DeepInfra API pricing
Updated
DeepInfra lists standard per-token prices for 92 models. The cheapest is Llama 3.1 8B Instruct at USD 0.02 input and USD 0.04 output per 1M tokens; the dearest is Claude Fable 5 at USD 10 / USD 50. It publishes cached-input prices for 45 of them, plus flex / spot and priority tiers (no batch). Checked 2026-11-14.
- Models with a standard price
- 92
- Median input / output
- USD 0.25 / USD 0.92
- Cached-input prices
- 45 of 92
- Cheapest host for
- 37 of 81 shared models
Which models is DeepInfra the cheapest provider for?
Of the 81 models that DeepInfra and at least one other provider both price at the standard tier, DeepInfra has the lowest price for 37, ranked on a blend of 3 input tokens to 1 output token (9 of them tied with another provider at the same price). It also ties the lowest price for 12 more, where another provider is listed first. It is the dearest for 8. Another 11 models have a standard price from DeepInfra only.
| Model | DeepInfra input / output | Next cheapest | Saving on 3:1 blend | Providers |
|---|---|---|---|---|
| GLM 5.3 (promo) | USD 0.5625 / USD 2.50 | GMI Cloud USD 0.70 / USD 2.20 | 3% | 24 |
| GLM 5.2 (promo) | USD 0.5625 / USD 1.80 | CoreWeave Forge USD 0.62 / USD 2.42 | 19% | 19 |
| DeepSeek V4.1 Flash 1017 (promo) | USD 0.098 / USD 0.294 | GMI Cloud USD 0.18 / USD 0.72 | 53% | 16 |
| DeepSeek V4.1 Flash (promo) | USD 0.14 / USD 0.42 | CoreWeave Forge USD 0.13 / USD 0.65 | 19% | 16 |
| DeepSeek V4 Flash 0731 | USD 0.06 / USD 0.18 | Hyperbolic USD 0.06 / USD 0.18 | tie | 15 |
| Llama 3.3 70B | USD 0.10 / USD 0.32 | Novita AI USD 0.135 / USD 0.40 | 23% | 14 |
| Kimi K3.1 Pro (promo) | USD 1.90 / USD 9.50 | AkashML USD 1.75 / USD 10 | under 1% | 13 |
| Gemma 4 26B A4B | USD 0.07 / USD 0.34 | Featherless USD 0.07 / USD 0.34 | tie | 11 |
| GLM 4.7 | USD 0.40 / USD 1.75 | Featherless USD 0.55 / USD 2.20 | 23% | 8 |
| DeepSeek V4 Flash | USD 0.09 / USD 0.18 | GMI Cloud USD 0.091 / USD 0.182 | 1% | 8 |
| DeepSeek V3.1 | USD 0.25 / USD 0.95 | GMI Cloud USD 0.27 / USD 1 | 6% | 7 |
| Qwen3.5 35B A3B | USD 0.14 / USD 1 | Parasail USD 0.15 / USD 1 | 2% | 7 |
| Gemma 3 27B | USD 0.08 / USD 0.16 | Novita AI USD 0.119 / USD 0.20 | 28% | 6 |
| Llama 4 Scout 17B 16E Instruct | USD 0.10 / USD 0.30 | GMI Cloud USD 0.08 / USD 0.50 | 19% | 6 |
| Qwen3.8 Max | USD 1.65 / USD 4.951 | Alibaba Cloud USD 2 / USD 6 | 17% | 6 |
Showing the 15 with the most competing providers; the full price list below marks every model page.
How does DeepInfra price the most widely hosted models?
The 6 models DeepInfra sells that the most other providers also sell, with DeepInfra's rank among them on the 3:1 blend.
| Model | DeepInfra | Rank | Cheapest |
|---|---|---|---|
| GLM 5.3 | USD 0.5625 / USD 2.50 | 1 of 24 | DeepInfra (this page) |
| OpenAI GPT OSS 120B | USD 0.037 / USD 0.17 | 2 of 21 | CoreWeave Forge USD 0.03 / USD 0.17 |
| GLM 5.3 Flash | USD 0.15 / USD 0.50 | 3 of 20 | GMI Cloud USD 0.075 / USD 0.25 |
| GLM 5.2 | USD 0.5625 / USD 1.80 | 1 of 19 | DeepInfra (this page) |
| Kimi K3 | USD 2.85 / USD 14.25 | 4 of 18 | Chutes USD 1.85 / USD 9.50 |
| DeepSeek V4.1 Flash | USD 0.14 / USD 0.42 | 1 of 16 | DeepInfra (this page) |
Which model makers does DeepInfra sell?
