DeepInfra
Catalogue / DeepInfra
DeepInfra currently lists 113 offers we track. The lowest output price is mistralai/Mistral-Nemo-Instruct-2407 at $0.030, the highest is anthropic/claude-fable-5 at $50.00. 13 more are no longer listed by DeepInfra. These are the prices DeepInfra charges as a seller, which are not necessarily the list prices of the vendor whose name a model carries.
Read between 22 September 2026 and 3 November 2026. Every figure below carries the date it was observed on its own page.
DeepInfra prices per model
| Model | Input | Output | Context | Last read |
|---|---|---|---|---|
| anthropic/claude-fable-5 | $10.00 | $50.00 | 1 000 000 | 28 October 2026 |
| anthropic/claude-opus-4-7 | $5.00 | $25.00 | 1 000 000 | 28 October 2026 |
| anthropic/claude-opus-4-8 | $5.00 | $25.00 | 1 000 000 | 28 October 2026 |
| anthropic/claude-opus-5 | $5.00 | $25.00 | 1 000 000 | 28 October 2026 |
| anthropic/claude-opus-5-5 | $4.00 | $20.00 | 1 000 000 | 29 October 2026 |
| anthropic/claude-sonnet-4-6 | $3.00 | $15.00 | 1 000 000 | 28 October 2026 |
| anthropic/claude-sonnet-5 | $3.00 | $15.00 | 1 000 000 | 28 October 2026 |
| moonshotai/Kimi-K3 | $2.85 | $14.25 | 1 048 576 | 3 November 2026 |
| google/gemini-3.1-pro | $2.00 | $12.00 | 1 000 000 | 28 October 2026 |
| anthropic/claude-sonnet-5-5 | $2.00 | $10.00 | 1 000 000 | 28 October 2026 |
| google/gemini-2.5-pro | $1.25 | $10.00 | 1 000 000 | 28 October 2026 |
| google/gemini-3.5-flash | $1.50 | $9.00 | 1 000 000 | 28 October 2026 |
| Qwen/Qwen3.7-Max | $2.50 | $7.50 | 256 000 | 28 October 2026 |
| Qwen/Qwen3.8-2.4T-A95B | $2.00 | $6.00 | 262 144 | 3 November 2026 |
| anthropic/claude-haiku-4-5 | $1.00 | $5.00 | 200 000 | 28 October 2026 |
| Qwen/Qwen3.8-Max | $1.65 | $4.951 | 256 000 | 28 October 2026 |
| thinkingmachines/Inkling | $0.950 | $4.05 | 524 288 | 3 November 2026 |
| zai-org/GLM-5.3 | $0.900 | $4.00 | 1 048 576 | 3 November 2026 |
| google/gemini-3.7-flash | $0.750 | $3.75 | 1 000 000 | 28 October 2026 |
| moonshotai/Kimi-K2.6 | $0.750 | $3.50 | 262 144 | 3 November 2026 |
| zai-org/GLM-5.1 | $1.05 | $3.50 | 202 752 | 3 November 2026 |
| moonshotai/Kimi-K2.7-Code | $0.680 | $3.40 | 262 144 | 3 November 2026 |
| Qwen/Qwen3.6-27B | $0.320 | $3.20 | 262 144 | 3 November 2026 |
| ByteDance/Seed-2.0-code | $0.500 | $3.00 | 256 000 | 28 October 2026 |
| ByteDance/Seed-2.0-pro | $0.500 | $3.00 | 256 000 | 28 October 2026 |
| Qwen/Qwen3.5-397B-A17B | $0.450 | $3.00 | 262 144 | 3 November 2026 |
| XiaomiMiMo/MiMo-V2.5-Pro | $1.00 | $3.00 | 1 048 576 | 3 November 2026 |
| Qwen/Qwen3.5-27B | $0.260 | $2.60 | 262 144 | 3 November 2026 |
| deepseek-ai/DeepSeek-V4-Pro | $1.30 | $2.60 | 1 048 576 | 3 November 2026 |
| deepseek-ai/DeepSeek-V4-Pro-0813 | $1.30 | $2.60 | 1 048 576 | 3 November 2026 |
| tencent/Hy4-preview | $0.834 | $2.501 | 1 048 576 | 3 November 2026 |
| Qwen/Qwen3.8-27B | $0.200 | $2.50 | 262 144 | 3 November 2026 |
| google/gemini-2.5-flash | $0.300 | $2.50 | 1 000 000 | 28 October 2026 |
| Qwen/Qwen3.5-122B-A10B | $0.290 | $2.40 | 262 144 | 3 November 2026 |
| zai-org/GLM-5.2 | $0.750 | $2.40 | 1 048 576 | 3 November 2026 |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.500 | $2.20 | 262 144 | 28 October 2026 |
| deepseek-ai/DeepSeek-R1-0528 | $0.500 | $2.15 | 163 840 | 3 November 2026 |
