# DeepInfra
HQ US · serves 68 tracked open-weights models, 49 confirmed by its own catalog. status page · privacy policy
- models
- 68
- verified
- 49
- of overall top 10
- 10
- cheapest on
- 26 models
- vs best $
- 1.10×
- ctx (median)
- 198k
- tps (median)
- 57
- ttft (median)
- 285ms
- uptime
- 99.5%
# models
| model | rank | $/M in | $/M out | ✓ |
|---|---|---|---|---|
| kimi-k3 | #1 | $2.85 | $14.25 | ✓ |
| deepseek-v4-pro | #2 | $1.30 | $2.60 | ✓ |
| glm-5.2 | #3 | $0.75 | $2.40 | ✓ |
| kimi-k2.6 | #4 | $0.75 | $3.50 | ✓ |
| hy3 | #5 | $0.14 | $0.58 | ✓ |
| minimax-m3 | #6 | $0.28 | $1.10 | ✓ |
| kimi-k2.7-code | #7 | $0.68 | $3.40 | ✓ |
| deepseek-v4-flash | #8 | $0.09 | $0.18 | ✓ |
| glm-5 | #9 | $0.60 | $2.08 | — |
| glm-5.1 | #10 | $1.05 | $3.50 | ✓ |
| minimax-m2.5 | #11 | $0.15 | $1.15 | — |
| kimi-k2.5 | #12 | $0.45 | $2.25 | — |
| qwen3.6-27b | #13 | $0.32 | $3.20 | ✓ |
| qwen3.5-27b | #14 | $0.26 | $2.60 | ✓ |
| glm-4.7 | #15 | $0.40 | $1.75 | ✓ |
| qwen3.6-35b-a3b | #16 | $0.10 | $0.95 | ✓ |
| qwen3.5-397b-a17b | #17 | $0.45 | $3.00 | ✓ |
| qwen3.5-122b-a10b | #18 | $0.29 | $2.40 | ✓ |
| deepseek-v3.2 | #19 | $0.26 | $0.38 | ✓ |
| kimi-k2-0905 | #22 | $0.50 | $2.00 | — |
| qwen3.5-35b-a3b | #23 | $0.14 | $1.00 | ✓ |
| glm-4.6 | #24 | $0.50 | $2.00 | ✓ |
| gemma-4-31b-it | #25 | $0.09 | $0.34 | ✓ |
| granite-4.2-30b | #26 | $0.16 | $0.65 | ✓ |
| gemma-4-26b-a4b-it | #27 | $0.07 | $0.34 | ✓ |
| glm-4.7-flash | #28 | $0.06 | $0.40 | — |
| qwen3-coder-480b-a35b | #32 | $0.30 | $1.00 | — |
| deepseek-r1 | #33 | $0.85 | $2.50 | — |
| glm-4.5 | #34 | $0.60 | $2.20 | — |
| gpt-oss-120b | #35 | $0.04 | $0.17 | ✓ |
| kimi-k2-instruct | #36 | $0.50 | $2.00 | — |
| deepseek-v3.1 | #37 | $0.25 | $0.95 | ✓ |
| granite-4.2-3b | #38 | $0.03 | $0.12 | ✓ |
| qwen3-235b-a22b-instruct-2507 | #39 | $0.09 | $0.55 | ✓ |
| glm-4.5-air | #41 | $0.20 | $1.10 | — |
| deepseek-v3 | #42 | $0.32 | $0.89 | ✓ |
| qwen3-vl-235b-a22b-instruct | #45 | $0.20 | $0.88 | ✓ |
| llama-4-maverick | #47 | $0.20 | $0.80 | ✓ |
| qwq-32b | #48 | $0.15 | $0.40 | — |
| qwen3-vl-30b-a3b-instruct | #51 | $0.15 | $0.60 | ✓ |
| nvidia-nemotron-nano-9b-v2 | #52 | $0.04 | $0.16 | — |
| gemma-3-27b-it | #54 | $0.08 | $0.16 | ✓ |
| deepseek-r1-0528 | — | $0.50 | $2.15 | ✓ |
| deepseek-v3.1-terminus | — | $0.27 | $0.95 | — |
| deepseek-v4-flash-0731 | — | $0.08 | $0.18 | ✓ |
| gemma-3-12b-it | — | $0.05 | $0.15 | ✓ |
| gpt-oss-20b | — | $0.03 | $0.14 | ✓ |
| inkling | — | $0.95 | $4.05 | ✓ |
| ling-3.0-flash-fin | — | $0.06 | $0.18 | ✓ |
| llama-3.1-405b-instruct | — | $0.80 | $0.80 | — |
| llama-3.3-70b-instruct | — | $0.10 | $0.32 | — |
