Qwen/Qwen3.8-2.4T-A95B
Input$2
Output$6
Cache$0.20
← ProvidersQwen3.8 2.4T A95B Kimi K2.7 Codedeprecated · Not a current offering · checked 2026-11-03 GLM-5.2current · Recent price · checked 2026-11-03 GLM-5.3current · Recent price · checked 2026-11-03 V4 Flashcurrent · Recent price · checked 2026-11-03 MiMo V2.6 Flashcurrent · Recent price · checked 2026-11-03 MiMo V2.6 Procurrent · Recent price · checked 2026-11-03 GLM-5.3-Flashcurrent · Recent price · checked 2026-11-03 Step 5 Previewdeprecated · Not a current offering · checked 2026-11-03 Hy4 previewcurrent · Recent price · checked 2026-11-03 Qwen3.8 Flashcurrent · Recent price · checked 2026-11-03 Qwen3.8 27Bcurrent · Recent price · checked 2026-11-03 ai/DeepSeek-V4-Procurrent · Recent price · checked 2026-11-03 Qwen3.8 Maxcurrent · Recent price · checked 2026-11-03 Inkling Smallcurrent · Recent price · checked 2026-11-03 Kimi K3current · Recent price · checked 2026-11-03 Inklingdeprecated · Not a current offering · checked 2026-11-03 Hy3deprecated · Not a current offering · checked 2026-11-03 Claude Fable 5current · Recent price · checked 2026-11-03 M3current · Recent price · checked 2026-11-03 Step 3.7 Flashdeprecated · Not a current offering · checked 2026-11-03 Qwen3.7 Maxcurrent · Recent price · checked 2026-11-03 Seed 2.0 Minicurrent · Recent price · checked 2026-11-03 Nemotron 3 Nano Omni 30B A3B Reasoningdeprecated · Not a current offering · checked 2026-11-03 MiMo-V2.5deprecated · Not a current offering · checked 2026-11-03 MiMo-V2.5-Prodeprecated · Not a current offering · checked 2026-11-03 Qwen3.6 27Bcurrent · Recent price · checked 2026-11-03 Kimi K2.6current · Recent price · checked 2026-11-03 Qwen3.6 35B-A3Bcurrent · Recent price · checked 2026-11-03 glm-5.1deprecated · Not a current offering · checked 2026-11-03 Gemma 4 31B ITcurrent · Recent price · checked 2026-11-03 Gemma 4 26B A4B ITcurrent · Recent price · checked 2026-11-03 Gemma 4 E4B ITdeprecated · Not a current offering · checked 2026-11-03 M2.7deprecated · Not a current offering · checked 2026-11-03 Qwen3.5 9Bcurrent · Recent price · checked 2026-11-03 Qwen3.5 35B-A3Bcurrent · Recent price · checked 2026-11-03 Qwen3.5 122B-A10Bdeprecated · Not a current offering · checked 2026-11-03 Qwen3.5 27Bcurrent · Recent price · checked 2026-11-03 Qwen3.5 397B-A17Bcurrent · Recent price · checked 2026-11-03 Seed 2.0 Codecurrent · Recent price · checked 2026-11-03 Seed 2.0 Procurrent · Recent price · checked 2026-11-03 MiniMaxAI/MiniMax-M2.5deprecated · Not a current offering · checked 2026-11-03 GLM-5deprecated · Not a current offering · checked 2026-11-03 Qwen3 Maxdeprecated · Not a current offering · checked 2026-11-03 GLM-4.7-Flashdeprecated · Not a current offering · checked 2026-11-03 Kimi K2.5deprecated · Not a current offering · checked 