| zai-org/GLM-5 | $0.600 | $2.08 | 202 752 | 3 November 2026 |
| ByteDance/Seed-1.8 | $0.250 | $2.00 | 256 000 | 28 October 2026 |
| zai-org/GLM-4.6 | $0.500 | $2.00 | 202 752 | 3 November 2026 |
| zai-org/GLM-4.7 | $0.400 | $1.75 | 202 752 | 3 November 2026 |
| google/gemini-3.1-flash-lite | $0.250 | $1.50 | 1 000 000 | 28 October 2026 |
| deepseek-ai/DeepSeek-V4-Flash-Vision-Exp | $0.440 | $1.32 | 1 048 576 | 3 November 2026 |
| meta-models/Muse-Glimmer-30B | $0.300 | $1.20 | 131 072 | 3 November 2026 |
| thinkingmachines/Inkling-Small | $0.450 | $1.20 | 524 288 | 3 November 2026 |
| stepfun-ai/Step-3.7-Flash | $0.200 | $1.15 | 262 144 | 3 November 2026 |
| MiniMaxAI/MiniMax-M3 | $0.280 | $1.10 | 524 288 | 3 November 2026 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | $0.090 | $1.10 | 262 144 | 3 November 2026 |
| MiniMaxAI/MiniMax-M2.7 | $0.250 | $1.00 | 196 608 | 3 November 2026 |
| Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | $0.300 | $1.00 | 262 144 | 28 October 2026 |
| Qwen/Qwen3.5-35B-A3B | $0.140 | $1.00 | 262 144 | 3 November 2026 |
| Qwen/Qwen3.6-35B-A3B | $0.100 | $0.950 | 262 144 | 3 November 2026 |
| deepseek-ai/DeepSeek-V3.1 | $0.250 | $0.950 | 163 840 | 3 November 2026 |
| openai/gpt-oss-120b-Ultra | $0.200 | $0.950 | 131 072 | 28 October 2026 |
| deepseek-ai/DeepSeek-V3-0324 | $0.240 | $0.900 | 163 840 | 3 November 2026 |
| inclusionAI/Ling-3.1-flash | $0.300 | $0.900 | 262 144 | 3 November 2026 |
| deepseek-ai/DeepSeek-V3 | $0.320 | $0.890 | 163 840 | 3 November 2026 |
| Qwen/Qwen3-VL-235B-A22B-Instruct | $0.200 | $0.880 | 262 144 | 3 November 2026 |
| XiaomiMiMo/MiMo-V2.6-Pro | $0.430 | $0.870 | 1 048 576 | 3 November 2026 |
| Sao10K/L3.1-70B-Euryale-v2.2 | $0.850 | $0.850 | 131 072 | 28 October 2026 |
| google/gemma-4-31B-it-Ultra | $0.270 | $0.760 | 131 072 | 28 October 2026 |
| NousResearch/Hermes-3-Llama-3.1-70B | $0.700 | $0.700 | 131 072 | 3 November 2026 |
| ibm-granite/granite-4.2-30b | $0.160 | $0.650 | 131 072 | 2 November 2026 |
| Qwen/Qwen3-VL-30B-A3B-Instruct | $0.150 | $0.600 | 262 144 | 3 November 2026 |
| deepseek-ai/DeepSeek-V4.1-Flash | $0.200 | $0.600 | 1 048 576 | 3 November 2026 |
| deepseek-ai/DeepSeek-V4.1-Flash-1017 | $0.200 | $0.600 | 1 048 576 | 31 October 2026 |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | $0.090 | $0.550 | 262 144 | 3 November 2026 |
| tencent/Hy3 | $0.130 | $0.530 | 262 144 | 3 November 2026 |
| Qwen/Qwen3-30B-A3B | $0.120 | $0.500 | 40 960 | 3 November 2026 |
| nvidia/NVIDIA-Nemotron-3.5-Super-VL | $0.150 | $0.500 | 262 144 | 3 November 2026 |
| zai-org/GLM-5.3-Flash | $0.150 | $0.500 | 1 048 576 | 3 November 2026 |
| ByteDance/Seed-2.0-mini | $0.100 | $0.400 | 256 000 | 28 October 2026 |
| Qwen/Qwen2.5-72B-Instruct | $0.360 | $0.400 | 32 768 | 2 November 2026 |
| google/gemma-4-31B-it | $0.200 | $0.400 | 262 144 | 3 November 2026 |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B | $0.085 | $0.400 | 262 144 | 28 October 2026 |
| zai-org/GLM-4.7-Flash | $0.060 | $0.400 | 202 752 | 3 November 2026 |
| Qwen/Qwen3.8-Flash | $0.113 | $0.382 | 1 000 000 | 2 November 2026 |
| deepseek-ai/DeepSeek-V3.2 | $0.260 | $0.380 | 163 840 | 3 November 2026 |
| google/gemma-4-26B-A4B-it | $0.070 | $0.340 | 262 144 | 3 November 2026 |
