone | - | 1M | $1$5 | $1.25(5m)·$2(1h)$6.25(5m)·$10(1h) | $0.1$0.5 | $5$25 | |
| claude-sonnet-4-6Official resource | 1-200K | 1M | $3 | $3.75 (5 min) · $6 (1 hr) | $0.3 | $15 | |
| 200K-1M | 1M | $3 | $3.75 (5 min) · $6 (1 hr) | $0.3 | $15 | ||
| claude-sonnet-4-6-ddValue zone | - | 1M | $1.65$3 | $2.0625(5m)·$3.3(1h)$3.75(5m)·$6(1h) | $0.165$0.3 | $8.25$15 | |
| claude-sonnet-4-6-rValue zone | - | 1M | $0.6$3 | $0.75(5m)·$1.2(1h)$3.75(5m)·$6(1h) | $0.06$0.3 | $3$15 | |
| claude-opus-4-5-20251101Official resource | - | 200K | $4.75 $5 | $5.9375 (5 min) · $9.50 (1 hr) $6.25 (5 min) × $10 (1 hr) | $0.475 $0.5 | $23.75 $25 | |
| claude-opus-4-5-20251101-ddValue zone | - | 200K | $2.75$5 | $3.4375(5m)$6.25(5m) | $0.275$0.5 | $13.75$25 | |
| claude-sonnet-4-5-20250929Official resource | 1-200K | 200K | $3 | $3.75 (5 min) · $6 (1 hr) | $0.3 | $15 | |
| 200K-1M | 200K | $6 | $7.5 (5 min) × $12 (1 hr) | $0.6 | $22.5 | ||
| claude-sonnet-4-5-20250929-ddValue zone | - | 200K | $1.65$3 | $2.0625(5m)$3.75(5m) | $0.165$0.3 | $8.25$15 | |
| claude-haiku-4-5-20251001Official resource | - | 20K | $1 | $1.25 (5 min) · $2 (1 hr) | $0.1 | $5 | |
| claude-haiku-4-5-20251001-ddValue zone | - | 200K | $0.55$1 | $0.6875(5m)·$1.1(1h)$1.25(5m)·$2(1h) | $0.055$0.1 | $2.75$5 | |
| claude-haiku-4-5-20251001-rValue zone | - | 200K | $0.2$1 | $0.25(5m)·$0.4(1h)$1.25(5m)·$2(1h) | $0.02$0.1 | $1$5 | |
| claude-opus-4-8-ccValue zone | - | 1M | $1.85$5 | $2.3125(5m)·$3.7(1h)$6.25(5m)·$10(1h) | $0.185$0.5 | $9.25$25 | |
| claude-opus-4-6-ccValue zone | - | 1M | $1.85$5 | $2.3125(5m)·$3.7(1h)$6.25(5m)·$10(1h) | $0.185$0.5 | $9.25$25 | |
| claude-opus-4-7-ccValue zone | - | 1M | $1.85$5 | $2.3125(5m)·$3.7(1h)$6.25(5m)·$10(1h) | $0.185$0.5 | $9.25$25 | |
| claude-sonnet-4-6-ccValue zone | - | 1M | $1.11$3 | $1.3875(5m)·$2.22(1h)$3.75(5m)·$6(1h) | $0.111$0.3 | $5.55$15 | |
| claude-haiku-4-5-20251001-ccValue zone | - | 200K | $0.37$1 | $0.4625(5m)·$0.74(1h)$1.25(5m)·$2(1h) | $0.037$0.1 | $1.85$5 |
OpenAI
OpenAI's GPT series of models offer state-of-the-art language understanding and generation capabilities, delivering outstanding performance across a wide range of tasks, and are among the industry's leading AI models.
