# DeepInfra models

[Get started](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai%3Futm_source%3Dgateway-providers-page%26utm_campaign%3Dai-gateway-providers&title=Get+Started+with+Vercel+AI+Gateway) [Read the docs](https://vercel.com/docs/ai-gateway)

Route requests to DeepInfra through Vercel AI Gateway. Compare the models DeepInfra serves, with unified billing and automatic failover across providers.

All

Text

Retrieval

| Model | Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | ZDR | No Training | Regional Inference | Free Tier | Released |  |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |

| ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3.8-27b](/ai-gateway/models/qwen3.8-27b) | 262K | 0.4s | 38tps | $0.40/M | $3/M | Read:$0.04/M Write:— | — | +1 |  |  |  |  | 08/14/2026 |  |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ![nvidia logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnvidia.png&w=48&q=75) [nvidia/nemotron-3.5-lightning](/ai-gateway/models/nemotron-3.5-lightning) | 262K | 0.3s | 317tps | $0.08/M | $0.20/M | Read:$0.04/M Write:— | — |  |  |  |  |  | 08/11/2026 |  |
| ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3.8-2.4t-a95b](/ai-gateway/models/qwen3.8-2.4t-a95b) | 256K | 1.6s | 49tps | $1.65/M | $4.95/M | Read:$0.12/M Write:— | — |  |  |  |  |  | 08/03/2026 |  |
| ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v4-flash-0731](/ai-gateway/models/deepseek-v4-flash-0731) | 1M | 1.2s | 35tps | $0.09/M | $0.18/M | Read:$0.02/M Write:— | — |  |  |  |  |  | 07/31/2026 |  |
| ![thinkingmachines logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fthinkingmachines.png&w=48&q=75) [thinkingmachines/inkling-small](/ai-gateway/models/inkling-small) | 1M | 0.6s | 128tps | $0.58/M | $1.44/M | Read:$0.12/M Write:— | — | +2 |  |  |  |  | 07/30/2026 |  |
| T [tencent/hy3](/ai-gateway/models/hy3) | 262K | 0.3s | 74tps | $0.14/M | $0.58/M | Read:$0.04/M Write:— | — |  |  |  |  |  | 07/06/2026 |  |
| ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [zai/glm-5.2](/ai-gateway/models/glm-5.2) | 1M | 0.6s | 47tps | $0.95/M | $3/M | Read:$0.18/M Write:— | — |  |  |  |  |  | 06/16/2026 |  |
| ![moonshotai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fmoonshotai.png&w=48&q=75) [moonshotai/kimi-k2.7-code](/ai-gateway/models/kimi-k2.7-code) | 262K | 0.7s | 36tps | $0.74/M | $3.50/M | Read:$0.15/M Write:— | — | +1 |  |  |  |  | 06/12/2026 |  |
| ![nvidia logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnvidia.png&w=48&q=75) [nvidia/nemotron-3-ultra-550b-a55b](/ai-gateway/models/nemotron-3-ultra-550b-a55b) | 262K | 1.0s | 37tps | $0.50/M | $2.50/M | Read:$0.15/M Write:— | — |  |  |  |  |  | 06/04/2026 |  |
| ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v4-flash](/ai-gateway/models/deepseek-v4-flash) | 1M | 1.6s | 32tps | $0.09/M | $0.18/M | Read:$0.02/M Write:— | — |  |  |  |  |  | 04/23/2026 |  |
| ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v4-pro](/ai-gateway/models/deepseek-v4-pro) | 66K | 0.6s | 42tps | $1.74/M | $3.48/M | Read:$0.14/M Write:— | — |  |  |  |  |  | 04/23/2026 |  |
| ![xiaomi logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fxiaomi.png&w=48&q=75) [xiaomi/mimo-v2.5](/ai-gateway/models/mimo-v2.5) | 262K | 1.1s | 65tps | $0.40/M | $2/M | Read:$0.08/M Write:— | — | +1 |  |  |  |  | 04/22/2026 |  |
| ![xiaomi logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fxiaomi.png&w=48&q=75) [xiaomi/mimo-v2.5-pro](/ai-gateway/models/mimo-v2.5-pro) | 1M | 0.6s | 46tps | $1/M | $3/M | Read:$0.2/M Write:— | — |  |  |  |  |  | 04/22/2026 |  |
| ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [zai/glm-5.1](/ai-gateway/models/glm-5.1) | 203K | 4.7s | 11tps | $1.40/M | $4.40/M | Read:$0.26/M Write:— | — |  |  |  |  |  | 04/07/2026 |  |
| ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [zai/glm-5](/ai-gateway/models/glm-5) | 203K | 0.8s | 32tps | $0.80/M | $2.56/M | Read:$0.16/M Write:— | — |  |  |  |  |  | 02/12/2026 |  |
| ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) [minimax/minimax-m2.5](/ai-gateway/models/minimax-m2.5) | 197K | 0.5s | 127tps | $0.27/M | $0.95/M | Read:$0.03/M Write:— | — |  |  |  |  |  | 02/12/2026 |  |
| ![stepfun logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fstepfun.png&w=48&q=75) [stepfun/step-3.5-flash](/ai-gateway/models/step-3.5-flash) | 262K | 0.3s | 166tps | $0.09/M | $0.30/M | Read:$0.02/M Write:— | — | +1 |  |  |  |  | 01/29/2026 |  |
| ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [zai/glm-4.7](/ai-gateway/models/glm-4.7) | 203K | 0.5s | 37tps | $0.43/M | $1.75/M | Read:$0.08/M Write:— | — |  |  |  |  |  | 12/22/2025 |  |
| ![nvidia logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnvidia.png&w=48&q=75) [nvidia/nemotron-3-nano\-30b-a3b](/ai-gateway/models/nemotron-3-nano-30b-a3b) | 262K | 0.3s | 228tps | $0.05/M | $0.24/M |  | — |  |  |  |  |  | 12/15/2025 |  |
| ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v3.2](/ai-gateway/models/deepseek-v3.2) | 164K | 8.7s | 9tps | $0.26/M | $0.38/M | Read:$0.13/M Write:— | — |  |  |  |  |  | 12/01/2025 |  |
| ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v3.2-thinking](/ai-gateway/models/deepseek-v3.2-thinking) | 164K | 13.1s | 8tps | $0.26/M | $0.38/M | Read:$0.13/M Write:— | — |  |  |  |  |  | 12/01/2025 |  |
| ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3-embedding-0.6b](/ai-gateway/models/qwen3-embedding-0.6b) | 33K |  |  | $0.01/M |  |  | — |  |  |  |  |  | 11/14/2025 |  |
| ![moonshotai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fmoonshotai.png&w=48&q=75) [moonshotai/kimi-k2-thinking](/ai-gateway/models/kimi-k2-thinking) | 216K | 0.6s | 37tps | $0.47/M | $2/M | Read:$0.14/M Write:— | — |  |  |  |  |  | 11/06/2025 |  |
| ![nvidia logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnvidia.png&w=48&q=75) [nvidia/nemotron-nano-12b-v2-vl](/ai-gateway/models/nemotron-nano-12b-v2-vl) | 131K | 1.1s | 47tps | $0.20/M | $0.60/M |  | — |  |  |  |  |  | 10/28/2025 |  |
| ![zai logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fzai-256.png%3Fv%3D1786428782581&w=48&q=75) [zai/glm-4.6](/ai-gateway/models/glm-4.6) | 203K | 0.4s | 63tps | $0.50/M | $2/M | Read:$0.1/M Write:— | — |  |  |  |  |  | 09/30/2025 |  |
| ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3-vl-235b-a22b-instruct](/ai-gateway/models/qwen3-vl-235b-a22b-instruct) | 262K | 0.9s | 10tps | $0.20/M | $0.88/M | Read:$0.11/M Write:— | — |  |  |  |  |  | 09/23/2025 |  |
| ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3-vl-instruct](/ai-gateway/models/qwen3-vl-instruct) | 262K | 0.8s | 10tps | $0.20/M | $0.88/M | Read:$0.11/M Write:— | — |  |  |  |  |  | 09/23/2025 |  |
| ![alibaba logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Falibaba%20model%20logo.png&w=48&q=75) [alibaba/qwen3-next-80b-a3b-instruct](/ai-gateway/models/qwen3-next-80b-a3b-instruct) | 262K | 0.5s | 36tps | $0.09/M | $1.10/M |  | — |  |  |  |  |  | 09/11/2025 |  |
| ![deepseek logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepseek.png&w=48&q=75) [deepseek/deepseek-v3.1](/ai-gateway/models/deepseek-v3.1) | 164K | 1.1s | 13tps | $0.25/M | $0.95/M | Read:$0.13/M Write:— | — |  |  |  |  |  | 08/21/2025 |  |
| ![nvidia logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnvidia.png&w=48&q=75) [nvidia/nemotron-nano-9b-v2](/ai-gateway/models/nemotron-nano-9b-v2) | 131K | 0.3s | 215tps | $0.04/M | $0.16/M |  | — |  |  |  |  |  | 08/18/2025 |  |