| llama-4-scout | — | $0.10 | $0.30 | ✓ |
| mimo-v2.5 | — | $0.40 | $2.00 | ✓ |
| mimo-v2.5-pro | — | $1.00 | $3.00 | ✓ |
| minimax-m2.7 | — | $0.25 | $1.00 | — |
| mistral-small-3.2-24b | — | $0.07 | $0.20 | ✓ |
| muse-glimmer-30b | — | $0.30 | $1.20 | ✓ |
| nemotron-3-nano-30b-a3b | — | $0.05 | $0.20 | ✓ |
| phi-4 | — | $0.07 | $0.14 | ✓ |
| qwen2.5-72b-instruct | — | $0.36 | $0.40 | ✓ |
| qwen2.5-coder-32b | — | $0.07 | $0.16 | — |
| qwen3-14b | — | $0.12 | $0.24 | ✓ |
| qwen3-235b-a22b | — | $0.20 | $0.60 | — |
| qwen3-30b-a3b | — | $0.12 | $0.50 | ✓ |
| qwen3-32b | — | $0.08 | $0.28 | ✓ |
| qwen3-next-80b-a3b-thinking | — | $0.14 | $1.40 | — |
| qwen3.5-9b | — | $0.10 | $0.15 | ✓ |
| qwen3.8-2.4t-a95b | — | $2.00 | $6.00 | ✓ |
# recent changes
| when (UTC) | model | change |
|---|---|---|
| Sep 5 04:41 | gemma-4-31b-it | $/M input $0.13 → $0.09 ↓ 30.8% |
| Sep 5 04:41 | gemma-4-31b-it | $/M output $0.38 → $0.34 ↓ 10.5% |
| Sep 4 20:51 | gemma-4-31b-it | $/M input $0.09 → $0.13 ↑ 44.4% |
| Sep 4 20:51 | gemma-4-31b-it | $/M output $0.34 → $0.38 ↑ 11.8% |
| Sep 4 09:43 | gemma-4-31b-it | $/M input $0.13 → $0.09 ↓ 30.8% |
| Sep 4 09:43 | gemma-4-31b-it | $/M output $0.38 → $0.34 ↓ 10.5% |
| Sep 4 04:45 | gemma-4-31b-it | $/M input $0.09 → $0.13 ↑ 44.4% |
| Sep 4 04:45 | gemma-4-31b-it | $/M output $0.34 → $0.38 ↑ 11.8% |
| Sep 3 21:08 | gemma-4-31b-it | $/M input $0.13 → $0.09 ↓ 30.8% |
| Sep 3 21:08 | gemma-4-31b-it | $/M output $0.38 → $0.34 ↓ 10.5% |
| Sep 3 11:26 | gemma-4-31b-it | $/M input $0.09 → $0.13 ↑ 44.4% |
| Sep 3 11:26 | gemma-4-31b-it | $/M output $0.34 → $0.38 ↑ 11.8% |
| Sep 3 09:55 | gemma-4-31b-it | $/M input $0.13 → $0.09 ↓ 30.8% |
| Sep 3 09:55 | gemma-4-31b-it | $/M output $0.38 → $0.34 ↓ 10.5% |
| Sep 2 09:42 | gemma-4-31b-it | $/M input $0.09 → $0.13 ↑ 44.4% |
| Sep 2 09:42 | gemma-4-31b-it | $/M output $0.34 → $0.38 ↑ 11.8% |
| Sep 2 04:47 | gemma-4-31b-it | $/M input $0.13 → $0.09 ↓ 30.8% |
| Sep 2 04:47 | gemma-4-31b-it | $/M output $0.38 → $0.34 ↓ 10.5% |
| Sep 1 11:49 | gemma-4-31b-it | $/M input $0.09 → $0.13 ↑ 44.4% |
| Sep 1 11:49 | gemma-4-31b-it | $/M output $0.34 → $0.38 ↑ 11.8% |
| Sep 1 10:11 | gemma-4-31b-it | $/M input $0.13 → $0.09 ↓ 30.8% |
| Sep 1 10:11 | gemma-4-31b-it | $/M output $0.38 → $0.34 ↓ 10.5% |
| Sep 1 05:21 | gemma-4-31b-it | $/M input $0.09 → $0.13 ↑ 44.4% |
| Sep 1 05:21 | gemma-4-31b-it | $/M output $0.34 → $0.38 ↑ 11.8% |
| Aug 31 11:38 | gemma-4-31b-it | $/M input $0.13 → $0.09 ↓ 30.8% |
| Aug 31 11:38 | gemma-4-31b-it | $/M output $0.38 → $0.34 ↓ 10.5% |
all providers · machine-readable: providers.json