2026-11-03 Qwen3 VL 235B A22B Instructcurrent · Recent price · checked 2026-11-03 GLM-4.7current · Recent price · checked 2026-11-03 ai/DeepSeek-V3.2current · Recent price · checked 2026-11-03 nemotron-3-nano-30b-a3bdeprecated · Not a current offering · checked 2026-11-03 Qwen3 VL 30B A3B Instructcurrent · Recent price · checked 2026-11-03 GLM-4.6current · Recent price · checked 2026-11-03 Qwen3-Next 80B-A3B Instructcurrent · Recent price · checked 2026-11-03 V3.1 · mixed source IDscurrent · Recent price · checked 2026-11-03 qwen3-235b-a22b-instruct-2507current · Recent price · checked 2026-11-03 GPT OSS 20Bcurrent · Recent price · checked 2026-11-03 GPT OSS 120Bcurrent · Recent price · checked 2026-11-03 Llama 3.3 Nemotron Super 49B v1.5deprecated · Not a current offering · checked 2026-11-03 qwen3-coder-480b-a35b-instructcurrent · Recent price · checked 2026-11-03 Qwen3 32Bcurrent · Recent price · checked 2026-11-03 R1 0528current · Recent price · checked 2026-11-03 Qwen3-30B-A3Bcurrent · Recent price · checked 2026-11-03 Llama-3.3-70B-Instructcurrent · Recent price · checked 2026-11-03 Llama Guard 4 12Bcurrent · Recent price · checked 2026-11-03 Llama 4 Maverick 17B 128E Instruct FP8deprecated · Not a current offering · checked 2026-11-03 Llama 4 Scout 17B Instructcurrent · Recent price · checked 2026-11-03 V3 0324 · mixed source IDsdeprecated · Not a current offering · checked 2026-11-03 V3current · Recent price · checked 2026-11-03 Gemma 3 12B ITcurrent · Recent price · checked 2026-11-03 Gemma 3 27B ITcurrent · Recent price · checked 2026-11-03 Gemma 3 4B ITcurrent · Recent price · checked 2026-11-03 Mistral Small 3current · Recent price · checked 2026-11-03
Inference provider
Deep Infra
Browse observed model offerings and paired prices from the source-backed catalog. Availability and provider policies should be checked with the provider before deployment.
72 models72 offeringsChecked 2026-11-03
Models and prices
USD per million tokens. Each price links to its observation source.
72 matching offerings
deprecated · Not a current offering · checked 2026-11-03
moonshotai/Kimi-K2.7-Code
Input$0.68
Output$3.40
Cache$0.136
zai-org/GLM-5.2
Input$0.75
Output$2.40
Cache$0.14
zai-org/GLM-5.3
Input$0.90
Output$4
Cache$0.20
deepseek-ai/DeepSeek-V4-Flash-0731
Input$0.06
Output$0.18
Cache$0.015
XiaomiMiMo/MiMo-V2.6-Flash
Input$0.14
Output$0.28
Cache$0.0028
XiaomiMiMo/MiMo-V2.6-Pro
Input$0.43
Output$0.87
Cache$0.0036
zai-org/GLM-5.3-Flash
Input$0.15
Output$0.50
Cache$0.03
stepfun-ai/Step-5-Preview
Input$1
Output$2.70
Cache$0.10
tencent/Hy4-preview
Input$0.834
Output$2.501
Cache$0.042
Qwen/Qwen3.8-Flash
Input$0.113
Output$0.382
Cache$0.0141
Qwen/Qwen3.8-27B
Input$0.20
Output$2.50
Cache$0.05
deepseek-ai/DeepSeek-V4-Pro
Input$1.30
Output$2.60
Cache$0.10
Qwen/Qwen3.8-Max
