Per MillionLLM API prices, tracked daily

DeepInfra API Pricing (Oct 2026): All 131 Models per 1M Tokens

As of : 131 models tracked. The median price is $0.27 per 1M input tokens and $0.95 per 1M output tokens. Cheapest blended price: Llama-3.2-3B-Instruct (DeepInfra, $0.02 per 1M input / $0.02 per 1M output).

API list prices for every DeepInfra chat model we track.

Browse: All models · Cheapest · Price changes · Cost calculator · By provider · Deprecations · Free RSS alerts

Models

Sort:

Models. Source: the LiteLLM price list (MIT License)
ModelProviderInput / 1MOutput / 1MCached input / 1MContext
Llama-3.2-3B-InstructDeepInfra$0.02$0.02—131K
Mistral-Nemo-Instruct-2407DeepInfra$0.02$0.03—131K
Meta-Llama-3.1-8B-Instruct-TurboDeepInfra$0.02$0.04—131K
Meta-Llama-3.1-8B-InstructDeepInfra$0.03$0.05—131K
Meta-Llama-3-8B-InstructDeepInfra$0.03$0.06—8K
gemma-4-E4B-itDeepInfra$0.02$0.10—131K
L3-8B-Lunaris-v1-TurboDeepInfra$0.04$0.05—8K
Llama-3.2-11B-Vision-InstructDeepInfra$0.05$0.05—131K
Qwen2.5-7B-InstructDeepInfra$0.04$0.10—33K
gpt-oss-20bDeepInfra$0.03$0.14—131K
Mistral-Small-24B-Instruct-2501DeepInfra$0.05$0.08—33K
gemma-3-4b-itDeepInfra$0.05$0.10—131K
NVIDIA-Nemotron-Nano-9B-v2DeepInfra$0.04$0.16—131K
gpt-oss-120bDeepInfra$0.04$0.17—131K
gemma-3-12b-itDeepInfra$0.05$0.15—131K
phi-4DeepInfra$0.07$0.14—16K
Nemotron-3-Nano-30B-A3BDeepInfra$0.05$0.20$0.03262K
Ling-3.0-flashDeepInfra$0.06$0.18$0.01131K
gemma-3-27b-itDeepInfra$0.08$0.16—131K
DeepSeek-V4-Flash-0731DeepInfra$0.08$0.18$0.021.04858M
Mistral-Small-3.2-24B-Instruct-2506DeepInfra$0.07$0.20—128K
NVIDIA-Nemotron-3.5-LightningDeepInfra$0.08$0.20$0.04262K
DeepSeek-V4-FlashDeepInfra$0.09$0.18$0.021.04858M
Qwen3.5-9BDeepInfra$0.10$0.15—262K
Qwen3-32BDeepInfra$0.08$0.28—41K
gemma-4-26B-A4B-itDeepInfra$0.07$0.34—262K
GLM-4.7-FlashDeepInfra$0.06$0.40$0.01203K
Qwen3-14BDeepInfra$0.12$0.24—41K
Llama-4-Scout-17B-16E-InstructDeepInfra$0.10$0.30—328K
gemma-4-31B-it-turboDeepInfra$0.09$0.34$0.05262K
Llama-3.3-70B-Instruct-TurboDeepInfra$0.10$0.32—131K
NVIDIA-Nemotron-3-Super-120B-A12BDeepInfra$0.09$0.40—262K
Seed-2.0-miniDeepInfra$0.10$0.40$0.02256K
Llama-3.3-Nemotron-Super-49B-v1.5DeepInfra$0.10$0.40—131K
gemma-4-31B-itDeepInfra$0.13$0.38—262K
Nemotron-Content-Safety-3.5DeepInfra$0.20$0.20—131K
Qwen3-235B-A22B-Instruct-2507DeepInfra$0.09$0.55—262K
