Inference provider
DeepInfra API pricing: every model, compared
We track 116 DeepInfra prices that other providers also sell. DeepInfra has the lowest listed price for 73 of them; for the rest, the table shows how much more you pay than at the cheapest provider.
Standard list prices in USD. Last price change Oct 19, 2026. DeepInfra's official pricing page. How we rank.
LLMs, most widely offered first
DeepInfra LLM prices vs the cheapest provider
| Model | Rank | Cheapest elsewhere | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|---|
| gpt-oss-120b | #2 of 18 | W&B Inference (CoreWeave)you pay 8% more here | $0.037 | $0.17 | 131K |
| GLM-5.2 | #1 of 13 | DeepInfra is cheapest | $0.75 | $2.40 | 1M |
| Llama-3.3-70B-Instruct | #4 of 13 | Nebius Token Factoryyou pay 38% more here | $0.23 | $0.40 | 131K |
| GLM-5.3 | #1 of 12 | DeepInfra is cheapest | $0.90 | $4.00 | 1M |
| GLM-5.3-Flash | #1 of 11 | DeepInfra is cheapest | $0.15 | $0.50 | 1M |
| DeepSeek V4 Flash 0731 | #1 of 10 | DeepInfra is cheapest | $0.08 | $0.18 | 1M |
| gpt-oss-20b | #2 of 10 | W&B Inference (CoreWeave)you pay 5% more here | $0.03 | $0.14 | 131K |
| Llama-3.1-8B-Instruct | #5 of 10 | Novita AIyou pay 27% more here | $0.03 | $0.05 | 131K |
| Kimi K3 | #2 of 9 | SiliconFlowyou pay 6% more here | $2.85 | $14.25 | 1M |
| DeepSeek V4 Pro 0813 | #1 of 8 | DeepInfra is cheapest | $1.30 | $2.60 | 1M |
| DeepSeek-R1 | #3 of 8 | SiliconFlowyou pay 22% more here | $0.70 | $2.40 | 164K |
| DeepSeek-V3 | #2 of 8 | SiliconFlowyou pay 6% more here | $0.32 | $0.89 | 164K |
| DeepSeek-V3.2 | #1 of 8 | DeepInfra is cheapest | $0.26 | $0.38 | 164K |
| DeepSeek-V4.1-Flash | #1 of 8 | DeepInfra is cheapest | $0.14 | $0.42 | 1M |
| Kimi K2.6 | #3 of 8 | W&B Inference (CoreWeave)you pay 7% more here | $0.75 | $3.50 | 262K |
| Kimi K2.7 Code | #1 of 8 | DeepInfra is cheapest | $0.68 | $3.40 | 262K |
| DeepSeek-V3.1 | #1 of 7 | DeepInfra is cheapest | $0.25 | $0.95 | 164K |
| DeepSeek-V4-Flash | #1 of 7 | DeepInfra is cheapest | $0.09 | $0.18 | 1M |
| Gemma 4 26B A4B IT | #1 of 7 | DeepInfra is cheapest | $0.07 | $0.34 | 262K |
| GLM-5.1 | #1 of 7 | DeepInfra is cheapest | $1.05 | $3.50 | 203K |
| Kimi K2.5 | #1 of 7 | DeepInfra is cheapest | $0.45 | $2.25 | 262K |
| Llama 3.2 3B Instruct | #2 of 7 | Lambdayou pay 14% more here | $0.02 | $0.02 | 131K |
| Llama 4 Scout 17B 16E Instruct | #3 of 7 | Lambdayou pay 140% more here | $0.10 | $0.30 | 328K |
| llama-3.1-70b-instruct | #2 of 7 | Nebius Token Factoryyou pay 103% more here | $0.40 | $0.40 | 131K |
| MiniMax-M3 | #2 of 7 | W&B Inference (CoreWeave)you pay 18% more here | $0.28 | $1.10 | 524K |
| Qwen3 32B | #1 of 7 | DeepInfra is cheapest | $0.08 | $0.28 | 41K |
| Qwen3.8 27B | #1 of 7 | DeepInfra is cheapest | $0.40 | $3.00 | 262K |
| DeepSeek V4 Pro | #1 of 6 | DeepInfra is cheapest | $1.30 | $2.60 | 1M |
| DeepSeek V4.1 Flash 1017 | #1 of 6 | DeepInfra is cheapest | $0.14 | $0.42 | 1M |
| DeepSeek-R1-0528 | #2 of 6 | Lambdayou pay 204% more here | $0.50 | $2.15 | 164K |
| deepseek-r1-distill-llama-70b | #1 of 6 | DeepInfra is cheapest | $0.20 | $0.60 | 131K |