Input$1.65
Output$4.951
Cache$0.206
thinkingmachines/Inkling-Small
Input$0.45
Output$1.20
Cache$0.10
moonshotai/Kimi-K3
Input$2.85
Output$14.25
Cache$0.285
thinkingmachines/Inkling
Input$0.95
Output$4.05
Cache$0.16
tencent/Hy3
Input$0.13
Output$0.53
Cache$0.033
anthropic/claude-fable-5
Input$10
Output$50
Cache—
MiniMaxAI/MiniMax-M3
Input$0.28
Output$1.10
Cache$0.056
stepfun-ai/Step-3.7-Flash
Input$0.20
Output$1.15
Cache$0.04
Qwen/Qwen3.7-Max
Input$2.50
Output$7.50
Cache$0.50
ByteDance/Seed-2.0-mini
Input$0.10
Output$0.40
Cache$0.02
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Input$0.20
Output$0.80
Cache—
XiaomiMiMo/MiMo-V2.5
Input$0.14
Output$0.28
Cache$0.0028
XiaomiMiMo/MiMo-V2.5-Pro
Input$1
Output$3
Cache$0.20
Qwen/Qwen3.6-27B
Input$0.32
Output$3.20
Cache—
moonshotai/Kimi-K2.6
Input$0.75
Output$3.50
Cache$0.15
Qwen/Qwen3.6-35B-A3B
Input$0.10
Output$0.95
Cache$0.10
zai-org/GLM-5.1
Input$1.05
Output$3.50
Cache$0.205
google/gemma-4-31B-it
Input$0.20
Output$0.40
Cache—
google/gemma-4-26B-A4B-it
Input$0.07
Output$0.34
Cache—
google/gemma-4-E4B-it
Input$0.02
Output$0.10
Cache—
MiniMaxAI/MiniMax-M2.7
Input$0.25
Output$1
Cache$0.05
Qwen/Qwen3.5-9B
Input$0.10
Output$0.15
Cache—
Qwen/Qwen3.5-35B-A3B
Input$0.14
Output$1
Cache$0.05
Qwen/Qwen3.5-122B-A10B
Input$0.29
Output$2.40
Cache—
Qwen/Qwen3.5-27B
Input$0.26
Output$2.60
Cache—
Qwen/Qwen3.5-397B-A17B
Input$0.45
Output$3
Cache$0.22
ByteDance/Seed-2.0-code
Input$0.50
Output$3
Cache$0.10
ByteDance/Seed-2.0-pro
Input$0.50
Output$3
Cache$0.10
MiniMaxAI/MiniMax-M2.5
Input$0.15
Output$1.15
Cache$0.03
zai-org/GLM-5
Input$0.60
Output$2.08
Cache$0.12
Qwen/Qwen3-Max
Input$1.20
Output$6
Cache$0.24
zai-org/GLM-4.7-Flash
Input$0.06
Output$0.40
Cache$0.01
moonshotai/Kimi-K2.5
Input$0.45
Output$2.25
Cache$0.07
Qwen/Qwen3-VL-235B-A22B-Instruct
Input$0.20
Output$0.88
Cache$0.11
zai-org/GLM-4.7
Input$0.40
Output$1.75
Cache$0.08
deepseek-ai/DeepSeek-V3.2
Input$0.26
Output$0.38
Cache$0.13
nvidia/Nemotron-3-Nano-30B-A3B
Input$0.05
Output$0.20
Cache$0.025
Qwen/Qwen3-VL-30B-A3B-Instruct
Input$0.15
Output$0.60
Cache—
zai-org/GLM-4.6
Input$0.50
Output$2
Cache$0.10
Qwen/Qwen3-Next-80B-A3B-Instruct
Input$0.09
Output$1.10
Cache—
deepseek-ai/DeepSeek-V3.1
Input$0.25
Output$0.95
Cache$0.13
Qwen/Qwen3-235B-A22B-Instruct-2507
Input$0.09
Output$0.55
Cache—
openai/gpt-oss-20b
Input$0.03
Output$0.14
Cache—
openai/gpt-oss-120b
Input$0.037
Output$0.17
Cache—
nvidia/Llama-3.3-Nemotron-Super-49B-v1.5
Input$0.40
Output$0.40
Cache—
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
Input$0.30
Output$1
Cache$0.10
Qwen/Qwen3-32B
Input$0.08
Output$0.28
Cache—
deepseek-ai/DeepSeek-R1-0528
Input$0.50
Output$2.15
Cache$0.35
Qwen/Qwen3-30B-A3B
Input$0.12
Output$0.50
Cache—
meta-llama/Llama-3.3-70B-Instruct-Turbo
Input$0.10
Output$0.32
Cache—
