All Providers
60 Models
17 Families
1.0M Max Context
$0.02–$2.85 Input Cost/MTok
$0.10–$14.25 Output Cost/MTok
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Setup
Set the following environment variable to use Deep Infra:
DEEPINFRA_API_KEY Models (60)
| Model | Model ID | Input Cost | Output Cost | Context | Capabilities |
|---|---|---|---|---|---|
| Gemma 4 E4B IT gemma | google/gemma-4-E4B-it | $0.02/MTok | $0.10/MTok | 131.1K | Reasoning Tools Open |
| GPT OSS 20B gpt-oss | openai/gpt-oss-20b | $0.03/MTok | $0.14/MTok | 131.1K | Reasoning Tools Open |
| GPT OSS 120B gpt-oss | openai/gpt-oss-120b | $0.04/MTok | $0.17/MTok | 131.1K | Reasoning Tools Open |
| Nemotron 3 Nano 30B A3B nemotron | nvidia/Nemotron-3-Nano-30B-A3B | $0.05/MTok | $0.20/MTok | 262.1K | Reasoning Tools Open |
| GLM-4.7-Flash glm-flash | zai-org/GLM-4.7-Flash | $0.06/MTok | $0.40/MTok | 202.8K | Reasoning Tools Open |
| Gemma 4 26B A4B IT gemma | google/gemma-4-26B-A4B-it | $0.07/MTok | $0.34/MTok | 262.1K | Reasoning Tools Open |
| DeepSeek V4 Flash 0731 deepseek-flash | deepseek-ai/DeepSeek-V4-Flash-0731 | $0.08/MTok | $0.18/MTok | 1.0M | Reasoning Tools Open |
| Qwen3 32B qwen | Qwen/Qwen3-32B | $0.08/MTok | $0.28/MTok | 41.0K | Reasoning Tools Open |
| DeepSeek V4 Flash deepseek-flash | deepseek-ai/DeepSeek-V4-Flash | $0.09/MTok | $0.18/MTok | 1.0M | Reasoning Tools Open |
| Qwen3 235B-A22B Instruct 2507 qwen | Qwen/Qwen3-235B-A22B-Instruct-2507 | $0.09/MTok | $0.55/MTok | 262.1K | Tools Open |
| Qwen3-Next 80B-A3B Instruct qwen | Qwen/Qwen3-Next-80B-A3B-Instruct | $0.09/MTok | $1.10/MTok | 262.1K | Tools Open |
| Seed 2.0 Mini seed | ByteDance/Seed-2.0-mini | $0.10/MTok | $0.40/MTok | 256K | Reasoning Tools |
| Qwen3.5 9B qwen | Qwen/Qwen3.5-9B | $0.10/MTok | $0.15/MTok | 262.1K | Reasoning Tools Open |
| Qwen3.6 35B A3B qwen | Qwen/Qwen3.6-35B-A3B | $0.10/MTok | $0.95/MTok | 262.1K | Reasoning Tools Open |
| Llama 3.3 70B Turbo llama | meta-llama/Llama-3.3-70B-Instruct-Turbo | $0.10/MTok | $0.32/MTok | 131.1K | Tools Open |
| Llama 4 Scout 17B llama | meta-llama/Llama-4-Scout-17B-16E-Instruct | $0.10/MTok | $0.30/MTok | 327.7K | Tools Open |
| Qwen3 30B A3B qwen | Qwen/Qwen3-30B-A3B | $0.12/MTok | $0.50/MTok | 41.0K | Reasoning Tools Open |
| Gemma 4 31B IT gemma | google/gemma-4-31B-it | $0.13/MTok | $0.38/MTok | 262.1K | Reasoning Tools Open |
| Hy3 Hy | tencent/Hy3 | $0.14/MTok | $0.58/MTok | 262.1K | Reasoning Tools Open |
| Qwen 3.5 35B A3B qwen | Qwen/Qwen3.5-35B-A3B | $0.14/MTok | $1/MTok | 262.1K | Reasoning Tools Open |
| MiniMax M2.5 minimax | MiniMaxAI/MiniMax-M2.5 | $0.15/MTok | $1.15/MTok | 196.6K | Reasoning Tools Open |
| Nemotron 3 Nano Omni 30B A3B Reasoning nemotron | nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning | $0.20/MTok | $0.80/MTok | 262.1K | Reasoning Tools Open |
| Step 3.7 Flash | stepfun-ai/Step-3.7-Flash | $0.20/MTok | $1.15/MTok | 262.1K | Reasoning Tools Open |
| Qwen3 VL 235B A22B Instruct qwen | Qwen/Qwen3-VL-235B-A22B-Instruct | $0.20/MTok | $0.88/MTok | 262.1K | Tools Open |
| Llama 4 Maverick 17B FP8 llama | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | $0.20/MTok | $0.80/MTok | 1.0M | Open |
| DeepSeek V3 0324 deepseek | deepseek-ai/DeepSeek-V3-0324 | $0.24/MTok | $0.90/MTok | 163.8K | Tools Open |
| MiniMax-M2.7 minimax | MiniMaxAI/MiniMax-M2.7 | $0.25/MTok | $1/MTok | 196.6K | Reasoning Tools Open |