| Model Name | Input Token Range | Context | Input (/Mt) | Cache Write (/Mt) | Cache read (/Mt) | Output (/Mt) | Operation |
|---|---|---|---|---|---|---|---|
| gpt-6-astraOfficial resource | 1-272K | 1.1M | $9.5 $10 | $11.875(30m)$12.5(30m) | $0.95$1 | $47.5$50 | |
| 272K-1.1M | 1.1M | $19$20 | $23.75(30m)$25(30m) | $1.9 $2 | $71.25 $75 | ||
| gpt-5.6-terra-esValue zone | 1-272K | 3.7M | $0.2$2 | $0.25(30m)$2.5(30m) | $0.02$0.2 | $1.2$12 | |
| 272K-372K | 3.7M | $0.4$4 | $0.5(30m)$5(30m) | $0.04$0.4 | $1.8$18 | ||
| gpt-5.6-luna-esValue zone | 1-272K | 372K | $0.02$0.2 | $0.025(30m)$0.25(30m) | $0.002$0.02 | $0.12$1.2 | |
| 272K-372K | 372K | $0.04$0.4 | $0.05(30m)$0.5(30m) | $0.004$0.04 | $0.18$1.8 | ||
| gpt-5.6-sol-esValue zone | 1-272K | 372K | $0.4$4 | $0.5(30m)$5(30m) | $0.04$0.4 | $2$20 | |
| 272K-372K | 372K | $0.8$8 | $1(30m)$10(30m) | $0.08$0.8 | $3$30 | ||
| gpt-5.6-terraOfficial resource | 1-272K | 1.1M | $2 | $2.5(30m) | $0.2 | $12 | |
| 272K-1.1M | 1.1M | $4 | $5(30m) | $0.4 | $18 | ||
| gpt-5.6-lunaOfficial resource | 1-272K | 1.1M | $0.2 | $0.25(30m) | $0.02 | $1.2 | |
| 272K-1.1M | 1.1M | $0.4 | $0.5(30m) | $0.04 | $1.8 | ||
| gpt-5.6-solOfficial resource | 1-272K | 1.1M | $4 | $5(30m) | $0.4 | $20 | |
| 272K-1.1M | 1.1M | $8 | $10(30m) | $0.8 | $30 | ||
| gpt-5.5-rValue zone | - | 1.1M | $0.5$5 | - | $0.05$0.5 | $3$30 | |
| gpt-5.5Official resource | 1-272K | 1.1M | $4.75 $5 | - | $0.475 $0.5 | $28.5$30 | |
| 272K-1.1M | 1.1M | $9.5 $10 | - | $0.95$1 | $42.75$45 | ||
| gpt-4.1-nanoOfficial resource | - | 1M | $0.095 $0.1 | - | $0.0237 $0.025 | $0.38 $0.4 | |
| gpt-5.5-proOfficial resource | 1-272K | 1.1M | $30 | - | - | $180 | |
| 272K-1.1M | 1.1M | $60 | - | - | $270 | ||
| gpt-5.4-proOfficial resource | 1-272K | 1.1M | $30 | - | - | $180 | |
| 272K-1.1M | 1.1M | $60 | - | - | $270 | ||
| gpt-5.4Official resource | 1-272K | 1.1M | $2.5 | - | $0.25 | $15 | |
| 272K-1.1M | 1.1M | $5 | - | $0.5 | $22.5 | ||
| gpt-5.4-miniOfficial resource | - | 400K | $0.7125 $0.75 | - | $0.0712 $0.075 | $4.275 $4.5 | |
| gpt-5.4-nanoOfficial resource | - | 400K | $0.19 $0.2 | - | $0.019 $0.02 | $1.1875 $1.25 | |
| gpt-5.3-codexOfficial resource | - | 400K | $1.6625 $1.75 | - | $0.1662 $0.175 | $13.3 $14 | |
| gpt-5.2-proOfficial resource | - | 400K | $19.95 $21 | - | - | $159.6 $168 | |
| gpt-5.2-codexOfficial resource | - | 400K | $1.75 | - | $0.175 | $14 | |
| gpt-5.2Official resource | - | 400K | $1.6625 $1.75 | - | $0.1662 $0.175 | $13.3 $14 | |
| gpt-5.1-codex-maxOfficial resource | - | 400K | $1.1875 $1.25 | - | $0.1187 $0.125 | $9.5 $10 | |
| gpt-5.1-codexOfficial resource | - | 400K | $1.1875 $1.25 | - | $0.1187 $0.125 | $9.5 $10 | |