meta-llama/Llama-Guard-4-12B
Input$0.18
Output$0.18
Cache—
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Input$0.20
Output$0.80
Cache—
meta-llama/Llama-4-Scout-17B-16E-Instruct
Input$0.10
Output$0.30
Cache—
deepseek-ai/DeepSeek-V3-0324
Input$0.24
Output$0.90
Cache$0.135
deepseek-ai/DeepSeek-V3
Input$0.32
Output$0.89
Cache—
google/gemma-3-12b-it
Input$0.05
Output$0.15
Cache—
google/gemma-3-27b-it
Input$0.08
Output$0.16
Cache—
google/gemma-3-4b-it
Input$0.05
Output$0.10
Cache—
mistralai/Mistral-Small-24B-Instruct-2501
Input$0.05
Output$0.08
Cache—
| Model | Status | Input | Output | Cache read | Retrieved |
|---|---|---|---|---|---|
| Qwen3.8 2.4T A95BQwen/Qwen3.8-2.4T-A95B | deprecatedNot a current offering | $2 | $6 | $0.20 | 2026-11-03 |
| Kimi K2.7 Codemoonshotai/Kimi-K2.7-Code | deprecatedNot a current offering | $0.68 | $3.40 | $0.136 | 2026-11-03 |
| GLM-5.2zai-org/GLM-5.2 | currentRecent price | $0.75 | $2.40 | $0.14 | 2026-11-03 |
| GLM-5.3zai-org/GLM-5.3 | currentRecent price | $0.90 | $4 | $0.20 | 2026-11-03 |
| V4 Flashdeepseek-ai/DeepSeek-V4-Flash-0731 | currentRecent price | $0.06 | $0.18 | $0.015 | 2026-11-03 |
| MiMo V2.6 FlashXiaomiMiMo/MiMo-V2.6-Flash | currentRecent price | $0.14 | $0.28 | $0.0028 | 2026-11-03 |
| MiMo V2.6 ProXiaomiMiMo/MiMo-V2.6-Pro | currentRecent price | $0.43 | $0.87 | $0.0036 | 2026-11-03 |
| GLM-5.3-Flashzai-org/GLM-5.3-Flash | currentRecent price | $0.15 | $0.50 | $0.03 | 2026-11-03 |
| Step 5 Previewstepfun-ai/Step-5-Preview | deprecatedNot a current offering | $1 | $2.70 | $0.10 | 2026-11-03 |
| Hy4 previewtencent/Hy4-preview | currentRecent price | $0.834 | $2.501 | $0.042 | 2026-11-03 |
| Qwen3.8 FlashQwen/Qwen3.8-Flash | currentRecent price | $0.113 | $0.382 | $0.0141 | 2026-11-03 |
| Qwen3.8 27BQwen/Qwen3.8-27B | currentRecent price | $0.20 | $2.50 | $0.05 | 2026-11-03 |
| ai/DeepSeek-V4-Prodeepseek-ai/DeepSeek-V4-Pro | currentRecent price | $1.30 | $2.60 | $0.10 | 2026-11-03 |
| Qwen3.8 MaxQwen/Qwen3.8-Max | currentRecent price | $1.65 | $4.951 | $0.206 | 2026-11-03 |
| Inkling Smallthinkingmachines/Inkling-Small | currentRecent price | $0.45 | $1.20 | $0.10 | 2026-11-03 |
| Kimi K3moonshotai/Kimi-K3 | currentRecent price | $2.85 | $14.25 | $0.285 | 2026-11-03 |
| Inklingthinkingmachines/Inkling | deprecatedNot a current offering | $0.95 | $4.05 | $0.16 | 2026-11-03 |
| Hy3tencent/Hy3 | deprecatedNot a current offering | $0.13 | $0.53 | $0.033 | 2026-11-03 |
| Claude Fable 5anthropic/claude-fable-5 | currentRecent price | $10 | $50 | — | 2026-11-03 |
| M3MiniMaxAI/MiniMax-M3 | currentRecent price | $0.28 | $1.10 | $0.056 | 2026-11-03 |
| Step 3.7 Flashstepfun-ai/Step-3.7-Flash | deprecatedNot a current offering | $0.20 | $1.15 | $0.04 | 2026-11-03 |
| Qwen3.7 MaxQwen/Qwen3.7-Max | currentRecent price | $2.50 | $7.50 | $0.50 | 2026-11-03 |