| google/gemma-4-31B-it-turbo | $0.090 | $0.340 | 262 144 | 28 October 2026 |
| meta-llama/Llama-3.3-70B-Instruct-Turbo | $0.100 | $0.320 | 131 072 | 29 October 2026 |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | $0.100 | $0.300 | 327 680 | 1 November 2026 |
| Qwen/Qwen3-32B | $0.080 | $0.280 | 40 960 | 3 November 2026 |
| XiaomiMiMo/MiMo-V2.5 | $0.140 | $0.280 | 262 144 | 3 November 2026 |
| XiaomiMiMo/MiMo-V2.6-Flash | $0.140 | $0.280 | 1 048 576 | 29 October 2026 |
| ibm-granite/granite-4.2-8b | $0.060 | $0.250 | 131 072 | 3 November 2026 |
| Qwen/Qwen3-14B | $0.120 | $0.240 | 40 960 | 3 November 2026 |
| mistralai/Mistral-Small-3.2-24B-Instruct-2506 | $0.075 | $0.200 | 128 000 | 28 October 2026 |
| nvidia/Nemotron-Content-Safety-3.5 | $0.200 | $0.200 | 131 072 | 28 October 2026 |
| deepseek-ai/DeepSeek-V4-Flash | $0.090 | $0.180 | 1 048 576 | 3 November 2026 |
| deepseek-ai/DeepSeek-V4-Flash-0731 | $0.060 | $0.180 | 1 048 576 | 3 November 2026 |
| inclusionAI/Ling-3.0-flash | $0.060 | $0.180 | 131 072 | 3 November 2026 |
| inclusionAI/Ling-3.0-flash-Fin | $0.060 | $0.180 | 262 144 | 3 November 2026 |
| inclusionAI/Ling-3.0-flash-VL | $0.060 | $0.180 | 131 072 | 3 November 2026 |
| meta-llama/Llama-Guard-4-12B | $0.180 | $0.180 | 163 840 | 3 November 2026 |
| openai/gpt-oss-120b | $0.037 | $0.170 | 131 072 | 3 November 2026 |
| google/gemma-3-27b-it | $0.080 | $0.160 | 131 072 | 3 November 2026 |
| nvidia/NVIDIA-Nemotron-3.5-Lightning | $0.060 | $0.160 | 262 144 | 3 November 2026 |
| Qwen/Qwen3.5-9B | $0.100 | $0.150 | 262 144 | 3 November 2026 |
| google/gemma-3-12b-it | $0.050 | $0.150 | 131 072 | 3 November 2026 |
| microsoft/phi-4 | $0.070 | $0.140 | 16 384 | 3 November 2026 |
| openai/gpt-oss-20b | $0.030 | $0.140 | 131 072 | 3 November 2026 |
| ibm-granite/granite-4.2-3b | $0.030 | $0.120 | 131 072 | 3 November 2026 |
| google/gemma-3-4b-it | $0.050 | $0.100 | 131 072 | 3 November 2026 |
| mistralai/Mistral-Small-24B-Instruct-2501 | $0.050 | $0.080 | 32 768 | 28 October 2026 |
| Sao10K/L3-8B-Lunaris-v1-Turbo | $0.040 | $0.050 | 8 192 | 28 October 2026 |
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | $0.020 | $0.040 | 131 072 | 28 October 2026 |
| mistralai/Mistral-Nemo-Instruct-2407 | $0.029 | $0.030 | 131 072 | 30 October 2026 |
| Cloudflare/clef | $0.240 | $0.000 | 65 537 | 3 November 2026 |
| Cloudflare/clef-flash | $0.038 | $0.000 | 24 576 | 31 October 2026 |
| nace-ai/drex-max | $0.120 | $0.000 | 262 144 | 2 November 2026 |
| nace-ai/drex-v1.5 | $0.040 | $0.000 | 131 072 | 30 October 2026 |
| nace-ai/drex-v2.0 | $0.060 | $0.000 | 131 072 | 30 October 2026 |
No longer listed by DeepInfra
Their last prices stay published and dated on their pages.
- Gryphe/MythoMax-L2-13b$0.400 / 1M out
- MiniMaxAI/MiniMax-M2.7-Turbo$1.70 / 1M out
- NousResearch/Hermes-3-Llama-3.1-405B$1.00 / 1M out
- Qwen/Qwen3-Max$6.00 / 1M out
- Qwen/Qwen3-Max-Thinking$6.00 / 1M out
- XiaomiMiMo/MiMo-V2.6-Flash-RL$0.280 / 1M out
- deepseek-ai/DeepSeek-V4.1-Flash-Turbo$1.20 / 1M out
- google/gemma-4-E4B-it$0.100 / 1M out
- meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8$0.800 / 1M out
- meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo$0.400 / 1M out
- nvidia/Nemotron-3-Nano-30B-A3B$0.200 / 1M out
- openai/gpt-oss-120b-Turbo$0.600 / 1M out
- stepfun-ai/Step-5-Preview$2.70 / 1M out