Loading price history...
Current Pricing
| Model / Service | Type | Input | Output | Unit |
|---|---|---|---|---|
| baai/bge-base-en-v1.5 | tokens | $0.0080 | - | /1M tokens |
| BGE Large EN v1.5 | tokens_input | $0.020 | - | /1M tokens |
| DeepSeek ai/DeepSeek-R1 | tokens | $3.00 | $7.00 | /1M tokens |
| DeepSeek ai/DeepSeek-R1-0528-tput | tokens | $0.550 | $2.19 | /1M tokens |
| DeepSeek ai/DeepSeek-V3 | tokens | $1.25 | $1.25 | /1M tokens |
| DeepSeek ai/DeepSeek-V3.1 | tokens | $0.600 | $1.70 | /1M tokens |
| DeepSeek R1 | tokens | $3.00 | $7.00 | /1M tokens |
| DeepSeek-R1-0528 | tokens_output | $3.00 | $7.00 | /1M tokens |
| DeepSeek R1 Distill Llama 70B | tokens_output | $2.00 | $2.00 | /1M tokens |
| DeepSeek V3 | tokens_output | $0.900 | $0.900 | /1M tokens |
| DeepSeek-V3.1 | tokens_output | $0.600 | $1.25 | /1M tokens |
| gpt-oss-120B | tokens_output | $0.150 | $0.600 | /1M tokens |
| gpt-oss-120BGPT-OSS | tokens_output | $0.150 | $0.600 | /1M tokens |
| gpt-oss-20BGPT-OSS | tokens_output | $0.050 | $0.200 | /1M tokens |
| Kimi K2.5 | tokens_output | $0.500 | $2.80 | /1M tokens |
| Kimi K2.5Kimi | tokens_output | $0.500 | $2.80 | /1M tokens |
| Kimi K2 InstructKimi | tokens_output | $1.00 | $3.00 | /1M tokens |
| Kimi K2 ThinkingKimi | tokens_output | $1.20 | $4.00 | /1M tokens |
| Kimi K2 ThinkingKimi K2 Instruct-0905Kimi K2 InstructKimi K2 Base | tokens_output | $15.00 | $37.50 | /1M tokens |
| LLaMA-2Llama | tokens_output | $0.900 | $0.900 | /1M tokens |
| Llama 3.1 405B | tokens | $3.50 | $3.50 | /1M tokens |
| Llama 3.1 405B Instruct Turbo | tokens_output | $3.50 | $3.50 | /1M tokens |
| Llama 3.1 405BLlama | tokens_output | $3.50 | $3.50 | /1M tokens |
| Llama 3.1 70B | tokens | $0.880 | $0.880 | /1M tokens |
| Llama 3.1 70B Instruct Turbo | tokens_output | $0.880 | $0.880 | /1M tokens |
| Llama 3.1 70BLlama | tokens_output | $0.880 | $0.880 | /1M tokens |
| Llama 3.1 8B | tokens | $0.180 | $0.180 | /1M tokens |
| Llama 3.1 8B Instruct Turbo | tokens_output | $0.180 | $0.180 | /1M tokens |
| Llama 3.1 8BLlama | tokens_output | $0.180 | $0.180 | /1M tokens |
| Llama 3.2 11B Vision (Free) | tokens_input | Free | - | /1M tokens |
| Llama 3.2 3B Instruct TurboLlama | tokens_output | $0.060 | $0.060 | /1M tokens |
| Llama 3.3 70B | tokens_output | $0.880 | $0.880 | /1M tokens |
| Llama 3.3 70B Instruct Turbo | tokens_output | $0.880 | $0.880 | /1M tokens |
| Llama 3.3-70B-Instruct-Turbo | tokens | $0.880 | $0.880 | /1M tokens |
| Llama 3.3-70B-Instruct-Turbo-Free | tokens | Free | - | /1M tokens |
| Llama 3.3 70BLlama | tokens_output | $0.880 | $0.880 | /1M tokens |
| Llama 3 70B Instruct ReferenceLlama | tokens_output | $0.880 | $0.880 | /1M tokens |
| Llama 3 8B Instruct LiteLlama | tokens_output | $0.100 | $0.100 | /1M tokens |
| Llama 4 Maverick | tokens_output | $0.270 | $0.850 | /1M tokens |
| Llama 4-Maverick-17B-128E-Instruct-FP8 | tokens | $0.270 | $0.850 | /1M tokens |
| Llama 4 MaverickLlama | tokens_output | $0.270 | $0.850 | /1M tokens |
| Llama 4 MaverickLlama 4 Maverick Instruct | tokens_output | $8.00 | $20.00 | /1M tokens |
| Llama 4 Scout | tokens_output | $0.180 | $0.590 | /1M tokens |
| Llama 4-Scout-17B-16E Instruct | tokens | $0.180 | $0.590 | /1M tokens |
| Llama 4 ScoutLlama | tokens_output | $0.180 | $0.590 | /1M tokens |
| Llama 4 ScoutLlama 4 Scout Instruct | tokens_output | $3.00 | $7.50 | /1M tokens |
| Llama Guard 2 8B | tokens_output | $0.200 | $0.200 | /1M tokens |
| Llama Guard 3 11B Vision Turbo | tokens_output | $0.180 | $0.180 | /1M tokens |
| Llama Guard 3 8B | tokens_output | $0.200 | $0.200 | /1M tokens |
| Llama Guard 4 12B | tokens_output | $0.200 | $0.200 | /1M tokens |
| LlamaRank | tokens_output | $0.100 | $0.100 | /1M tokens |