| Seed 2.0 MiniByteDance/Seed-2.0-mini | currentRecent price | $0.10 | $0.40 | $0.02 | 2026-11-03 |
| Nemotron 3 Nano Omni 30B A3B Reasoningnvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning | deprecatedNot a current offering | $0.20 | $0.80 | — | 2026-11-03 |
| MiMo-V2.5XiaomiMiMo/MiMo-V2.5 | deprecatedNot a current offering | $0.14 | $0.28 | $0.0028 | 2026-11-03 |
| MiMo-V2.5-ProXiaomiMiMo/MiMo-V2.5-Pro | deprecatedNot a current offering | $1 | $3 | $0.20 | 2026-11-03 |
| Qwen3.6 27BQwen/Qwen3.6-27B | currentRecent price | $0.32 | $3.20 | — | 2026-11-03 |
| Kimi K2.6moonshotai/Kimi-K2.6 | currentRecent price | $0.75 | $3.50 | $0.15 | 2026-11-03 |
| Qwen3.6 35B-A3BQwen/Qwen3.6-35B-A3B | currentRecent price | $0.10 | $0.95 | $0.10 | 2026-11-03 |
| glm-5.1zai-org/GLM-5.1 | deprecatedNot a current offering | $1.05 | $3.50 | $0.205 | 2026-11-03 |
| Gemma 4 31B ITgoogle/gemma-4-31B-it | currentRecent price | $0.20 | $0.40 | — | 2026-11-03 |
| Gemma 4 26B A4B ITgoogle/gemma-4-26B-A4B-it | currentRecent price | $0.07 | $0.34 | — | 2026-11-03 |
| Gemma 4 E4B ITgoogle/gemma-4-E4B-it | deprecatedNot a current offering | $0.02 | $0.10 | — | 2026-11-03 |
| M2.7MiniMaxAI/MiniMax-M2.7 | deprecatedNot a current offering | $0.25 | $1 | $0.05 | 2026-11-03 |
| Qwen3.5 9BQwen/Qwen3.5-9B | currentRecent price | $0.10 | $0.15 | — | 2026-11-03 |
| Qwen3.5 35B-A3BQwen/Qwen3.5-35B-A3B | currentRecent price | $0.14 | $1 | $0.05 | 2026-11-03 |
| Qwen3.5 122B-A10BQwen/Qwen3.5-122B-A10B | deprecatedNot a current offering | $0.29 | $2.40 | — | 2026-11-03 |
| Qwen3.5 27BQwen/Qwen3.5-27B | currentRecent price | $0.26 | $2.60 | — | 2026-11-03 |
| Qwen3.5 397B-A17BQwen/Qwen3.5-397B-A17B | currentRecent price | $0.45 | $3 | $0.22 | 2026-11-03 |
| Seed 2.0 CodeByteDance/Seed-2.0-code | currentRecent price | $0.50 | $3 | $0.10 | 2026-11-03 |
| Seed 2.0 ProByteDance/Seed-2.0-pro | currentRecent price | $0.50 | $3 | $0.10 | 2026-11-03 |
| MiniMaxAI/MiniMax-M2.5MiniMaxAI/MiniMax-M2.5 | deprecatedNot a current offering | $0.15 | $1.15 | $0.03 | 2026-11-03 |
| GLM-5zai-org/GLM-5 | deprecatedNot a current offering | $0.60 | $2.08 | $0.12 | 2026-11-03 |
| Qwen3 MaxQwen/Qwen3-Max | deprecatedNot a current offering | $1.20 | $6 | $0.24 | 2026-11-03 |
| GLM-4.7-Flashzai-org/GLM-4.7-Flash | deprecatedNot a current offering | $0.06 | $0.40 | $0.01 | 2026-11-03 |
| Kimi K2.5moonshotai/Kimi-K2.5 | deprecatedNot a current offering | $0.45 | $2.25 | $0.07 | 2026-11-03 |
| Qwen3 VL 235B A22B InstructQwen/Qwen3-VL-235B-A22B-Instruct | currentRecent price | $0.20 | $0.88 | $0.11 | 2026-11-03 |
| GLM-4.7zai-org/GLM-4.7 | currentRecent price | $0.40 | $1.75 | $0.08 | 2026-11-03 |
| ai/DeepSeek-V3.2deepseek-ai/DeepSeek-V3.2 | currentRecent price | $0.26 | $0.38 | $0.13 | 2026-11-03 |