DeepInfra prices models from 19 makers. Qwen leads with 19 models. Standard prices, USD per 1M input / output tokens.
| Maker | Models | Cheapest model | Median input / output |
|---|---|---|---|
| Qwen | 19 | Qwen3.5 9B USD 0.10 / USD 0.15 | USD 0.15 / USD 0.95 |
| 13 | Gemma 3 4B USD 0.05 / USD 0.10 | USD 0.25 / USD 0.76 | |
| DeepSeek | 11 | DeepSeek V4 Flash 0731 USD 0.06 / USD 0.18 | USD 0.25 / USD 0.6468 |
| Anthropic | 9 | Claude Haiku 4.5 USD 1 / USD 5 | USD 4 / USD 20 |
| Meta | 5 | Llama 3.1 8B Instruct USD 0.02 / USD 0.04 | USD 0.10 / USD 0.30 |
| NVIDIA | 5 | NVIDIA Nemotron 3.5 Lightning 30B A3B USD 0.06 / USD 0.16 | USD 0.15 / USD 0.40 |
| Z.ai | 5 | GLM 5.3 Flash USD 0.15 / USD 0.50 | USD 0.50 / USD 1.80 |
| ByteDance Seed | 4 | Seed-2.0-mini USD 0.10 / USD 0.40 | USD 0.375 / USD 2.50 |
| Mistral AI | 3 | Mistral-Nemo-Instruct-2407 USD 0.029 / USD 0.03 | USD 0.05 / USD 0.08 |
| Moonshot AI | 3 | Kimi K2.6 USD 0.75 / USD 3.50 | USD 1.90 / USD 9.50 |
| OpenAI | 3 | GPT OSS 20B USD 0.03 / USD 0.14 | USD 0.037 / USD 0.17 |
| inclusionAI | 2 | Ling 3.0 Flash USD 0.06 / USD 0.18 | USD 0.06 / USD 0.18 |
| Sao10K | 2 | L3-8B-Lunaris-v1-Turbo USD 0.04 / USD 0.05 | USD 0.445 / USD 0.45 |
| Thinking Machines | 2 | Inkling 2 Small USD 0.285 / USD 0.95 | USD 0.3675 / USD 1.075 |
| Xiaomi | 2 | MiMo V2.6 Flash USD 0.14 / USD 0.28 | USD 0.2635 / USD 0.5315 |
| IBM | 1 | IBM Granite 4.2 8B USD 0.06 / USD 0.25 | — |
| Microsoft | 1 | Phi-4 USD 0.07 / USD 0.14 | — |
| MiniMax | 1 | MiniMax M3 USD 0.28 / USD 1.10 | — |
| Tencent | 1 | Hy4 Preview USD 0.834 / USD 2.501 | — |
DeepInfra price list
USD per 1M tokens: 183 prices for 92 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means DeepInfra is cheaper. Of 34 hosted model prices with a maker price to compare, 19 are below the maker's and 2 above.