DeepSeek-V4.1-FlashDeepInfra$0.14$0.42$0.00421.04858M
QwQ-32BDeepInfra$0.15$0.40—131K
Qwen3-30B-A3BDeepInfra$0.12$0.50—41K
Hy3DeepInfra$0.14$0.58$0.04262K
Qwen3-VL-30B-A3B-InstructDeepInfra$0.15$0.60—262K
gpt-oss-120b-TurboDeepInfra$0.15$0.60—131K
Qwen3-235B-A22BDeepInfra$0.18$0.54—41K
DeepSeek-R1-Distill-Qwen-32BDeepInfra$0.27$0.27—131K
Llama-3.3-70B-InstructDeepInfra$0.23$0.40—131K
DeepSeek-V3.2DeepInfra$0.26$0.38$0.13164K
Qwen2.5-VL-32B-InstructDeepInfra$0.20$0.60—128K
DeepSeek-R1-Distill-Llama-70BDeepInfra$0.20$0.60—131K
Qwen3.6-35B-A3BDeepInfra$0.10$0.95—262K
Qwen3-Next-80B-A3B-InstructDeepInfra$0.09$1.10—262K
Llama-4-Maverick-17B-128E-Instruct-FP8DeepInfra$0.20$0.80—1.04858M
Qwen3.5-35B-A3BDeepInfra$0.14$1.00$0.05262K
Qwen2.5-72B-InstructDeepInfra$0.36$0.40—33K
Qwen3-VL-235B-A22B-InstructDeepInfra$0.20$0.88$0.11262K
gpt-oss-120b-UltraDeepInfra$0.20$0.95—131K
gemma-4-31B-it-UltraDeepInfra$0.27$0.76—131K
MythoMax-L2-13bDeepInfra$0.40$0.40—4K
Meta-Llama-3.1-70B-InstructDeepInfra$0.40$0.40—131K
Meta-Llama-3.1-70B-Instruct-TurboDeepInfra$0.40$0.40—131K
Mixtral-8x7B-Instruct-v0.1DeepInfra$0.40$0.40—33K
DeepSeek-V3-0324DeepInfra$0.24$0.90$0.14164K
DeepSeek-V3.1DeepInfra$0.25$0.95$0.22164K
MiniMax-M2.7DeepInfra$0.25$1.00$0.05197K
Step-3.7-FlashDeepInfra$0.20$1.15$0.04262K
DeepSeek-V3.1-TerminusDeepInfra$0.27$1.00$0.22164K
Qwen3-Next-80B-A3B-ThinkingDeepInfra$0.14$1.40—262K
DeepSeek-V3DeepInfra$0.32$0.89—164K
Qwen3-Coder-480B-A35B-Instruct-TurboDeepInfra$0.30$1.00$0.10262K
WizardLM-2-8x22BDeepInfra$0.48$0.48—66K
MiniMax-M3DeepInfra$0.28$1.10$0.06524K
Muse-Glimmer-30BDeepInfra$0.30$1.20$0.04131K
gemini-3.1-flash-liteDeepInfra$0.25$1.50—1M
olmOCR-7B-0725-FP8DeepInfra$0.27$1.50—16K
Llama-3.1-Nemotron-70B-InstructDeepInfra$0.60$0.60—131K
Inkling-SmallDeepInfra$0.45$1.20$0.10524K
L3.3-70B-Euryale-v2.3DeepInfra$0.65$0.75—131K
Seed-1.8DeepInfra$0.25$2.00$0.05256K
Hermes-3-Llama-3.1-70BDeepInfra$0.70$0.70—131K
Qwen3-Coder-480B-A35B-InstructDeepInfra$0.40$1.60—262K
GLM-4.5DeepInfra$0.40$1.60—131K
MiniMax-M2.7-TurboDeepInfra$0.38$1.70$0.07197K
GLM-4.7DeepInfra$0.40$1.75$0.08203K
MiMo-V2.5DeepInfra$0.40$2.00$0.08262K
Qwen3.5-122B-A10BDeepInfra$0.29$2.40—262K
Qwen3.5-27BDeepInfra$0.26$2.60—262K
L3.1-70B-Euryale-v2.2DeepInfra$0.85$0.85—131K
gemini-2.5-flashDeepInfra$0.30$2.50—1M
