DeepInfra vs Runcrate
API prices for the 53 models both providers list, side by side. Prices as of October 25, 2026.
DeepInfra is cheaper on 43 of the 53 models we can price on both, Runcrate on 10. DeepInfra is 5% cheaper than Runcrate on the median shared model. By category — LLMs: DeepInfra cheaper on 37 of 47; Embeddings: DeepInfra cheaper on 4 of 4.
Runcrate is an aggregator: it routes requests to models hosted by other providers, so a price there may be another provider's rate passed through.
Each side is its lowest listed price for the model. LLMs are compared on input + output price per 1M tokens; image, video and audio models on their per-unit price. Resolution, tier and variant can change the price. Methodology
At a glance
| DeepInfra | Runcrate | |
|---|---|---|
| Type | Serverless | Aggregator |
| Models we track | 80 | 100 |
| Free tier | Yes | DeepSeek V4.1 Flash, GLM 5.3, GLM 5.3 Flash, gpt-oss 120B and Qwen3.8 Flash free with a GitHub account at least 30 days old (session cap plus weekly allowance, resets Monday) |
| OpenAI-compatible API | ||
| Function calling | — | |
| JSON mode | — | |
| Vision | ||
| Batch API | — | — |
| Fine-tuning | — | |
| SOC 2 | — | — |
| HIPAA | — | — |
| GDPR | — | — |
Prices for models on both
LLM prices are input / output per 1M tokens. The cheaper side is highlighted.
LLMs (47 · DeepInfra cheaper on 37, Runcrate on 10)
| Model | DeepInfra | Runcrate | Difference |
|---|---|---|---|
| Claude Fable 5 Anthropic | $10.00 / $50.00 | $10.50 / $52.50 | DeepInfra −5% |
| Claude Opus 5 Anthropic | $5.00 / $25.00 | $5.25 / $26.25 | DeepInfra −5% |
| Claude Opus 5.5 Anthropic | $4.00 / $20.00 | $4.20 / $21.00 | DeepInfra −5% |
| Claude Sonnet 5 Anthropic | $3.00 / $15.00 | $3.15 / $15.75 | DeepInfra −5% |
| Claude Sonnet 5.5 Anthropic | $2.00 / $10.00 | $2.10 / $10.50 | DeepInfra −5% |
| DeepSeek V3.2 DeepSeek | $0.260 / $0.380 | $0.273 / $0.399 | DeepInfra −5% |
| DeepSeek V4 Flash DeepSeek | $0.060 / $0.180 0731 | $0.095 / $0.189 | DeepInfra −15% |
| DeepSeek V4 Pro DeepSeek | $1.30 / $2.60 | $1.36 / $2.73 | DeepInfra −5% |
| DeepSeek V4.1 Flash DeepSeek | $0.200 / $0.600 | $0.147 / $0.441 | Runcrate −27% |
| GLM 4.7 Zhipu AI | $0.060 / $0.400 | $0.336 / $1.47 | DeepInfra −75% |
| GLM 5.2 Z.ai | $0.750 / $2.40 | $0.591 / $1.89 | Runcrate −21% |
| GLM 5.3 Z.ai | $0.900 / $4.00 | $0.591 / $2.63 | Runcrate −34% |
| GLM 5.3 Flash Z.ai | $0.150 / $0.500 | $0.158 / $0.525 | DeepInfra −5% |
| GPT OSS 120B OpenAI | $0.037 / $0.170 | $0.039 / $0.178 | DeepInfra −5% |
| Gemini 2.5 Flash Google | $0.300 / $2.50 | $0.158 / $1.31 | Runcrate −48% |
| Gemini 2.5 Pro Google | $1.25 / $10.00 | $0.656 / $5.25 | Runcrate −48% |
| Gemini 3.1 Flash Lite Google | $0.250 / $1.50 | $0.263 / $1.57 | DeepInfra −5% |
| Gemini 3.1 Pro Google | $2.00 / $12.00 | $2.10 / $12.60 | DeepInfra −5% |
| Gemini 3.5 Flash Google | $1.50 / $9.00 | $1.57 / $9.45 | DeepInfra −5% |
| Gemini 3.7 Flash Google | $0.750 / $3.75 | $0.787 / $3.94 | DeepInfra −5% |
| Gemma 3 12B Google | $0.050 / $0.150 | $0.042 / $0.126 | Runcrate −16% |
| Gemma 3 27B Google | $0.080 / $0.160 | $0.084 / $0.168 | DeepInfra −5% |
| Gemma 3 4B Google | $0.050 / $0.100 | $0.052 / $0.105 | DeepInfra −5% |
| Gemma 4 26B A4B Google | $0.070 / $0.340 | $0.073 / $0.357 | DeepInfra −5% |
| Gemma 4 31B Google | $0.200 / $0.400 | $0.142 / $0.535 | DeepInfra −11% |
