Deep Infra
- 77
- Models
- 16
- Labs
Models on this provider
USD per 1M tokens
| Model | Provider model ID | Context | Output | Input $ | Output $ | Cache read | Cache write | Reasoning | Tools | Structured | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|
| deepseek-ai/DeepSeek-V4.1-Flash-1017 | 1.05M | 384K | $0.20 | $0.60 | $0.006 | — | Yes | Yes | Yes | Oct 17, 2026 | |
| XiaomiMiMo/MiMo-V2.6-Flash | 1.05M | 131K | $0.14 | $0.28 | $0.0028 | — | Yes | Yes | Yes | Sep 22, 2026 | |
| XiaomiMiMo/MiMo-V2.6-Pro | 1.05M | 131K | $0.43 | $0.87 | $0.0036 | — | Yes | Yes | Yes | Sep 22, 2026 | |
| stepfun-ai/Step-5-Preview | 1.05M | 1M | $1.00 | $2.70 | $0.10 | — | Yes | Yes | Yes | Sep 20, 2026 | |
| deepseek-ai/DeepSeek-V4.1-Flash | 1.05M | 384K | $0.20 | $0.60 | $0.006 | — | Yes | Yes | Yes | Sep 10, 2026 | |
| deepseek-ai/DeepSeek-V4-Flash-Vision-Exp | 1.05M | 384K | $0.44 | $1.32 | $0.01 | — | Yes | Yes | Yes | Sep 1, 2026 | |
| tencent/Hy4-preview | 1.05M | 64K | $0.83 | $2.50 | $0.04 | — | Yes | Yes | Yes | Aug 28, 2026 | |
| zai-org/GLM-5.3-Flash | 1.05M | 131K | $0.15 | $0.50 | $0.03 | — | Yes | Yes | Yes | Aug 26, 2026 | |
| Qwen/Qwen3.8-Flash | 1M | 131K | $0.11 | $0.38 | $0.01 | — | No | Yes | Yes | Aug 26, 2026 | |
| deepseek-ai/DeepSeek-V4-Pro-0813 | 1.05M | 384K | $1.30 | $2.60 | $0.10 | — | Yes | Yes | Yes | Aug 22, 2026 | |
| zai-org/GLM-5.3 | 1.05M | 131K | $0.90 | $4.00 | $0.20 | — | Yes | Yes | Yes | Aug 14, 2026 | |
| Qwen/Qwen3.8-27B | 262K | 33K | $0.20 | $2.50 | $0.05 | — | Yes | Yes | Yes | Aug 14, 2026 | |
| Qwen/Qwen3.8-2.4T-A95B | 262K | 131K | $2.00 | $6.00 | $0.20 | — | Yes | Yes | Yes | Aug 12, 2026 | |
| Qwen/Qwen3.8-Max | 256K | 131K | $1.65 | $4.95 | $0.21 | — | No | Yes | Yes | Aug 3, 2026 | |
| deepseek-ai/DeepSeek-V4-Flash-0731 | 1.05M | 384K | $0.06 | $0.18 | $0.01 | — | Yes | Yes | Yes | Jul 31, 2026 | |
| thinkingmachines/Inkling-Small | 524K | 1.05M | $0.45 | $1.20 | $0.10 | — | Yes | Yes | Yes | Jul 30, 2026 | |
| moonshotai/Kimi-K3 | 1.05M | 131K | $2.85 | $14.25 | $0.28 | $3.56 | Yes | Yes | Yes | Jul 16, 2026 | |
| thinkingmachines/Inkling | 524K | 1.05M | $0.95 | $4.05 | $0.16 | — | Yes | Yes | Yes | Jul 15, 2026 | |
| tencent/Hy3 | 262K | 128K | $0.13 | $0.53 | $0.03 | — | Yes | Yes | Yes | Jul 6, 2026 | |
| zai-org/GLM-5.2 | 1.05M | 33K | $0.75 | $2.40 | $0.14 | $0.94 | Yes | Yes | Yes | Jun 13, 2026 | |
| moonshotai/Kimi-K2.7-Code | 262K | 262K | $0.68 | $3.40 | $0.14 | $0.85 | Yes | Yes | Yes | Jun 12, 2026 | |
| anthropic/claude-fable-5 | 1M | 128K | $10.00 | $50.00 | — | — | Yes | Yes | Yes | Jun 9, 2026 | |
| MiniMaxAI/MiniMax-M3 | 524K | 512K | $0.28 | $1.10 | $0.06 | — | Yes | Yes | Yes | Jun 1, 2026 | |
| stepfun-ai/Step-3.7-Flash | 262K | 256K | $0.20 | $1.15 | $0.04 | — | Yes | Yes | Unknown | May 29, 2026 | |