| Gemma 4 31B IT | #2 of 6 | W&B Inference (CoreWeave)you pay 20% more here | $0.13 | $0.38 | 262K |
| Llama 4 Maverick 17B 128E Instruct FP8 | #2 of 6 | Lambdayou pay 460% more here | $0.20 | $0.80 | 1M |
| Qwen2.5-72B-Instruct | #2 of 6 | Nebius Token Factoryyou pay 87% more here | $0.36 | $0.40 | 33K |
| Qwen3 235B A22B Instruct 2507 | #1 of 6 | DeepInfra is cheapest | $0.09 | $0.55 | 262K |
| Qwen3.6 35B-A3B | #1 of 6 | DeepInfra is cheapest | $0.10 | $0.95 | 262K |
| Claude Fable 5 | #1 of 5 | DeepInfra is cheapest | $10.00 | $50.00 | 1M |
| Claude Haiku 4.5 | #1 of 5 | DeepInfra is cheapest | $1.00 | $5.00 | 200K |
| Claude Opus 4.7 | #1 of 5 | DeepInfra is cheapest | $5.00 | $25.00 | 1M |
| Claude Opus 4.8 | #1 of 5 | DeepInfra is cheapest | $5.00 | $25.00 | 1M |
| Claude Opus 5 | #1 of 5 | DeepInfra is cheapest | $5.00 | $25.00 | 1M |
| Claude Sonnet 4.6 | #1 of 5 | DeepInfra is cheapest | $3.00 | $15.00 | 1M |
| Claude Sonnet 5 | #1 of 5 | DeepInfra is cheapest | $2.00 | $10.00 | 1M |
| Deepseek R1 Distill Qwen 32B | #2 of 5 | Nscaleyou pay 80% more here | $0.27 | $0.27 | 131K |
| deepseek-v3-0324 | #2 of 5 | Lambdayou pay 35% more here | $0.24 | $0.90 | 164K |
| Gemma-3-27b-it | #1 of 5 | DeepInfra is cheapest | $0.08 | $0.16 | 131K |
| GLM-4.6 | #1 of 5 | DeepInfra is cheapest | $0.50 | $2.00 | 203K |
| GLM-4.7 | #1 of 5 | DeepInfra is cheapest | $0.40 | $1.75 | 203K |
| GLM-5 | #1 of 5 | DeepInfra is cheapest | $0.60 | $2.08 | 203K |
| Llama 3.2 11B Vision Instruct | #2 of 5 | Lambdayou pay 180% more here | $0.049 | $0.049 | 131K |
| Qwen3.5 397B-A17B | #1 of 5 | DeepInfra is cheapest | $0.45 | $3.00 | 262K |
| Qwen3.8 2.4T A95B | #1 of 5 | DeepInfra is cheapest | $2.00 | $6.00 | 262K |
| Qwq 32B | #2 of 5 | Nscaleyou pay 15% more here | $0.15 | $0.40 | 131K |
| DeepSeek V4 Flash Vision Exp | #2 of 4 | DeepSeekyou pay 26% more here | $0.44 | $1.32 | 1M |
| DeepSeek-V3.1-Terminus | #1 of 4 | DeepInfra is cheapest | $0.27 | $1.00 | 164K |
| Gemini 2.5 Flash | #2 of 4 | Oracle Cloud Generative AIyou pay 224% more here | $0.30 | $2.50 | 1M |
| GLM-4.5 | #1 of 4 | DeepInfra is cheapest | $0.40 | $1.60 | 131K |
| GLM-4.7-Flash | #1 of 4 | DeepInfra is cheapest | $0.06 | $0.40 | 203K |
| Kimi K2 Instruct | #1 of 4 | DeepInfra is cheapest | $0.50 | $2.00 | 131K |
| Llama Guard 3 8B | #2 of 4 | Nebius Token Factoryyou pay 83% more here | $0.055 | $0.055 | 131K |
| llama3-8b-instruct | #1 of 4 | DeepInfra is cheapest | $0.03 | $0.06 | 8K |
| MiniMax-M2.7 | #1 of 4 | DeepInfra is cheapest | $0.25 | $1.00 | 197K |
| mistral-nemo-instruct-2407 | #1 of 4 | DeepInfra is cheapest | $0.019 | $0.03 | 131K |
| Qwen2.5-7B-Instruct | #2 of 4 | SiliconFlowyou pay 10% more here | $0.04 | $0.10 | 33K |
| Qwen3 VL 30B A3B Instruct | #1 of 4 | DeepInfra is cheapest | $0.15 | $0.60 | 262K |
| Qwen3-14B | #3 of 4 | Nebius Token Factoryyou pay 25% more here | $0.12 | $0.24 | 41K |
| Qwen3-Coder-480B-A35B-Instruct | #3 of 4 | SiliconFlowyou pay 60% more here | $0.40 | $1.60 | 262K |
| qwen3-next-80b-a3b-thinking | #2 of 4 | Nebius Token Factoryyou pay 10% more here | $0.14 | $1.40 | 262K |
| Qwen3.5 122B-A10B | #2 of 4 | SiliconFlowyou pay 14% more here | $0.29 | $2.40 | 262K |