| gpt-5.1-codex-miniOfficial resource | - | 400K | $0.2375 $0.25 | - | $0.0237 $0.025 | $1.9 $2 | |
| gpt-5.1Official resource | - | 400K | $1.1875 $1.25 | - | $0.1187 $0.125 | $9.5 $10 | |
| gpt-5-proOfficial resource | - | 400K | $14.25 $15 | - | - | $114 $120 | |
| gpt-5-codexOfficial resource | - | 400K | $1.1875 $1.25 | - | $0.1187 $0.125 | $9.5 $10 | |
| gpt-5Official resource | - | 400K | $1.1875 $1.25 | - | $0.1187 $0.125 | $9.5 $10 | |
| gpt-5-miniOfficial resource | - | 400K | $0.2375 $0.25 | - | $0.0237 $0.025 | $1.9 $2 | |
| gpt-5-nanoOfficial resource | - | 400K | $0.0475 $0.05 | - | $0.0047 $0.005 | $0.38 $0.4 | |
| gpt-4.1Official resource | - | 1M | $2 | - | $0.5 | $8 | |
| gpt-4.1-miniOfficial resource | - | 1M | $0.4 | - | $0.1 | $1.6 | |
| gpt-4oOfficial resource | - | 131.1K | $2.375 $2.5 | - | $1.1875 $1.25 | $9.5 $10 | |
| gpt-4o-miniOfficial resource | - | 128K | $0.1425 $0.15 | - | $0.0712 $0.075 | $0.57 $0.6 | |
| OpenAI: GPT OSS 20B | - | 131.1K | $0.05 | - | - | $0.2 | |
| OpenAI GPT OSS 120B | - | 131.1K | $0.1 | - | - | $0.5 |
Gemini
Google's Gemini model offers high-quality natural language processing capabilities, performs exceptionally well across a wide range of NLP tasks, and boasts powerful multimodal capabilities.
| Model Name | Input Token Range | Context | Input (/Mt) | Cache Write (/Mt) | Cache read (/Mt) | Output (/Mt) | Operation |
|---|---|---|---|---|---|---|---|
| gemini-3.1-flash-lite | - | 1M | $0.25 | $0.083(5m)·$1(1h) | $0.025 | $1.5 | |
| gemini-3.5-flashOfficial resource | - | 1M | $1.425 $1.5 | $0.0788 (5 min) × $0.95 (1 hr) $0.083 (5 min) × $1 (1 hr) | $0.1425 $0.15 | $8.55$9 | |
| gemini-3.1-pro-previewOfficial resource | 1-204.8K | 1M | $2 | $0.375 (5 min) × $4.5 (1 hr) | $0.2 | $12 | |
| 204.8K-1M | 1M | $4 | $0.375 (5 min) × $4.5 (1 hr) | $0.4 | $18 | ||
| gemini-3-flash-previewOfficial resource | - | 1M | $0.475 $0.5 | $0.0788 (5 min) × $0.95 (1 hr) $0.083 (5 min) × $1 (1 hr) | $0.0475 $0.05 | $2.85 $3 | |
| gemini-2.5-proOfficial resource | - | 1M | $1.1875 $1.25 | $0.3562 (5-month) × $4.275 (1-hour) $0.375 (5 min) × $4.5 (1 hr) | $0.1187 $0.125 | $9.5 $10 | |
| gemini-2.5-pro-preview-06-05Official resource | - | 1M | $1.1875 $1.25 | $0.3562 (5-month) × $4.275 (1-hour) $0.375 (5 min) × $4.5 (1 hr) | $0.1187 $0.125 | $9.5 $10 | |
| gemini-2.5-flash-preview-05-20Official resource | - | 1M | $0.1425 $0.15 | $0.0788 (5 min) × $0.95 (1 hr) $0.083 (5 min) × $1 (1 hr) | $0.0285 $0.03 | $3.325 $3.5 | |
| gemini-2.5-flash | - | 1M | $0.285 $0.3 | $0.0788 (5 min) × $0.95 (1 hr) $0.083 (5 min) × $1 (1 hr) | $0.0285 $0.03 | $2.375 $2.5 | |
