# DeepInfra
HQ US · serves 86 tracked open-weights models, 49 confirmed by its own catalog. status page · privacy policy
- models
- 86
- verified
- 49
- of overall top 10
- 8
- cheapest on
- 33 models
- vs best $
- 1.16×
- ctx (median)
- 256k
- tps (median)
- 49
- ttft (median)
- 619ms
- uptime
- 99.9%
# models
| model | rank | $/M in | $/M out | ✓ |
|---|---|---|---|---|
| glm-5.3 | #1 | $0.90 | $4.00 | ✓ |
| kimi-k3 | #2 | $2.85 | $14.25 | ✓ |
| glm-5.3-flash | #3 | $0.15 | $0.50 | ✓ |
| qwen3.8-2.4t-a95b | #4 | $2.00 | $6.00 | — |
| deepseek-v4-flash-0731 | #6 | $0.06 | $0.18 | ✓ |
| deepseek-v4-pro | #7 | $1.30 | $2.60 | ✓ |
| qwen3.8-27b | #8 | $0.20 | $2.50 | ✓ |
| glm-5.2 | #10 | $0.75 | $2.40 | ✓ |
| minimax-m3 | #12 | $0.28 | $1.10 | ✓ |
| glm-5 | #14 | $0.60 | $2.08 | — |
| kimi-k2.6 | #15 | $0.75 | $3.50 | ✓ |
| mimo-v2.5-pro | #16 | $1.00 | $3.00 | — |
| hy3 | #17 | $0.13 | $0.53 | — |
| glm-5.1 | #18 | $1.05 | $3.50 | — |
| kimi-k2.7-code | #19 | $0.68 | $3.40 | — |
| minimax-m2.5 | #20 | $0.15 | $1.15 | — |
| inkling | #21 | $0.95 | $4.05 | — |
| deepseek-v4-flash | #22 | $0.09 | $0.18 | ✓ |
| kimi-k2.5 | #23 | $0.45 | $2.25 | — |
| minimax-m2.7 | #25 | $0.25 | $1.00 | — |
| qwen3.5-27b | #27 | $0.26 | $2.60 | ✓ |
| glm-4.7 | #28 | $0.40 | $1.75 | ✓ |
| qwen3.6-27b | #29 | $0.32 | $3.20 | ✓ |
| qwen3.5-397b-a17b | #31 | $0.45 | $3.00 | ✓ |
| deepseek-v3.2 | #32 | $0.26 | $0.38 | ✓ |
| step-3.5-flash | #33 | $0.10 | $0.30 | — |
| qwen3.5-122b-a10b | #37 | $0.29 | $2.40 | — |
| step-3.7-flash | #39 | $0.20 | $1.15 | — |
| glm-4.6 | #40 | $0.50 | $2.00 | ✓ |
| qwen3.5-35b-a3b | #41 | $0.14 | $1.00 | ✓ |
| qwen3.6-35b-a3b | #43 | $0.10 | $0.95 | ✓ |
| deepseek-v3.1-terminus | #45 | $0.27 | $0.95 | — |
| gemma-4-26b-a4b-it | #47 | $0.07 | $0.34 | ✓ |
| kimi-k2-0905 | #48 | $0.50 | $2.00 | — |
| gemma-4-31b-it | #49 | $0.20 | $0.40 | ✓ |
| glm-4.7-flash | #51 | $0.06 | $0.40 | — |
| granite-4.2-30b | #53 | $0.16 | $0.65 | — |
| qwen3.5-9b | #54 | $0.10 | $0.15 | ✓ |
| deepseek-r1 | #55 | $0.85 | $2.50 | — |
| glm-4.5 | #56 | $0.60 | $2.20 | — |
| deepseek-v3.1 | #57 | $0.25 | $0.95 | ✓ |
| qwen3-235b-a22b-instruct-2507 | #59 | $0.09 | $0.55 | ✓ |
| qwen3-coder-480b-a35b | #60 | $0.30 | $1.00 | — |
| kimi-k2-instruct | #61 | $0.50 | $2.00 | — |
| gpt-oss-120b | #63 | $0.04 | $0.17 | ✓ |
| granite-4.2-8b | #64 | $0.06 | $0.25 | ✓ |
| glm-4.5-air | #68 | $0.20 | $1.10 | — |
| qwen3-vl-235b-a22b-instruct | #73 | $0.20 | $0.88 | ✓ |
| gpt-oss-20b | #75 | $0.03 | $0.14 | ✓ |
| deepseek-v3 | #77 | $0.32 | $0.89 | ✓ |
| granite-4.2-3b | #82 | $0.03 | $0.12 | — |
| qwq-32b | #85 | $0.15 | $0.40 | — |
| llama-4-maverick | #86 | $0.20 | $0.80 | — |
| qwen3-vl-30b-a3b-instruct | #90 | $0.15 | $0.60 | ✓ |
| nvidia-nemotron-nano-9b-v2 | #93 | $0.04 | $0.16 | — |
| llama-3.3-70b-instruct | #94 | $0.10 | $0.32 | — |
| qwen2.5-72b-instruct | #99 | $0.36 | $0.40 | ✓ |
| mistral-small-3.2-24b | #100 | $0.07 | $0.20 | ✓ |
| llama-4-scout | #103 | $0.10 | $0.30 | ✓ |
| gemma-3-27b-it | #106 | $0.08 | $0.16 | ✓ |