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
|---|---|---|---|---|---|---|---|
| Claude Fable 5 | standard | USD 10 | — | USD 50 | 1,000,000 | same | source |
| Claude Haiku 4.5 | standard | USD 1 | — | USD 5 | 200,000 | same | source |
| Claude Opus 4.7 | standard | USD 5 | — | USD 25 | 1,000,000 | same | source |
| Claude Opus 4.8 | standard | USD 5 | — | USD 25 | 1,000,000 | same | source |
| Claude Opus 5 | standard | USD 5 | — | USD 25 | 1,000,000 | same | source |
| Claude Opus 5.5 | standard | USD 4 | USD 0.20 | USD 20 | 1,000,000 | same | source |
| Claude Sonnet 4.6 | standard | USD 3 | — | USD 15 | 1,000,000 | same | source |
| Claude Sonnet 5 | standard | USD 3 | — | USD 15 | 1,000,000 | +50% | source |
| Claude Sonnet 5.5 | standard | USD 2 | — | USD 10 | 1,000,000 | same | source |
| DeepSeek R1 0528 | standard flex / spot | USD 0.50 USD 0.40 | USD 0.35 USD 0.28 | USD 2.15 USD 1.72 | 163,840 | — | source |
| DeepSeek V3 | standard flex / spot | USD 0.32 USD 0.256 | — — | USD 0.89 USD 0.712 | 163,840 | — | source |
| DeepSeek V3.1 | standard flex / spot | USD 0.25 USD 0.20 | USD 0.13 USD 0.104 | USD 0.95 USD 0.76 | 163,840 | — | source |
| DeepSeek V3.2 | standard flex / spot | USD 0.26 USD 0.208 | USD 0.13 USD 0.104 | USD 0.38 USD 0.304 | 163,840 | — | source |
| DeepSeek V4 Flash | standard flex / spot priority | USD 0.09 USD 0.072 USD 0.135 | USD 0.018 USD 0.0144 USD 0.027 | USD 0.18 USD 0.144 USD 0.27 | 1,048,576 | — | source |
| DeepSeek V4 Flash 0731 | standard flex / spot priority | USD 0.06 USD 0.048 USD 0.09 | USD 0.015 USD 0.012 USD 0.0225 | USD 0.18 USD 0.144 USD 0.27 | 1,048,576 | — | source |
| DeepSeek V4 Pro | standard flex / spot priority | USD 1.30 USD 1.04 USD 1.95 | USD 0.10 USD 0.08 USD 0.15 | USD 2.60 USD 2.08 USD 3.90 | 1,048,576 | −18% | source |
| DeepSeek V4 Pro 0813 | standard flex / spot priority | USD 1.30 USD 1.04 USD 1.95 | USD 0.10 USD 0.08 USD 0.15 | USD 2.60 USD 2.08 USD 3.90 | 1,048,576 | −18% | source |
| DeepSeek V4.1 Flashpromo | standard flex / spot priority | USD 0.14 USD 0.112 USD 0.21 | USD 0.0042 USD 0.0034 USD 0.0063 | USD 0.42 USD 0.336 USD 0.63 | 1,048,576 | −60% | source |
| DeepSeek V4.1 Flash 1017promo | standard flex / spot priority | USD 0.098 USD 0.0784 USD 0.147 | USD 0.00294 USD 0.0024 USD 0.0044 | USD 0.294 USD 0.2352 USD 0.441 | 1,048,576 | −72% | source |
| DeepSeek-V4-Flash-Vision-Exppromo | standard flex / spot priority | USD 0.2156 USD 0.1725 USD 0.3234 | USD 0.00686 USD 0.0055 USD 0.0103 | USD 0.6468 USD 0.5174 USD 0.9702 | 1,048,576 | — | source |
| Gemini 2.5 Flash | standard | USD 0.30 | — | USD 2.50 | 1,000,000 | same | source |
| Gemini 2.5 Pro | standard | USD 1.25 | — | USD 10 | 1,000,000 | same | source |
| Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite) | standard | USD 0.25 | — | USD 1.50 | 1,000,000 | same | source |
| Gemini 3.5 Flash | standard | USD 1.50 | — | USD 9 | 1,000,000 | — | source |
| Gemini 3.7 Flash | standard | USD 0.75 | — | USD 3.75 | 1,000,000 | — | source |
| Gemini-3.1-pro | standard | USD 2 | — | USD 12 | 1,000,000 | — | source |
| Gemma 3 12B | standard flex / spot priority | USD 0.05 USD 0.04 USD 0.075 | — — — | USD 0.15 USD 0.12 USD 0.225 | 131,072 | — | source |