| gemini-2.5-flash-lite-preview-09-2025Official resource | - | 1M | $0.095 $0.1 | $0.0788 (5 min) × $0.95 (1 hr) $0.083 (5 min) × $1 (1 hr) | $0.0095 $0.01 | $0.38 $0.4 | |
| gemini-2.5-flash-liteOfficial resource | - | 1M | $0.095 $0.1 | $0.0788 (5 min) × $0.95 (1 hr) $0.083 (5 min) × $1 (1 hr) | $0.0095 $0.01 | $0.38 $0.4 | |
| Gemma 3 27B | - | 32.8K | $0.119 | - | - | $0.2 | |
| Gemma3 12B | - | 131.1K | $0.05 | - | - | $0.1 | |
| gemini-3.8-flash | - | 1M | $0.75 | $0.0417(5m)·$0.5(1h) | $0.075 | $3.75 | |
| gemini-3.7-flash | - | 1M | $0.75 | $0.0417(5m)·$0.5(1h) | $0.075 | $3.75 | |
| gemini-3.6-flashOfficial resource | - | 1M | $0.75 | $0.0417(5m)·$0.5(1h) | $0.075 | $3.75 | |
| gemini-3.5-flash-liteOfficial resource | - | 1M | $0.3 | $0.0833(5m)·$1(1h) | $0.03 | $2.5 |
Llama
Meta's Llama model offers state-of-the-art language understanding capabilities and features an open architecture, making it suitable for a wide range of applications.
Qwen
The Qwen series of models offers powerful natural language processing capabilities and is available in a range of parameter sizes, from lightweight to enterprise-grade solutions.
| Model Name | Input Token Range | Context | Input (/Mt) | Cache read (/Mt) | Output (/Mt) | Operation |
|---|---|---|---|---|---|---|
| Qwen3.5-Plus | 1-256K | 1M | $0.4 | - | $2.4 | |
| 256K-1M | 1M | $1.2 | - | $7.2 | ||
| Qwen3.8 Flash | - | 1M | $0.15 | $0.016 | $0.47 | |
| Qwen3.8 27B | - | 1M | $0.42 | $0.085 | $3 | |
| Qwen3.8 2.4T A95B | - | 1M | $2 | $0.25 | $6 | |
| Qwen3 235B A22B Instruct 2507 | - | 131.1K | $0.15 | - | $0.8 | |
| Qwen 2.5 72B Instruct | - | 32K | $0.38 | - | $0.4 | |
| Qwen MT Plus | - | 4.1K | $0.25 | - | $0.75 | |
| Qwen 2.5 7B Instruct | - | 32K | $0.07 | - | $0.07 | |
| Qwen 2.5 VL 72B Instruction Manual | - | 32.8K | $0.8 | - | $0.8 | |
| Qwen3 30B A3B | - | 41K | $0.09 | - | $0.45 | |
| Qwen3 32B | - | 41K | $0.1 | - | $0.45 | |
| Qwen3 235B A22B | - | 41K | $0.2 | - | $0.8 | |
| Qwen3 235B A22b Thinking 2507 | - | 131.1K | $0.3 | - | $3 | |
| Qwen3 Coder 480B A35B Instructions | - | 262.1K | $0.38 | - | $1.55 | |
| Qwen3 Coder Next FP8 | - | 262.1K | $0.2 | - | $1.5 | |
| Qwen3 Next 80B A3B Instruct | - | 65.5K | $0.15 | - | $1.5 | |
| Qwen3 Next 80B A3B Thinking | - | 65.5K | $0.15 | - | $1.5 | |
| Qwen3.5-27B | - | 262.1K | $0.3 | - | $2.4 | |
| Qwen3.8 Max | - | 1M | $2 | $0.25 | $6 | |
| Qwen3.5-122B-A10B | - | 262.1K | $0.4 | - | $3.2 | |
| Qwen3.5-35B-A3B | - | 262.1K | $0.25 | - | $2 | |
| Qwen3.5-397B-A17B | - | 262.1K | $0.6 | - | $3.6 |
THUDM
The GLM series of models from Tsinghua University feature advanced Chinese language understanding and generation capabilities.