| Qwen3.5 27B | #4 of 4 | SiliconFlowyou pay 23% more here | $0.26 | $2.60 | 262K |
| Qwen3.5 35B-A3B | #1 of 4 | DeepInfra is cheapest | $0.14 | $1.00 | 262K |
| Qwen3.6 27B | #2 of 4 | SiliconFlowyou pay 1% more here | $0.32 | $3.20 | 262K |
| Qwen3.7 Max | #3 of 4 | Novita AIyou pay 100% more here | $2.50 | $7.50 | 256K |
| Qwen3.8 Flash | #1 of 4 | DeepInfra is cheapest | $0.113 | $0.382 | 1M |
| Qwen3.8 Max | #1 of 4 | DeepInfra is cheapest | $1.65 | $4.95 | 256K |
| claude-3-7-sonnet | #3 of 3 | Replicateyou pay 10% more here | $3.30 | $16.50 | 200K |
| Gemini 2.5 Pro | #1 of 3 | DeepInfra is cheapest | $1.25 | $10.00 | 1M |
| Gemini 3.1 Flash Lite | #1 of 3 | DeepInfra is cheapest | $0.25 | $1.50 | 1M |
| Gemini 3.5 Flash | #1 of 3 | DeepInfra is cheapest | $1.50 | $9.00 | 1M |
| Gemini 3.7 Flash | #1 of 3 | DeepInfra is cheapest | $0.75 | $3.75 | 1M |
| Gemma 3 12B IT | #2 of 3 | Novita AIyou pay 20% more here | $0.05 | $0.15 | 131K |
| Hy3 | #2 of 3 | SiliconFlowyou pay 8% more here | $0.14 | $0.58 | 262K |
| Inkling | #1 of 3 | DeepInfra is cheapest | $0.95 | $4.05 | 524K |
| mistral-small-3.2-24b-instruct-2506 | #1 of 3 | DeepInfra is cheapest | $0.075 | $0.20 | 128K |
| mixtral-8x7b-instruct-v0.1 | #1 of 3 | DeepInfra is cheapest | $0.40 | $0.40 | 33K |
| MythoMax L2 13B | #3 of 3 | Novita AIyou pay 344% more here | $0.40 | $0.40 | 4K |
| Nemotron Ultra | #2 of 3 | W&B Inference (CoreWeave)you pay 1% more here | $0.50 | $2.20 | 262K |
| Qwen3 30B A3B | #2 of 3 | Nebius Token Factoryyou pay 43% more here | $0.12 | $0.50 | 41K |
| Qwen3 VL 235B A22B Instruct | #1 of 3 | DeepInfra is cheapest | $0.20 | $0.88 | 262K |
| qwen3-235b-a22b | #1 of 3 | DeepInfra is cheapest | $0.18 | $0.54 | 41K |
| qwen3-235b-a22b-thinking-2507 | #2 of 3 | Fireworks AIyou pay 147% more here | $0.30 | $2.90 | 262K |
| Qwen3-Next 80B-A3B Instruct | #1 of 3 | DeepInfra is cheapest | $0.09 | $1.10 | 262K |
| Qwen3.5 9B | #1 of 3 | DeepInfra is cheapest | $0.10 | $0.15 | 262K |
| claude-4-sonnet | #2 of 2 | Replicateyou pay 10% more here | $3.30 | $16.50 | 200K |
| DeepSeek R1 (Turbo) | #2 of 2 | Novita AIyou pay 30% more here | $1.00 | $3.00 | 41K |
| Gemma 3 4B IT | #2 of 2 | Amazon Bedrockyou pay 25% more here | $0.05 | $0.10 | 131K |
| hermes-3-llama-3.1-405b | #1 of 2 | DeepInfra is cheapest | $1.00 | $1.00 | 131K |
| Hy4 preview | #1 of 2 | DeepInfra is cheapest | $0.834 | $2.50 | 1M |
| kimi-k2-instruct-0905 | #1 of 2 | DeepInfra is cheapest | $0.50 | $2.00 | 262K |
| l3.1-70b-euryale-v2.2 | #1 of 2 | DeepInfra is cheapest | $0.85 | $0.85 | 131K |
| Ling 3.0 Flash | #1 of 2 | DeepInfra is cheapest | $0.06 | $0.18 | 131K |
| llama-3.1-nemotron-70b-instruct | #1 of 2 | DeepInfra is cheapest | $0.60 | $0.60 | 131K |
| MiMo-V2.5 | #2 of 2 | Novita AIyou pay 281% more here | $0.40 | $2.00 | 262K |
| MiMo-V2.5-Pro | #2 of 2 | Novita AIyou pay 130% more here | $1.00 | $3.00 | 1M |
| MiMo-V2.6-Flash | #1 of 2 | DeepInfra is cheapest | $0.14 | $0.28 | 1M |
| MiMo-V2.6-Pro | #1 of 2 | DeepInfra is cheapest | $0.43 | $0.87 | 1M |
| Mistral Small 3 | #1 of 2 | DeepInfra is cheapest | $0.05 | $0.08 | 33K |