| Gemma 3 27B | standard flex / spot priority | USD 0.08 USD 0.064 USD 0.12 | — — — | USD 0.16 USD 0.128 USD 0.24 | 131,072 | — | source |
| Gemma 3 4B | standard flex / spot priority | USD 0.05 USD 0.04 USD 0.075 | — — — | USD 0.10 USD 0.08 USD 0.15 | 131,072 | — | source |
| Gemma 4 26B A4B | standard flex / spot priority | USD 0.07 USD 0.056 USD 0.105 | — — — | USD 0.34 USD 0.272 USD 0.51 | 262,144 | — | source |
| Gemma 4 31B | standard flex / spot priority | USD 0.20 USD 0.16 USD 0.30 | — — — | USD 0.40 USD 0.32 USD 0.60 | 262,144 | — | source |
| gemma-4-31B-it-turbo | standard flex / spot priority | USD 0.09 USD 0.072 USD 0.135 | USD 0.05 USD 0.04 USD 0.075 | USD 0.34 USD 0.272 USD 0.51 | 262,144 | — | source |
| gemma-4-31B-it-Ultra | standard | USD 0.27 | — | USD 0.76 | 131,072 | — | source |
| GLM 4.6 | standard flex / spot | USD 0.50 USD 0.40 | USD 0.10 USD 0.08 | USD 2 USD 1.60 | 202,752 | −12% | source |
| GLM 4.7 | standard flex / spot | USD 0.40 USD 0.32 | USD 0.08 USD 0.064 | USD 1.75 USD 1.40 | 202,752 | −26% | source |
| GLM 5.2promo | standard flex / spot priority | USD 0.5625 USD 0.45 USD 0.8438 | USD 0.105 USD 0.084 USD 0.1575 | USD 1.80 USD 1.44 USD 2.70 | 1,048,576 | −59% | source |
| GLM 5.3promo | standard flex / spot | USD 0.5625 USD 0.45 | USD 0.125 USD 0.10 | USD 2.50 USD 2 | 1,048,576 | −51% | source |
| GLM 5.3 Flash | standard | USD 0.15 | USD 0.03 | USD 0.50 | 1,048,576 | same | source |
| GPT OSS 20B | standard flex / spot priority | USD 0.03 USD 0.024 USD 0.045 | — — — | USD 0.14 USD 0.112 USD 0.21 | 131,072 | — | source |
| gpt-oss-120b-Ultra | standard | USD 0.20 | — | USD 0.95 | 131,072 | — | source |
| Hy4 Preview | standard | USD 0.834 | USD 0.042 | USD 2.501 | 1,048,576 | — | source |
| IBM Granite 4.2 8B | standard | USD 0.06 | USD 0.015 | USD 0.25 | 131,072 | — | source |
| Inkling 2 Smallpromo | standard | USD 0.285 | USD 0.0285 | USD 0.95 | 1,048,576 | — | source |
| Inkling-Small | standard | USD 0.45 | USD 0.10 | USD 1.20 | 524,288 | — | source |
| Kimi K2.6 | standard flex / spot priority | USD 0.75 USD 0.60 USD 1.125 | USD 0.15 USD 0.12 USD 0.225 | USD 3.50 USD 2.80 USD 5.25 | 262,144 | −16% | source |
| Kimi K3 | standard | USD 2.85 | USD 0.285 | USD 14.25 | 1,048,576 | −5% | source |
| Kimi K3.1 Propromo | standard flex / spot priority | USD 1.90 USD 1.52 USD 2.85 | USD 0.19 USD 0.152 USD 0.285 | USD 9.50 USD 7.60 USD 14.25 | 1,048,576 | −5% | source |
| L3-8B-Lunaris-v1-Turbo | standard flex / spot | USD 0.04 USD 0.032 | — — | USD 0.05 USD 0.04 | 8,192 | — | source |
| L3.1-70B-Euryale-v2.2 | standard flex / spot | USD 0.85 USD 0.68 | — — | USD 0.85 USD 0.68 | 131,072 | — | source |
| Ling 3.0 Flash | standard | USD 0.06 | USD 0.012 | USD 0.18 | 131,072 | — | source |
| Ling 3.0 Flash VL | standard | USD 0.06 | USD 0.012 | USD 0.18 | 131,072 | — | source |
| Llama 3.1 8B Instruct | standard flex / spot | USD 0.02 USD 0.016 | — — | USD 0.04 USD 0.032 | 131,072 | — | source |
| Llama 3.3 70B | standard flex / spot | USD 0.10 USD 0.08 | — — | USD 0.32 USD 0.256 | 131,072 | — | source |
| Llama 4 Scout 17B 16E Instruct | standard flex / spot priority | USD 0.10 USD 0.08 USD 0.15 | — — — | USD 0.30 USD 0.24 USD 0.45 | 327,680 | — | source |