| Model Name | Context | Input (/Mt) | Cache read (/Mt) | Output (/Mt) | Operation |
|---|---|---|---|---|---|
| GLM 5.3 Flash | 1M | $0.15 | $0.03 | $0.5 | |
| GLM 5.3 | 1M | $1.4 | $0.26 | $4.4 | |
| GLM 5.2 | 1M | $1.4 | $0.26 | $4.4 | |
| GLM-5.1 | 204.8K | $1.38 | $0.26 | $4.4 | |
| GLM-5V-Turbo | 204.8K | $1.2 | $0.24 | $4 | |
| GLM 4.5V | 65.5K | $0.6 | - | $1.8 | |
| GLM-4.5 | 131.1K | $0.6 | - | $2.2 | |
| GLM-4.7 | 204.8K | $0.6 | - | $2.2 | |
| GLM-4.7-Flash | 200K | $0.07 | $0.01 | $0.4 | |
| GLM-5 | 204.8K | $1 | $0.2 | $3.2 | |
| GLM-5-Turbo | 202.8K | $1.2 | $0.24 | $4 |
Sao10K
A fine-tuned model specifically optimized for creative and role-playing applications, featuring enhanced storytelling capabilities.
Deepseek
Advanced AI models from DeepSeek, offering cutting-edge inference capabilities and competitive pricing for enterprise and research applications.
| Model Name | Context | Input (/Mt) | Cache Write (/Mt) | Cache read (/Mt) | Output (/Mt) | Operation |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 1M | $0.3 | - | $0.006 | $1.2 | |
| DeepSeek V4 Pro 0813 | 1M | $1.32 | - | $0.044 | $3.96 | |
| DeepSeek V4 Flash Vision Exp | 1M | $0.44 | - | $0.028 | $1.32 | |
| Deepseek V4 Flash 0731 | 1M | $0.44 | - | $0.028 | $1.32 | |
| Deepseek V4 Flash | 1M | $0.14 | - | $0.028 | $0.28 | |
| Deepseek V4 Pro | 1M | $1.6 | - | $0.135 | $3.2 | |
| DeepSeek R1 0528 | 163.8K | $0.7 | - | $0.35 | $2.5 | |
| DeepSeek V3 0324 | 163.8K | $0.28 | $0.14 (5m) | $0.14 | $1.14 | |
| DeepSeek V3.1 | 163.8K | $0.27 | - | - | $1 | |
| DeepSeek-OCR 2 | 8.2K | $0.03 | - | - | $0.03 |
MiniMax
MiniMax AI's advanced language model delivers powerful conversational AI capabilities, excelling in customer service, content generation, and creative applications, with robust multilingual support and enterprise-grade scalability.
Mixture of Experts
A sophisticated collection of state-of-the-art AI models, featuring advanced reasoning and mathematical proof capabilities, as well as cutting-edge language understanding across multiple domains.
| Model Name | Input Token Range | Context | Input (/Mt) | Cache Write (/Mt) | Cache read (/Mt) | Output (/Mt) | Operation |
|---|---|---|---|---|---|---|---|
| Qwen3.5-Plus | 1-256K | 1M | $0.4 | - | - | $2.4 | |
| 256K-1M | 1M | $1.2 | - | - | $7.2 | ||
| DeepSeek V4.1 Flash | - | 1M | $0.3 | - | $0.006 | $1.2 | |
| GLM 5.3 Flash | - | 1M | $0.15 | - | $0.03 | $0.5 | |
| GLM 5.3 | - | 1M | $1.4 | - | $0.26 | $4.4 | |
| DeepSeek V4 Pro 0813 | - | 1M | $1.32 | - | $0.044 | $3.96 | |
| Qwen3.8 Flash | - | 1M | $0.15 | - | $0.016 | $0.47 | |
| DeepSeek V4 Flash Vision Exp | - | 1M | $0.44 | - | $0.028 | $1.32 | |