| Qwen/Qwen3.7-Max | 256K | 131K | $2.50 | $7.50 | $0.50 | — | No | Yes | Yes | May 21, 2026 | |
| nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning | 262K | 66K | $0.20 | $0.80 | — | — | Yes | Yes | Yes | Apr 28, 2026 | |
| deepseek-ai/DeepSeek-V4-Flash | 1.05M | 16K | $0.09 | $0.18 | $0.02 | $0.11 | Yes | Yes | Yes | Apr 24, 2026 | |
| deepseek-ai/DeepSeek-V4-Pro | 1.05M | 16K | $1.30 | $2.60 | $0.10 | — | Yes | Yes | Yes | Apr 24, 2026 | |
| XiaomiMiMo/MiMo-V2.5 | 262K | 16K | $0.14 | $0.28 | $0.0028 | — | Yes | Yes | Yes | Apr 22, 2026 | |
| XiaomiMiMo/MiMo-V2.5-Pro | 1.05M | 16K | $1.00 | $3.00 | $0.20 | — | Yes | Yes | Yes | Apr 22, 2026 | |
| Qwen/Qwen3.6-27B | 262K | 66K | $0.32 | $3.20 | — | — | Yes | Yes | Yes | Apr 22, 2026 | |
| moonshotai/Kimi-K2.6 | 262K | 16K | $0.75 | $3.50 | $0.15 | — | Yes | Yes | Yes | Apr 20, 2026 | |
| Qwen/Qwen3.6-35B-A3B | 262K | 82K | $0.10 | $0.95 | $0.10 | — | Yes | Yes | Yes | Apr 17, 2026 | |
| zai-org/GLM-5.1 | 203K | 16K | $1.05 | $3.50 | $0.20 | — | Yes | Yes | Yes | Apr 7, 2026 | |
| google/gemma-4-26B-A4B-it | 262K | 33K | $0.07 | $0.34 | — | — | Yes | Yes | Yes | Apr 2, 2026 | |
| google/gemma-4-31B-it | 262K | 33K | $0.20 | $0.40 | — | — | Yes | Yes | Yes | Apr 2, 2026 | |
| google/gemma-4-E4B-it | 131K | 8K | $0.02 | $0.10 | — | — | Yes | Yes | Yes | Apr 2, 2026 | |
| MiniMaxAI/MiniMax-M2.7 | 197K | 131K | $0.25 | $1.00 | $0.05 | — | Yes | Yes | Unknown | Mar 18, 2026 | |
| Qwen/Qwen3.5-122B-A10B | 262K | 66K | $0.29 | $2.40 | — | — | Yes | Yes | Yes | Feb 23, 2026 | |
| Qwen/Qwen3.5-27B | 262K | 66K | $0.26 | $2.60 | — | — | Yes | Yes | Yes | Feb 23, 2026 | |
| Qwen/Qwen3.5-35B-A3B | 262K | 82K | $0.14 | $1.00 | $0.05 | — | Yes | Yes | Yes | Feb 23, 2026 | |
| Qwen/Qwen3.5-9B | 262K | 66K | $0.10 | $0.15 | — | — | Yes | Yes | Yes | Feb 23, 2026 | |
| Qwen/Qwen3.5-397B-A17B | 262K | 82K | $0.45 | $3.00 | $0.22 | — | Yes | Yes | Yes | Feb 15, 2026 | |
| ByteDance/Seed-2.0-code | 256K | 131K | $0.50 | $3.00 | $0.10 | — | Yes | Yes | Yes | Feb 14, 2026 | |
| ByteDance/Seed-2.0-mini | 256K | 32K | $0.10 | $0.40 | $0.02 | — | Yes | Yes | Yes | Feb 14, 2026 | |
| ByteDance/Seed-2.0-pro | 256K | 128K | $0.50 | $3.00 | $0.10 | — | Yes | Yes | Yes | Feb 14, 2026 | |
| zai-org/GLM-5 | 203K | 16K | $0.60 | $2.08 | $0.12 | — | Yes | Yes | Yes | Feb 12, 2026 | |
| MiniMaxAI/MiniMax-M2.5 | 197K | 131K | $0.15 | $1.15 | $0.03 | — | Yes | Yes | Unknown | Feb 12, 2026 | |
| moonshotai/Kimi-K2.5 | 262K | 33K | $0.45 | $2.25 | $0.07 | — | Yes | Yes | Yes | Jan 27, 2026 | |
| zai-org/GLM-4.7-Flash | 203K | 16K | $0.06 | $0.40 | $0.01 | — | Yes | Yes | Yes | Jan 19, 2026 | |
| zai-org/GLM-4.7 | 203K | 16K | $0.40 | $1.75 | $0.08 | — | Yes | Yes | Yes | Dec 22, 2025 | |