| M2-BERT 80M 8K | tokens_input | $0.0080 | - | /1M tokens |
| Meta-Llama-3.1-405B-Instruct-Turbo | tokens | $3.50 | $3.50 | /1M tokens |
| Meta-Llama-3.1-70B-Instruct-Turbo | tokens | $0.880 | $0.880 | /1M tokens |
| Meta-Llama-3.1-8B-Instruct-Turbo | tokens | $0.180 | $0.180 | /1M tokens |
| Mistral 7B Instruct | tokens_output | $0.200 | $0.200 | /1M tokens |
| Mistral 7B Instruct v0.3 | tokens_output | $0.200 | $0.200 | /1M tokens |
| Mixtral 8x22B Instruct | tokens_output | $1.20 | $1.20 | /1M tokens |
| Mixtral 8x7B Instruct | tokens_output | $0.600 | $0.600 | /1M tokens |
| Mixtral-8x7B-Instruct-v0.1 | tokens | $0.600 | $0.600 | /1M tokens |
| moonshotai/Kimi-K2.5 | tokens | $0.500 | $2.80 | /1M tokens |
| moonshotai/Kimi-K2 Instruct | tokens | $1.00 | $3.00 | /1M tokens |
| openai/gpt-oss-120b | tokens | $0.150 | $0.600 | /1M tokens |
| openai/gpt-oss-20b | tokens | $0.050 | $0.200 | /1M tokens |
| Qwen 2.5 72B | tokens | $1.20 | $1.20 | /1M tokens |
| Qwen2.5 72B | tokens_output | $1.20 | $1.20 | /1M tokens |
| Qwen 2.5 72B Instruct Turbo | tokens_output | $1.20 | $1.20 | /1M tokens |
| Qwen2.5 72BQwen | tokens_output | $1.20 | $1.20 | /1M tokens |
| Qwen 2.5 7B Instruct Turbo | tokens_output | $0.300 | $0.300 | /1M tokens |
| Qwen2.5 7B Instruct TurboQwen | tokens_output | $0.300 | $0.300 | /1M tokens |
| Qwen2.5 Coder 32B InstructQwen | tokens_output | $0.800 | $0.800 | /1M tokens |
| Qwen2.5-VL 72B InstructQwen | tokens_output | $1.95 | $8.00 | /1M tokens |
| Qwen3 235B A22B FP8 ThroughputQwen | tokens_output | $0.200 | $0.600 | /1M tokens |
| Qwen3 235B A22B Instruct 2507 FP8Qwen | tokens_output | $0.200 | $0.600 | /1M tokens |
| Qwen3-235B-A22BQwen3-235B-A22B-Instruct-2507 | tokens_output | $6.00 | $15.00 | /1M tokens |
| Qwen3 235B A22B Thinking 2507 FP8Qwen | tokens_output | $0.650 | $3.00 | /1M tokens |
| Qwen3-Coder-480B-A35B-Instruct | tokens_output | $9.00 | $22.50 | /1M tokens |
| Qwen3-Coder 480B A35B InstructQwen | tokens_output | $2.00 | $2.00 | /1M tokens |
| Qwen3-Coder-Next | tokens_output | $0.500 | $1.20 | /1M tokens |
| Qwen3-Next-80B-A3B-InstructQwen | tokens_output | $0.150 | $1.50 | /1M tokens |
| Qwen3-Next-80B-A3B-ThinkingQwen | tokens_output | $0.150 | $1.50 | /1M tokens |
| Qwen3-VL-32B-InstructQwen | tokens_output | $0.500 | $1.50 | /1M tokens |
| Qwen Image | tokens_output | $0.0058 | $0.0058 | /1M tokens |
| Qwen Image Edit | tokens_output | $0.0032 | $0.0032 | /1M tokens |
| Qwen/Qwen3-235B-A22B-fp8-tput | tokens | $0.200 | $0.600 | /1M tokens |
| Qwen/Qwen3-235B-A22B-Instruct-2507-tput | tokens | $0.200 | $6.00 | /1M tokens |
| Qwen/Qwen3.5-397B-A17B | tokens | $0.600 | $3.60 | /1M tokens |
| Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | tokens | $2.00 | $2.00 | /1M tokens |
| Qwen/Qwen3-Next-80B-A3B Instruct | tokens | $0.150 | $1.50 | /1M tokens |
| Qwen/Qwen3-Next-80B-A3B-Thinking | tokens | $0.150 | $1.50 | /1M tokens |
| Qwen QwQ-32BQwen | tokens_output | $1.20 | $1.20 | /1M tokens |
| together-ai-21.1b-41b | tokens | $0.800 | $0.800 | /1M tokens |
| together-ai-41.1b-80b | tokens | $0.900 | $0.900 | /1M tokens |
| together-ai-4.1b-8b | tokens | $0.200 | $0.200 | /1M tokens |
| together-ai-81.1b-110b | tokens | $1.80 | $1.80 | /1M tokens |
| together-ai-8.1b-21b | tokens | $0.300 | $0.300 | /1M tokens |
| together-ai-embedding-151m-to-350m | tokens | $0.016 | - | /1M tokens |
| together-ai-embedding-up-to-150m | tokens | $0.0080 | - | /1M tokens |
| together-ai-up-to-4b | tokens | $0.100 | $0.100 | /1M tokens |
| zai-org/GLM-4.5-Air-FP8 | tokens | $0.200 | $1.10 | /1M tokens |
| zai-org/GLM-4.6 | tokens | $0.600 | $2.20 | /1M tokens |
| zai-org/GLM-4.7 | tokens | $0.450 | $2.00 | /1M tokens |