| Deepseek V4 Flash 0731 | - | 1M | $0.44 | - | $0.028 | $1.32 | |
| Qwen3.8 2.4T A95B | - | 1M | $2 | - | $0.25 | $6 | |
| GLM 5.2 | - | 1M | $1.4 | - | $0.26 | $4.4 | |
| Kimi K2.7 Code | - | 262.1K | $0.95 | - | $0.19 | $4 | |
| MiniMax M3 | 1-524.3K | 1M | $0.3 | - | $0.06 | $1.2 | |
| 524.3K-1M | 1M | $1.2 | - | $0.24 | $4.8 | ||
| Deepseek V4 Flash | - | 1M | $0.14 | - | $0.028 | $0.28 | |
| Deepseek V4 Pro | - | 1M | $1.6 | - | $0.135 | $3.2 | |
| MiniMax M2.7 | - | 204.8K | $0.3 | - | $0.03 | $1.2 | |
| Kimi K2.5 | - | 262.1K | $0.6 | - | $0.1 | $3 | |
| Kimi K2 Instruct | - | 131.1K | $0.57 | - | - | $2.3 | |
| GLM-5.1 | - | 204.8K | $1.38 | - | $0.26 | $4.4 | |
| GLM-5V-Turbo | - | 204.8K | $1.2 | - | $0.24 | $4 | |
| ERNIE 4.5 VL 424B A47B | - | 123K | $0.42 | - | - | $1.25 | |
| OpenAI: GPT OSS 20B | - | 131.1K | $0.05 | - | - | $0.2 | |
| OpenAI GPT OSS 120B | - | 131.1K | $0.1 | - | - | $0.5 | |
| DeepSeek R1 0528 | - | 163.8K | $0.7 | - | $0.35 | $2.5 | |
| DeepSeek V3 0324 | - | 163.8K | $0.28 | $0.14 (5m) | $0.14 | $1.14 | |
| DeepSeek V3.1 | - | 163.8K | $0.27 | - | - | $1 | |
| ERNIE 4.5 300B A47B | - | 123K | $0.28 | - | - | $1.1 | |
| GLM 4.5V | - | 65.5K | $0.6 | - | - | $1.8 | |
| GLM-4.5 | - | 131.1K | $0.6 | - | - | $2.2 | |
| Kimi K2.6 | - | 262.1K | $0.8 | - | $0.16 | $3.4 | |
| GLM-4.7 | - | 204.8K | $0.6 | - | - | $2.2 | |
| GLM-4.7-Flash | - | 200K | $0.07 | - | $0.01 | $0.4 | |
| GLM-5 | - | 204.8K | $1 | - | $0.2 | $3.2 | |
| GLM-5-Turbo | - | 202.8K | $1.2 | - | $0.24 | $4 | |
| Llama 4 Maverick Instructions | - | 1M | $0.17 | - | - | $0.85 | |
| Llama 4 Scout Instructor | - | 131.1K | $0.1 | - | - | $0.5 | |
| MiniMax M1 | - | 1M | $0.55 | - | - | $2.2 | |
| Minimax M2.1 | - | 204.8K | $0.3 | $0.375 (5m) | $0.03 | $1.2 | |
| MiniMax M2.5 | - | 204.8K | $0.3 | - | $0.03 | $1.2 | |
| MiniMax M2.7-highspeed | - | 204.8K | $0.6 | - | $0.06 | $2.4 | |
| MiniMax M2.5-highspeed | - | 204.8K | $0.6 | - | $0.03 | $2.4 | |
| Qwen3 30B A3B | - | 41K | $0.09 | - | - | $0.45 | |
| Qwen3 32B | - | 41K | $0.1 | - | - | $0.45 | |
| Qwen3 235B A22B | - | 41K | $0.2 | - | - | $0.8 | |
| Qwen3 235B A22b Thinking 2507 | - | 131.1K | $0.3 | - | - | $3 | |
| XiaomiMiMo/MiMo-V2-Pro | 1-262.1K | 1M | $1 | - | $0.2 | $3 | |
| 262.1K-1M | 1M | $2 | - | $0.4 | $6 | ||
| Qwen3.8 Max | - | 1M | $2 | - | $0.25 | $6 | |
| XiaomiMiMo/MiMo-V2.5-Pro | 1-262.1K | 1M | $1 | - | $0.2 | $3 | |
| 262.1K-1M | 1M | $2 | - | $0.4 | $6 | ||
| Qwen3.5-122B-A10B | - | 262.1K | $0.4 | - | - | $3.2 | |
| Qwen3.5-35B-A3B | - | 262.1K | $0.25 | - | - | $2 | |
| Qwen3.5-397B-A17B | - | 262.1K | $0.6 | - | - | $3.6 |