| nvidia/Nemotron-3-Nano-30B-A3B | 262K | 262K | $0.05 | $0.20 | $0.03 | — | Yes | Yes | Unknown | Dec 15, 2025 | |
| deepseek-ai/DeepSeek-V3.2 | 164K | 64K | $0.26 | $0.38 | $0.13 | — | Yes | Yes | Yes | Dec 1, 2025 | |
| Qwen/Qwen3-VL-30B-A3B-Instruct | 262K | 33K | $0.15 | $0.60 | — | — | No | Yes | Yes | Oct 4, 2025 | |
| zai-org/GLM-4.6 | 203K | 131K | $0.50 | $2.00 | $0.10 | — | Yes | Yes | Yes | Sep 30, 2025 | |
| Qwen/Qwen3-Max | 256K | 66K | $1.20 | $6.00 | $0.24 | — | No | Yes | Yes | Sep 23, 2025 | |
| Qwen/Qwen3-VL-235B-A22B-Instruct | 262K | 33K | $0.20 | $0.88 | $0.11 | — | No | Yes | Yes | Sep 23, 2025 | |
| Qwen/Qwen3-Next-80B-A3B-Instruct | 262K | 33K | $0.09 | $1.10 | — | — | No | Yes | Yes | Sep 2025 | |
| deepseek-ai/DeepSeek-V3.1 | 164K | 8K | $0.25 | $0.95 | $0.13 | — | Yes | Yes | Yes | Aug 21, 2025 | |
| openai/gpt-oss-120b | 131K | 16K | $0.04 | $0.17 | — | — | Yes | Yes | Yes | Aug 5, 2025 | |
| openai/gpt-oss-20b | 131K | 16K | $0.03 | $0.14 | — | — | Yes | Yes | Yes | Aug 5, 2025 | |
| nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 | 131K | 131K | $0.40 | $0.40 | — | — | Yes | Yes | Yes | Jul 25, 2025 | |
| Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | 262K | 67K | $0.30 | $1.00 | $0.10 | — | No | Yes | Yes | Jul 22, 2025 | |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | 262K | 16K | $0.09 | $0.55 | — | — | No | Yes | Yes | Jul 21, 2025 | |
| deepseek-ai/DeepSeek-R1-0528 | 164K | 64K | $0.50 | $2.15 | $0.35 | — | Yes | Yes | Yes | May 28, 2025 | |
| meta-llama/Llama-Guard-4-12B | 164K | 164K | $0.18 | $0.18 | — | — | No | No | Unknown | Apr 29, 2025 | |
| Qwen/Qwen3-30B-A3B | 41K | 16K | $0.12 | $0.50 | — | — | Yes | Yes | Yes | Apr 28, 2025 | |
| Qwen/Qwen3-32B | 41K | 16K | $0.08 | $0.28 | — | — | Yes | Yes | Yes | Apr 28, 2025 | |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | 1.05M | 16K | $0.20 | $0.80 | — | — | No | No | Yes | Apr 5, 2025 | |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | 328K | 16K | $0.10 | $0.30 | — | — | No | Yes | Yes | Apr 5, 2025 | |
| deepseek-ai/DeepSeek-V3-0324 | 164K | 164K | $0.24 | $0.90 | $0.14 | — | No | Yes | Yes | Mar 24, 2025 | |
| google/gemma-3-12b-it | 131K | 131K | $0.05 | $0.15 | — | — | No | Yes | Yes | Mar 12, 2025 | |
| google/gemma-3-27b-it | 131K | 131K | $0.08 | $0.16 | — | — | No | Yes | Yes | Mar 12, 2025 | |
| google/gemma-3-4b-it | 131K | 131K | $0.05 | $0.10 | — | — | No | Yes | Yes | Mar 12, 2025 | |
| mistralai/Mistral-Small-24B-Instruct-2501 | 33K | 16K | $0.05 | $0.08 | — | — | No | No | Yes | Jan 30, 2025 | |
| deepseek-ai/DeepSeek-V3 | 164K | 8K | $0.32 | $0.89 | — | — | No | Yes | Yes | Dec 26, 2024 | |
| meta-llama/Llama-3.3-70B-Instruct-Turbo | 131K | 16K | $0.10 | $0.32 | — | — | No | Yes | Yes | Dec 6, 2024 |