| Llama-Guard-4-12B | standard flex / spot priority | USD 0.18 USD 0.144 USD 0.27 | — — — | USD 0.18 USD 0.144 USD 0.27 | 163,840 | — | source |
| MiMo V2.6 Flash | standard | USD 0.14 | USD 0.0028 | USD 0.28 | 1,048,576 | — | source |
| MiMo V2.6 Propromo | standard | USD 0.387 | USD 0.00324 | USD 0.783 | 1,048,576 | — | source |
| MiniMax M3 | standard flex / spot | USD 0.28 USD 0.224 | USD 0.056 USD 0.0448 | USD 1.10 USD 0.88 | 524,288 | −8% | source |
| Mistral Small 3.2 24B Instruct | standard flex / spot priority | USD 0.075 USD 0.06 USD 0.1125 | — — — | USD 0.20 USD 0.16 USD 0.30 | 128,000 | — | source |
| Mistral-Nemo-Instruct-2407 | standard flex / spot | USD 0.029 USD 0.0232 | — — | USD 0.03 USD 0.024 | 131,072 | — | source |
| Mistral-Small-24B-Instruct-2501 | standard flex / spot | USD 0.05 USD 0.04 | — — | USD 0.08 USD 0.064 | 32,768 | — | source |
| Muse Glimmer 30B | standard | USD 0.30 | USD 0.04 | USD 1.20 | 131,072 | — | source |
| Nemotron-Content-Safety-3.5 | standard flex / spot priority | USD 0.20 USD 0.16 USD 0.30 | — — — | USD 0.20 USD 0.16 USD 0.30 | 131,072 | — | source |
| NVIDIA Nemotron 3 Super 120B A12B | standard flex / spot priority | USD 0.075 USD 0.06 USD 0.1125 | — — — | USD 0.40 USD 0.32 USD 0.60 | 262,144 | — | source |
| NVIDIA Nemotron 3 Ultra | standard flex / spot priority | USD 0.50 USD 0.40 USD 0.75 | USD 0.10 USD 0.08 USD 0.15 | USD 2.20 USD 1.76 USD 3.30 | 262,144 | — | source |
| NVIDIA Nemotron 3.5 Lightning 30B A3B | standard | USD 0.06 | USD 0.03 | USD 0.16 | 262,144 | — | source |
| NVIDIA Nemotron 3.5 Super VL | standard | USD 0.15 | USD 0.02 | USD 0.50 | 262,144 | — | source |
| OpenAI GPT OSS 120B | standard | USD 0.037 | — | USD 0.17 | 131,072 | — | source |
| Phi-4 | standard flex / spot | USD 0.07 USD 0.056 | — — | USD 0.14 USD 0.112 | 16,384 | — | source |
| Qwen2.5-72B-Instruct | standard flex / spot | USD 0.36 USD 0.288 | — — | USD 0.40 USD 0.32 | 32,768 | — | source |
| Qwen3 235B A22B Instruct 2507 FP8 | standard flex / spot priority | USD 0.09 USD 0.072 USD 0.135 | — — — | USD 0.55 USD 0.44 USD 0.825 | 262,144 | — | source |
| Qwen3 30B A3B (fp8) | standard flex / spot priority | USD 0.12 USD 0.096 USD 0.18 | — — — | USD 0.50 USD 0.40 USD 0.75 | 40,960 | — | source |
| Qwen3 32B FP8 | standard flex / spot priority | USD 0.08 USD 0.064 USD 0.12 | — — — | USD 0.28 USD 0.224 USD 0.42 | 40,960 | — | source |
| Qwen3 Coder 480B A35B | standard flex / spot | USD 0.30 USD 0.24 | USD 0.10 USD 0.08 | USD 1 USD 0.80 | 262,144 | — | source |
| Qwen3 Next 80B A3B Instruct | standard flex / spot priority | USD 0.09 USD 0.072 USD 0.135 | — — — | USD 1.10 USD 0.88 USD 1.65 | 262,144 | — | source |
| Qwen3 VL 235B A22B | standard flex / spot priority | USD 0.20 USD 0.16 USD 0.30 | USD 0.11 USD 0.088 USD 0.165 | USD 0.88 USD 0.704 USD 1.32 | 262,144 | — | source |
| Qwen3 VL 30B A3B Instruct | standard flex / spot priority | USD 0.15 USD 0.12 USD 0.225 | — — — | USD 0.60 USD 0.48 USD 0.90 | 262,144 | — | source |
| Qwen3-14B | standard flex / spot priority | USD 0.12 USD 0.096 USD 0.18 | — — — | USD 0.24 USD 0.192 USD 0.36 | 40,960 | — | source |
| Qwen3.5 27B | standard flex / spot priority | USD 0.26 USD 0.208 USD 0.39 | — — — | USD 2.60 USD 2.08 USD 3.90 | 262,144 | +2% | source |