| nemotron-3-nano-30b-a3bnvidia/Nemotron-3-Nano-30B-A3B | deprecatedNot a current offering | $0.05 | $0.20 | $0.025 | 2026-11-03 |
| Qwen3 VL 30B A3B InstructQwen/Qwen3-VL-30B-A3B-Instruct | currentRecent price | $0.15 | $0.60 | — | 2026-11-03 |
| GLM-4.6zai-org/GLM-4.6 | currentRecent price | $0.50 | $2 | $0.10 | 2026-11-03 |
| Qwen3-Next 80B-A3B InstructQwen/Qwen3-Next-80B-A3B-Instruct | currentRecent price | $0.09 | $1.10 | — | 2026-11-03 |
| V3.1 · mixed source IDsdeepseek-ai/DeepSeek-V3.1 | currentRecent price | $0.25 | $0.95 | $0.13 | 2026-11-03 |
| qwen3-235b-a22b-instruct-2507Qwen/Qwen3-235B-A22B-Instruct-2507 | currentRecent price | $0.09 | $0.55 | — | 2026-11-03 |
| GPT OSS 20Bopenai/gpt-oss-20b | currentRecent price | $0.03 | $0.14 | — | 2026-11-03 |
| GPT OSS 120Bopenai/gpt-oss-120b | currentRecent price | $0.037 | $0.17 | — | 2026-11-03 |
| Llama 3.3 Nemotron Super 49B v1.5nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 | deprecatedNot a current offering | $0.40 | $0.40 | — | 2026-11-03 |
| qwen3-coder-480b-a35b-instructQwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | currentRecent price | $0.30 | $1 | $0.10 | 2026-11-03 |
| Qwen3 32BQwen/Qwen3-32B | currentRecent price | $0.08 | $0.28 | — | 2026-11-03 |
| R1 0528deepseek-ai/DeepSeek-R1-0528 | currentRecent price | $0.50 | $2.15 | $0.35 | 2026-11-03 |
| Qwen3-30B-A3BQwen/Qwen3-30B-A3B | currentRecent price | $0.12 | $0.50 | — | 2026-11-03 |
| Llama-3.3-70B-Instructmeta-llama/Llama-3.3-70B-Instruct-Turbo | currentRecent price | $0.10 | $0.32 | — | 2026-11-03 |
| Llama Guard 4 12Bmeta-llama/Llama-Guard-4-12B | currentRecent price | $0.18 | $0.18 | — | 2026-11-03 |
| Llama 4 Maverick 17B 128E Instruct FP8meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | deprecatedNot a current offering | $0.20 | $0.80 | — | 2026-11-03 |
| Llama 4 Scout 17B Instructmeta-llama/Llama-4-Scout-17B-16E-Instruct | currentRecent price | $0.10 | $0.30 | — | 2026-11-03 |
| V3 0324 · mixed source IDsdeepseek-ai/DeepSeek-V3-0324 | deprecatedNot a current offering | $0.24 | $0.90 | $0.135 | 2026-11-03 |
| V3deepseek-ai/DeepSeek-V3 | currentRecent price | $0.32 | $0.89 | — | 2026-11-03 |
| Gemma 3 12B ITgoogle/gemma-3-12b-it | currentRecent price | $0.05 | $0.15 | — | 2026-11-03 |
| Gemma 3 27B ITgoogle/gemma-3-27b-it | currentRecent price | $0.08 | $0.16 | — | 2026-11-03 |
| Gemma 3 4B ITgoogle/gemma-3-4b-it | currentRecent price | $0.05 | $0.10 | — | 2026-11-03 |
| Mistral Small 3mistralai/Mistral-Small-24B-Instruct-2501 | currentRecent price | $0.05 | $0.08 | — | 2026-11-03 |
About these observations
The catalog records model and price observations; it does not measure this provider’s latency, uptime, data retention, or regional availability. Follow each row’s source to verify a quote before choosing a provider.