Kimi-K2-InstructDeepInfra$0.50$2.00—131K
GLM-4.6DeepInfra$0.50$2.00$0.10203K
Kimi-K2.5DeepInfra$0.45$2.25$0.07262K
DeepSeek-R1-0528DeepInfra$0.50$2.15$0.40164K
NVIDIA-Nemotron-3-Ultra-550B-A55BDeepInfra$0.50$2.20$0.10262K
Qwen3-235B-A22B-Thinking-2507DeepInfra$0.30$2.90—262K
GLM-5DeepInfra$0.60$2.08$0.12203K
Hermes-3-Llama-3.1-405BDeepInfra$1.00$1.00—131K
Qwen3.6-27BDeepInfra$0.32$3.20—262K
Qwen3.8-27BDeepInfra$0.40$3.00$0.04262K
Qwen3.5-397B-A17BDeepInfra$0.45$3.00$0.22262K
Seed-2.0-codeDeepInfra$0.50$3.00$0.10256K
Seed-2.0-proDeepInfra$0.50$3.00$0.10256K
DeepSeek-R1DeepInfra$0.70$2.40—164K
GLM-5.2DeepInfra$0.75$2.40$0.141.04858M
Kimi-K2.7-CodeDeepInfra$0.68$3.40$0.14262K
Kimi-K2.6DeepInfra$0.75$3.50$0.15262K
MiMo-V2.5-ProDeepInfra$1.00$3.00$0.201.04858M
DeepSeek-R1-0528-TurboDeepInfra$1.00$3.00—33K
DeepSeek-R1-TurboDeepInfra$1.00$3.00—41K
gemini-3.7-flashDeepInfra$0.75$3.75—1M
DeepSeek-V4-ProDeepInfra$1.30$2.60$0.101.04858M
GLM-5.1DeepInfra$1.05$3.50$0.20203K
InklingDeepInfra$0.95$4.05$0.16524K
claude-haiku-4-5DeepInfra$1.00$5.00—200K
Qwen3-MaxDeepInfra$1.20$6.00$0.24256K
Qwen3-Max-ThinkingDeepInfra$1.20$6.00$0.24256K
Qwen3.8-MaxDeepInfra$1.65$4.95$0.21256K
Qwen3.8-2.4T-A95BDeepInfra$2.00$6.00$0.20262K
gemini-3.5-flashDeepInfra$1.50$9.00—1M
gemini-2.5-proDeepInfra$1.25$10.00—1M
Qwen3.7-MaxDeepInfra$2.50$7.50$0.50256K
claude-sonnet-5DeepInfra$2.00$10.00—1M
gemini-3.1-proDeepInfra$2.00$12.00—1M
Kimi-K3DeepInfra$2.85$14.25$0.281.04858M
claude-sonnet-4-6DeepInfra$3.00$15.00—1M
claude-3-7-sonnet-latestDeepInfra$3.30$16.50$0.33200K
claude-4-sonnetDeepInfra$3.30$16.50—200K
claude-opus-4-7DeepInfra$5.00$25.00—1M
claude-opus-4-8DeepInfra$5.00$25.00—1M
claude-opus-5DeepInfra$5.00$25.00—1M
claude-fable-5DeepInfra$10.00$50.00—1M
claude-4-opusDeepInfra$16.50$82.50—200K

FAQ

How are prices shown?

In US dollars per 1 million tokens, as listed for each model's API. 'Blended' assumes 3 input tokens for every output token.

Which model is cheapest here?

Llama-3.2-3B-Instruct from DeepInfra, at $0.02 per 1M input and $0.02 per 1M output tokens (as of ).

How current are these prices?

We copy the open-source LiteLLM price list once a day and record every change. Providers can change prices at any time, so confirm on the official pricing page linked from each model.