| Qwen3.5 35B A3B | standard flex / spot priority | USD 0.14 USD 0.112 USD 0.21 | USD 0.05 USD 0.04 USD 0.075 | USD 1 USD 0.80 USD 1.50 | 262,144 | −48% | source |
| Qwen3.5 397B A17B | standard flex / spot priority | USD 0.45 USD 0.36 USD 0.675 | USD 0.22 USD 0.176 USD 0.33 | USD 3 USD 2.40 USD 4.50 | 262,144 | −19% | source |
| Qwen3.5 9B | standard flex / spot priority | USD 0.10 USD 0.08 USD 0.15 | — — — | USD 0.15 USD 0.12 USD 0.225 | 262,144 | — | source |
| Qwen3.6 27B | standard flex / spot priority | USD 0.32 USD 0.256 USD 0.48 | — — — | USD 3.20 USD 2.56 USD 4.80 | 262,144 | −23% | source |
| Qwen3.6 35B A3B | standard flex / spot priority | USD 0.10 USD 0.08 USD 0.15 | USD 0.10 USD 0.08 USD 0.15 | USD 0.95 USD 0.76 USD 1.425 | 262,144 | −63% | source |
| Qwen3.7 Max | standard | USD 2.50 | USD 0.50 | USD 7.50 | 256,000 | same | source |
| Qwen3.8 27Bpromo | standard flex / spot priority | USD 0.15 USD 0.12 USD 0.225 | USD 0.0375 USD 0.03 USD 0.0563 | USD 1.875 USD 1.50 USD 2.8125 | 262,144 | −48% | source |
| Qwen3.8 Flash | standard | USD 0.113 | USD 0.0141 | USD 0.382 | 1,000,000 | −22% | source |
| Qwen3.8 Max | standard | USD 1.65 | USD 0.206 | USD 4.951 | 256,000 | −17% | source |
| Seed-1.8 | standard | USD 0.25 | USD 0.05 | USD 2 | 256,000 | — | source |
| Seed-2.0-code | standard | USD 0.50 | USD 0.10 | USD 3 | 256,000 | — | source |
| Seed-2.0-mini | standard | USD 0.10 | USD 0.02 | USD 0.40 | 256,000 | — | source |
| Seed-2.0-pro | standard | USD 0.50 | USD 0.10 | USD 3 | 256,000 | — | source |
- Cached "—" means DeepInfra's page shows no cache price for that row; budget cached tokens at the input price.
- Promo: DeepInfra's page describes 9 prices as promotional or discounted; they can end without notice. Each model page has the list price where the source gives one.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What service tiers does DeepInfra publish?
- flex / spot (54 rows). Across 54 models with both prices, the median flex / spot price is 20% below standard. DeepInfra row note: “Flex service tier (0.8× standard).”
- priority (37 rows). Across 37 models with both prices, the median priority price is 1.5× standard. DeepInfra row note: “Priority service tier (1.5× standard).”
Cached input: 45 of 92 standard prices include a cache-read price, a median 20% of the input price. What cached input means.
What we recorded about DeepInfra's pricing page: Per-model prices read from each model page on deepinfra.com (cross-checked against DeepInfra's own public model list API). Standard price shown is the price currently charged, including any promotional discount shown on the page. Priority (1.5x) and Flex (0.8x) rows are listed where the model page shows them. Embedding, image, speech and other non-text models excluded.
Is DeepInfra cheaper than the model makers' own APIs?
Mostly yes. Of 34 standard prices for models whose maker sells its own API, 19 are below the maker's price, 2 above and 13 the same, on the 3:1 blend. The median difference is 6% below the maker. The biggest saving is DeepSeek V4.1 Flash 1017, 72% below DeepSeek. The biggest markup is Claude Sonnet 5, 50% above Anthropic.