| DeepSeek-V3.1 deepseek | deepseek-ai/DeepSeek-V3.1 | $0.25/MTok | $0.95/MTok | 163.8K | Reasoning Tools Open |
| DeepSeek-V3.2 | deepseek-ai/DeepSeek-V3.2 | $0.26/MTok | $0.38/MTok | 163.8K | Reasoning Tools |
| Qwen3.5 27B qwen | Qwen/Qwen3.5-27B | $0.26/MTok | $2.60/MTok | 262.1K | Reasoning Tools Open |
| MiniMax-M3 minimax | MiniMaxAI/MiniMax-M3 | $0.28/MTok | $1.10/MTok | 524.3K | Reasoning Tools Open |
| Qwen3.5 122B-A10B qwen | Qwen/Qwen3.5-122B-A10B | $0.29/MTok | $2.40/MTok | 262.1K | Reasoning Tools Open |
| Qwen3 Coder 480B A35B Instruct Turbo qwen | Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | $0.30/MTok | $1/MTok | 262.1K | Tools Open |
| DeepSeek-V3 deepseek | deepseek-ai/DeepSeek-V3 | $0.32/MTok | $0.89/MTok | 163.8K | Tools Open |
| Qwen3.6 27B qwen | Qwen/Qwen3.6-27B | $0.32/MTok | $3.20/MTok | 262.1K | Reasoning Tools Open |
| MiMo-V2.5 mimo | XiaomiMiMo/MiMo-V2.5 | $0.40/MTok | $2/MTok | 262.1K | Reasoning Tools Open |
| Llama 3.3 Nemotron Super 49B v1.5 nemotron | nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 | $0.40/MTok | $0.40/MTok | 131.1K | Reasoning Tools Open |
| Qwen3.8 27B qwen | Qwen/Qwen3.8-27B | $0.40/MTok | $3/MTok | 262.1K | Reasoning Tools Open |
| GLM-4.7 glm | zai-org/GLM-4.7 | $0.40/MTok | $1.75/MTok | 202.8K | Reasoning Tools Open |
| Kimi K2.5 kimi-k2 | moonshotai/Kimi-K2.5 | $0.45/MTok | $2.25/MTok | 262.1K | Reasoning Tools Open |
| Qwen 3.5 397B A17B qwen | Qwen/Qwen3.5-397B-A17B | $0.45/MTok | $3/MTok | 262.1K | Reasoning Tools Open |
| Inkling Small ling | thinkingmachines/Inkling-Small | $0.45/MTok | $1.20/MTok | 524.3K | Reasoning Tools Open |
| Seed 2.0 Code seed | ByteDance/Seed-2.0-code | $0.50/MTok | $3/MTok | 256K | Reasoning Tools |
| Seed 2.0 Pro seed | ByteDance/Seed-2.0-pro | $0.50/MTok | $3/MTok | 256K | Reasoning Tools |
| DeepSeek-R1-0528 | deepseek-ai/DeepSeek-R1-0528 | $0.50/MTok | $2.15/MTok | 163.8K | Reasoning Tools |
| GLM-4.6 glm | zai-org/GLM-4.6 | $0.50/MTok | $2/MTok | 202.8K | Reasoning Tools Open |
| GLM-5 glm | zai-org/GLM-5 | $0.60/MTok | $2.08/MTok | 202.8K | Reasoning Tools Open |
| Kimi K2.7 Code kimi-k2 | moonshotai/Kimi-K2.7-Code | $0.68/MTok | $3.40/MTok | 262.1K | Reasoning Tools Open |
| Kimi K2.6 kimi-k2 | moonshotai/Kimi-K2.6 | $0.75/MTok | $3.50/MTok | 262.1K | Reasoning Tools Open |
| GLM-5.2 glm | zai-org/GLM-5.2 | $0.75/MTok | $2.40/MTok | 1.0M | Reasoning Tools Open |
| Inkling ling | thinkingmachines/Inkling | $0.95/MTok | $4.05/MTok | 524.3K | Reasoning Tools Open |
| MiMo-V2.5-Pro mimo | XiaomiMiMo/MiMo-V2.5-Pro | $1/MTok | $3/MTok | 1.0M | Reasoning Tools Open |
| GLM-5.1 glm | zai-org/GLM-5.1 | $1.05/MTok | $3.50/MTok | 202.8K | Reasoning Tools Open |
| Qwen3 Max qwen | Qwen/Qwen3-Max | $1.20/MTok | $6/MTok | 256K | Tools |
| DeepSeek V4 Pro deepseek-thinking | deepseek-ai/DeepSeek-V4-Pro | $1.30/MTok | $2.60/MTok | 1.0M | Reasoning Tools Open |
| DeepSeek V4 Pro 0813 deepseek-thinking | deepseek-ai/DeepSeek-V4-Pro-0813 | $1.30/MTok | $2.60/MTok | 1.0M | Reasoning Tools |
| Qwen3.8 Max qwen | Qwen/Qwen3.8-Max | $1.65/MTok | $4.95/MTok | 256K | Tools |
| Qwen3.8 2.4T A95B qwen | Qwen/Qwen3.8-2.4T-A95B | $2/MTok | $6/MTok | 262.1K | Reasoning Tools Open |
| Qwen3.7 Max qwen | Qwen/Qwen3.7-Max | $2.50/MTok | $7.50/MTok | 256K | Tools |
| Kimi K3 kimi-k3 | moonshotai/Kimi-K3 | $2.85/MTok | $14.25/MTok | 1.0M | Reasoning Tools Open |