| Granite 4.2 8B IBM | $0.060 / $0.250 | $0.063 / $0.263 | DeepInfra −5% |
| Hy4 Preview Tencent | $0.834 / $2.50 | $0.876 / $2.63 | DeepInfra −5% |
| Inkling Small Thinking Machines | $0.450 / $1.20 | $0.472 / $1.26 | DeepInfra −5% |
| Kimi K2.6 Moonshot AI | $0.750 / $3.50 | $0.787 / $3.67 | DeepInfra −5% |
| Kimi K3 Moonshot AI | $2.85 / $14.25 | $2.99 / $14.96 | DeepInfra −5% |
| MiMo V2.6 Flash Xiaomi | $0.140 / $0.280 | $0.096 / $0.191 | Runcrate −32% |
| MiMo V2.6 Pro Xiaomi | $0.430 / $0.870 | $0.406 / $0.822 | Runcrate −6% |
| MiniMax M3 MiniMax | $0.280 / $1.10 | $0.294 / $1.16 | DeepInfra −5% |
| Muse Glimmer 30B Meta | $0.300 / $1.20 | $0.315 / $1.26 | DeepInfra −5% |
| Qwen 3.5 9B Alibaba | $0.100 / $0.150 | $0.105 / $0.158 | DeepInfra −5% |
| Qwen3 Next 80B A3B Instruct Alibaba | $0.090 / $1.10 | $0.076 / $0.924 | Runcrate −16% |
| Qwen3 VL 235B A22B Instruct Alibaba | $0.200 / $0.880 | $0.210 / $0.924 | DeepInfra −5% |
| Qwen3 VL 30B A3B Instruct Alibaba | $0.150 / $0.600 | $0.158 / $0.630 | DeepInfra −5% |
| Qwen3.6 27B Alibaba | $0.320 / $3.20 | $0.336 / $3.36 | DeepInfra −5% |
| Qwen3.6 35B A3B Alibaba | $0.100 / $0.950 | $0.105 / $0.998 | DeepInfra −5% |
| Qwen3.7 Max Alibaba | $2.50 / $7.50 | $2.63 / $7.88 | DeepInfra −5% |
| Qwen3.8 27B Alibaba | $0.200 / $2.50 | $0.158 / $1.97 | Runcrate −21% |
| Qwen3.8 Flash Alibaba | $0.113 / $0.382 | $0.119 / $0.401 | DeepInfra −5% |
| Qwen3.8 Max Alibaba | $1.65 / $4.95 | $1.73 / $5.20 | DeepInfra −5% |
| Seed 2.0 Code ByteDance | $0.500 / $3.00 | $0.525 / $3.15 | DeepInfra −5% |
| Seed-2.0-Mini ByteDance | $0.100 / $0.400 | $0.105 / $0.420 | DeepInfra −5% |
| gpt-oss-20b OpenAI | $0.030 / $0.140 | $0.032 / $0.147 | DeepInfra −5% |
Image generation (1 · DeepInfra cheaper on 1, Runcrate on 0)
| Model | DeepInfra | Runcrate | Difference |
|---|---|---|---|
| Flux 2 Max Black Forest Labs | $0.070/img | $0.073/img | DeepInfra −5% |
Audio & speech (1 · DeepInfra cheaper on 1, Runcrate on 0)
| Model | DeepInfra | Runcrate | Difference |
|---|---|---|---|
| Qwen 3 TTS Alibaba | $20.00/1M chars | $105.00/1M chars | DeepInfra −81% |
Embeddings (4 · DeepInfra cheaper on 4, Runcrate on 0)
| Model | DeepInfra | Runcrate | Difference |
|---|---|---|---|
| BGE-M3 BAAI | $0.010 in | $0.011 in | DeepInfra −5% |
| Qwen3 Embedding 0.6B Alibaba | $0.010 in | $0.011 in | DeepInfra −5% |
| Qwen3 Embedding 4B Alibaba | $0.020 in | $0.021 in | DeepInfra −5% |
| Qwen3 Embedding 8B Alibaba | $0.010 in | $0.011 in | DeepInfra −5% |
Only on DeepInfra (27)
Only on Runcrate (47)
DeepInfra vs Runcrate FAQ
Is DeepInfra cheaper than Runcrate?
Usually yes. DeepInfra is cheaper on 43 of the 53 models we can price on both, Runcrate on 10. DeepInfra is 5% cheaper than Runcrate on the median shared model.
Which has more models, DeepInfra or Runcrate?
We track 80 models on DeepInfra and 100 on Runcrate. 53 are on both, 27 only on DeepInfra and 47 only on Runcrate.
Do DeepInfra and Runcrate have a free tier?
DeepInfra: yes. Runcrate: yes (DeepSeek V4.1 Flash, GLM 5.3, GLM 5.3 Flash, gpt-oss 120B and Qwen3.8 Flash free with a GitHub account at least 30 days old (session cap plus weekly allowance, resets Monday)).
Which models do both DeepInfra and Runcrate offer?
53 models, including BGE-M3, Claude Fable 5, Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5, Claude Sonnet 5.5 and more. The full list with both prices is in the table above.