| phi-4 | #107 | $0.07 | $0.14 | ✓ |
| gemma-3-12b-it | #109 | $0.05 | $0.15 | ✓ |
| deepseek-chat-v3-0324 | — | $0.24 | $0.90 | — |
| deepseek-r1-0528 | — | $0.50 | $2.15 | ✓ |
| deepseek-v4-pro-0813 | — | $1.30 | $2.60 | ✓ |
| deepseek-v4.1-flash | — | $0.20 | $0.60 | ✓ |
| deepseek-v4.1-flash-1017 | — | $0.20 | $0.60 | ✓ |
| hy4-preview | — | $0.83 | $2.50 | ✓ |
| ling-3.1-flash | — | $0.30 | $0.90 | ✓ |
| llama-3.1-405b-instruct | — | $0.80 | $0.80 | — |
| mimo-v2.5 | — | $0.14 | $0.28 | — |
| mimo-v2.6-flash | — | $0.14 | $0.28 | ✓ |
| mimo-v2.6-pro | — | $0.43 | $0.87 | ✓ |
| muse-glimmer-30b | — | $0.30 | $1.20 | ✓ |
| nemotron-3-nano-30b-a3b | — | $0.05 | $0.20 | — |
| nemotron-3-super-120b-a12b | — | $0.09 | $0.40 | — |
| nemotron-3-ultra-550b-a55b | — | $0.40 | $1.76 | — |
| nemotron-3.5-content-safety | — | $0.20 | $0.20 | — |
| nemotron-3.5-super-vl | — | $0.15 | $0.50 | ✓ |
| 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 | — |
| step-5-preview | — | $1.00 | $2.70 | ✓ |
# recent changes
| when (UTC) | model | change |
|---|---|---|
| Oct 26 05:00 | gemma-4-31b-it | $/M input $0.09 → $0.20 ↑ 122.2% |
| Oct 26 05:00 | gemma-4-31b-it | $/M output $0.34 → $0.40 ↑ 17.6% |
| Oct 25 20:59 | gemma-4-31b-it | $/M input $0.20 → $0.09 ↓ 55.0% |
| Oct 25 20:59 | gemma-4-31b-it | $/M output $0.40 → $0.34 ↓ 15.0% |
| Oct 25 20:59 | step-3.5-flash | now listed (via hfrouter) |
| Oct 25 16:36 | ling-3.0-flash-fin | no longer listed |
| Oct 25 16:36 | step-3.5-flash | no longer listed |
| Oct 25 11:47 | gemma-4-31b-it | $/M input $0.09 → $0.20 ↑ 122.2% |
| Oct 25 11:47 | gemma-4-31b-it | $/M output $0.34 → $0.40 ↑ 17.6% |
| Oct 25 09:53 | mimo-v2.5 | $/M input $0.40 → $0.14 ↓ 65.0% [source switch] |
| Oct 25 09:53 | mimo-v2.5 | $/M output $2.00 → $0.28 ↓ 86.0% [source switch] |
| Oct 25 04:57 | gemma-4-31b-it | $/M input $0.20 → $0.09 ↓ 55.0% |
| Oct 25 04:57 | gemma-4-31b-it | $/M output $0.40 → $0.34 ↓ 15.0% |
| Oct 25 04:57 | mimo-v2.5 | $/M input $0.14 → $0.40 ↑ 185.7% [source switch] |
| Oct 25 04:57 | mimo-v2.5 | $/M output $0.28 → $2.00 ↑ 614.3% [source switch] |
| Oct 24 20:59 | gemma-4-31b-it | $/M input $0.09 → $0.20 ↑ 122.2% |
| Oct 24 20:59 | gemma-4-31b-it | $/M output $0.34 → $0.40 ↑ 17.6% |
| Oct 24 16:05 | gemma-4-31b-it | $/M input $0.20 → $0.09 ↓ 55.0% |
| Oct 24 16:05 | gemma-4-31b-it | $/M output $0.40 → $0.34 ↓ 15.0% |
| Oct 24 16:05 | step-3.5-flash | now listed (via hfrouter) |
| Oct 24 11:18 | gemma-4-31b-it | $/M input $0.09 → $0.20 ↑ 122.2% |
| Oct 24 11:18 | gemma-4-31b-it | $/M output $0.34 → $0.40 ↑ 17.6% |
| Oct 24 11:18 | step-3.5-flash | no longer listed |
| Oct 24 09:36 | gemma-4-31b-it | $/M input $0.20 → $0.09 ↓ 55.0% |
| Oct 24 09:36 | gemma-4-31b-it | $/M output $0.40 → $0.34 ↓ 15.0% |
| Oct 24 04:48 | ling-3.0-flash-fin | now listed (via hfrouter) |
| Oct 23 21:31 | gemma-4-31b-it | $/M input $0.09 → $0.20 ↑ 122.2% |
| Oct 23 21:31 | gemma-4-31b-it | $/M output $0.34 → $0.40 ↑ 17.6% |
| Oct 23 21:31 | ling-3.0-flash-fin | no longer listed |
all providers · machine-readable: providers.json