| muse-glimmer-30b | #1 of 2 | DeepInfra is cheapest | $0.30 | $1.20 | 131K |
| Nemotron 3 Nano 30B A3B | #1 of 2 | DeepInfra is cheapest | $0.05 | $0.20 | 262K |
| nvidia-nemotron-nano-9b-v2 | #1 of 2 | DeepInfra is cheapest | $0.04 | $0.16 | 131K |
| Phi-4 | #1 of 2 | DeepInfra is cheapest | $0.07 | $0.14 | 16K |
| qwen2.5-vl-32b-instruct | #1 of 2 | DeepInfra is cheapest | $0.20 | $0.60 | 128K |
| qwen3-max | #1 of 2 | DeepInfra is cheapest | $1.20 | $6.00 | 256K |
| Step 3.7 Flash | #1 of 2 | DeepInfra is cheapest | $0.20 | $1.15 | 262K |
| Step 5 Preview | #1 of 2 | DeepInfra is cheapest | $1.00 | $2.70 | 1M |
| WizardLM 2 8x22B | #1 of 2 | DeepInfra is cheapest | $0.48 | $0.48 | 66K |
Rank and difference use the blended price (3 input : 1 output tokens). Equal prices share a rank.
Ranked for your volume
gpt-oss-120b monthly cost by provider
Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.
More requirements: caching, context, features, provider
| Provider | Estimated / month | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
1 W&B Inference (CoreWeave)lowest for your volumePricing page | $0.64 | $0.03 | $0.17 | Not listed | 131,000 |
2 DeepInfraPricing page | $0.71 | $0.037 | $0.17 | Not listed | 131,072 |
3 Novita AIPricing page | $1.00 | $0.05 | $0.25 | Not listed | 131,072 |
4 SiliconFlowPricing page | $1.40 | $0.05 | $0.45 | Not listed | 131,000 |
5 OVHcloud AI EndpointsBilled in EUR: €0.08 input, €0.40 output per 1M tokens. USD at the ECB rate of Oct 30, 2026 (1.1172).Pricing page | $1.79 | $0.0894 | $0.4469 | Not listed | 131,000 |
6 BasetenPricing page | $2.00 | $0.10 | $0.50 | $0.10 | 128,072 |
7 Amazon BedrockPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
8 Fireworks AIPricing page | $2.70 | $0.15 | $0.60 | $0.015 | 131,072 |
9 Microsoft Azure AI FoundryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
10 Nebius Token FactoryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.
Ranked #1? Show it on your site
DeepInfra has the lowest blended list price (3 input : 1 output tokens) for these models. The badge states that basis, updates daily and always shows the current rank, whatever it is; ranking is by price only.
<a href="https://aiselect.online/models/glm-5-2"><img src="https://aiselect.online/badge/glm-5-2/deepinfra.svg" alt="GLM-5.2 API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/glm-5-3"><img src="https://aiselect.online/badge/glm-5-3/deepinfra.svg" alt="GLM-5.3 API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/glm-5-3-flash"><img src="https://aiselect.online/badge/glm-5-3-flash/deepinfra.svg" alt="GLM-5.3-Flash API price ranking on AISelect" height="20"></a>Compare more
Other providers
Alibaba Cloud Model Studio, Amazon Bedrock, Anthropic, Baseten, Cloudflare Workers AI, Cohere, DeepSeek, fal, Fireworks AI, FriendliAI, Google Cloud Vertex AI, Google Gemini API, IBM watsonx.ai, Lambda, Microsoft Azure AI Foundry, Mistral AI, Moonshot AI, Nebius Token Factory, Novita AI, Nscale, OpenAI, Oracle Cloud Generative AI, OVHcloud AI Endpoints, Perplexity, Replicate, SambaNova, Scaleway, SiliconFlow, Together AI, W&B Inference (CoreWeave), xAI, Z.ai