BroadNet Inference and DeepInfra
BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 4 models that DeepInfra prices: BroadNet Gemma 4 VL 26B at USD 0.10 / USD 0.22 against DeepInfra's USD 0.07 / USD 0.34 (BroadNet is cheaper on the 3:1 blend); DeepSeek V4.1 Flash at USD 0.175 / USD 0.52 against DeepInfra's USD 0.14 / USD 0.42 (DeepInfra is cheaper on the 3:1 blend); Qwen3.8 27B at USD 0.175 / USD 2.17 against DeepInfra's USD 0.15 / USD 1.875 (DeepInfra is cheaper on the 3:1 blend); GLM 5.3 at USD 0.78 / USD 3.46 against DeepInfra's USD 0.5625 / USD 2.50 (DeepInfra is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.
More on DeepInfra
- DeepInfra's own pricing page (the source; checked 2026-11-14)
- DeepInfra alternative: when low per-token prices are not enough
- LLM API free tiers and rate limits: DeepInfra's free tier and default limits next to other providers'
- All 41 providers compared · Cheapest LLM APIs right now · Download every price (CSV, JSON)
Quick answers
Is DeepInfra OpenAI-compatible?
Yes, for chat completions; Responses API clients use the same base URL. Embeddings, images and speech are documented on a separate page (DeepInfra, chat completions overview, checked 2026-11-15).
What is DeepInfra's API base URL?
https://api.deepinfra.com/v1/openai, as DeepInfra documents it (DeepInfra, chat completions overview, checked 2026-11-15).
Does DeepInfra have a free tier?
No free credit or free tier mentioned on the rate-limits page. Default limits (Default account limit, Per public model): 200 concurrent requests. "every account has a default limit of 200 concurrent requests per model"; no fixed RPM or TPM (DeepInfra rate limits docs, checked 2026-11-14).
Questions
How much does the DeepInfra API cost per token?
DeepInfra's standard prices run from USD 0.02 input and USD 0.04 output per 1M tokens (Llama 3.1 8B Instruct) to USD 10 / USD 50 (Claude Fable 5). The median across 92 standard prices is USD 0.25 input and USD 0.92 output per 1M, which is USD 0.00000025 per input token. Input, cached input and output are billed separately.
What is the cheapest model on DeepInfra?
Llama 3.1 8B Instruct, at USD 0.02 input and USD 0.04 output per 1M tokens (USD 0.025 on a 3:1 input-to-output blend). The cheapest from other makers: Qwen3.5 9B (Qwen) at USD 0.10 / USD 0.15; Gemma 3 4B (Google) at USD 0.05 / USD 0.10; DeepSeek V4 Flash 0731 (DeepSeek) at USD 0.06 / USD 0.18.
Is DeepInfra cheaper than other providers?
It depends on the model. Of 81 models that other providers also price, DeepInfra is the cheapest standard price for 37 (9 of them tied with another provider), for example GLM 5.3, GLM 5.2 and DeepSeek V4.1 Flash 1017; it ties the lowest price, without beating it, for 12 more; another provider is cheaper for 32; and it is the dearest for 8. Its median rank is 1 of a median 5 providers, on a 3:1 input-to-output blend.
Does DeepInfra have batch, cached or priority pricing?
Cached input: yes, for 45 of 92 standard prices, at a median 20% of the input price. Other tiers: flex / spot on 54 rows (median input 20% below standard); priority on 37 rows (median input 1.5× standard).
How much does a chatbot cost per month on DeepInfra?
For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 2.52 on Llama 3.1 8B Instruct, USD 28.98 on Qwen3 VL 235B A22B (the middle of DeepInfra's list) and USD 1,800 on Claude Fable 5. Try your own numbers.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- DeepInfra: pricing page (checked 2026-11-14)
- DeepInfra: Claude Fable 5 price source (checked 2026-11-14)
- DeepInfra: Claude Haiku 4.5 price source (checked 2026-11-14)
- DeepInfra: Claude Opus 4.7 price source (checked 2026-11-14)
- DeepInfra: Claude Opus 4.8 price source (checked 2026-11-14)
- DeepInfra: rate limits and free tier (checked 2026-11-14)
- DeepInfra, chat completions overview (checked 2026-11-15)