Models we route across

One endpoint. This is the set it routes to.

Every model Ainfera can route to, neutral across providers. The Intelligence column is the external Artificial Analysis Index (refreshed weekly) — a quality reference, not our routing score. Price is the upstream provider reference, never your per-call cost; cost, latency and availability are decided live, per call, inside your caps.

Intelligence, ranked

The whole field, by Artificial Analysis Intelligence Index.

The full routable catalog, ranked. Preferred-core models in accent; the coverage tier dimmed. A quality reference — not our routing score.

188+ models · refreshed daily

Claude Opus 4.773
OpenAI o4-pro72
Claude Opus 4.7 1M70
GPT-5.570
Gemini 3.1 Pro68
Grok 465
Claude Sonnet 4.763
Llama 4 405B (Together)62
Mistral Large 360
GPT-5.5 Mini58
Gemini 3.1 Flash57
Qwen3.7 Max (Novita)57
Grok 4 Mini55
MiniMax-M355
Mistral Medium 354
DeepSeek V4 Pro (Together)52
GLM 5.1 (Novita)51
GLM-550
MiniMax M2.7 (Novita)50
Qwen3.6 Plus50
Gemini 3.1 Flash Lite48
GLM-5-Turbo47
Deepseek V4 Flash46
Qwen3.6-27B46
Qwen3.5 397B A17B (DeepInfra)45
Qwen3.5 397B A17B (Together)45
Qwen3.6-35B-A3B44
GLM-5V-Turbo43
GLM-4.742
MiniMax M2.542
Qwen3.5-122B-A10B42
Qwen3.5-27B42
Qwen3-Max-Thinking40
Minimax M2.139
Qwen3.5-35B-A3B37
GPT-OSS 120B (Novita)33
Deepseek V3.232
Qwen3.5-9B32
Qwen3-Max31
GLM-4.630
GLM-4.7-Flash30
DeepSeek-V3.128
DeepSeek-V3.1-Terminus28
Qwen3 Coder Next28
GLM-4.526
Qwen3 235B A22B Instruct 250725
Qwen3 Coder 480B A35B Instruct25
GPT-OSS 20B (Novita)24
MiniMax M124
zai-org/glm-4.5-air23
DeepSeek-V3-032422
Qwen3-VL-235B-A22B-Instruct21
Qwen QwQ-32B20
Qwen3 Coder 30b A3B Instruct20
Qwen3-Next-80B-A3B-Instruct20
GLM 4.6V17
Qwen3-VL-32B-Instruct17
DeepSeek R1 Distill LLama 70B16
DeepSeek R1 Distill Qwen 14B16
DeepSeek-V316
Qwen2.5-72B-Instruct16
Qwen3-VL-30B-A3B-Instruct16
qwen/qwen3-vl-8b-instruct14
GLM 4.5V13
Qwen 2.5 Coder 32B Instruct13
Qwen2 72B Instruct12
Qwen3 Omni 30B A3B Instruct11
DeepSeek R1 Distill Qwen 1.5B9

Intelligence: Artificial Analysis · artificialanalysis.ai

Sort

247 of 247 models

Claude Opus 4.7

Lab: Anthropic
Host: Anthropic
Intelligence: 73
Context: 1M
Modalities: text · image
Ref. in/out · 1M: $15.00 / $75.00
Origin: US
Routable: active · cleared

text
tool_use
vision
code

OpenAI o4-pro

Lab: OpenAI
Host: OpenAI
Intelligence: 72
Context: 200K
Modalities: text
Ref. in/out · 1M: $60.00 / $240.00
Origin: US
Routable: active · cleared

text
reasoning
chain_of_thought

Claude Opus 4.7 1M

Lab: Anthropic
Host: Anthropic
Intelligence: 70
Context: 1M
Modalities: text · image
Ref. in/out · 1M: $30.00 / $150.00
Origin: US
Routable: active · cleared

text
tool_use
vision
long_context

GPT-5.5

Lab: OpenAI
Host: OpenAI
Intelligence: 70
Context: 200K
Modalities: text · image
Ref. in/out · 1M: $5.00 / $15.00
Origin: US
Routable: active · cleared

text
tool_use
vision
code

Gemini 3.1 Pro

Lab: Google
Host: Google
Intelligence: 68
Context: 1M
Modalities: text · image
Ref. in/out · 1M: $1.25 / $10.00
Origin: US
Routable: active · cleared

text
tool_use
vision
long_context

Grok 4

Lab: xAI
Host: xAI
Intelligence: 65
Context: 200K
Modalities: text
Ref. in/out · 1M: $5.00 / $15.00
Origin: US
Routable: active · cleared

text
tool_use

Claude Sonnet 4.7

Lab: Anthropic
Host: Anthropic
Intelligence: 63
Context: 200K
Modalities: text · image
Ref. in/out · 1M: $3.00 / $15.00
Origin: US
Routable: active · cleared

text
tool_use
vision

Llama 4 405B (Together)

Lab: Meta
Host: together
Intelligence: 62
Context: 128K
Modalities: text
Ref. in/out · 1M: $3.00 / $3.00
Origin: US
Routable: active · cleared

text
tool_use

Mistral Large 3

Lab: Mistral
Host: Mistral
Intelligence: 60
Context: 128K
Modalities: text
Ref. in/out · 1M: $2.00 / $6.00
Origin: FR
Routable: active · cleared

text
tool_use

GPT-5.5 Mini

Lab: OpenAI
Host: OpenAI
Intelligence: 58
Context: 200K
Modalities: text · image
Ref. in/out · 1M: $0.40 / $1.60
Origin: US
Routable: active · cleared

text
tool_use
vision
code

Gemini 3.1 Flash

Lab: Google
Host: Google
Intelligence: 57
Context: 1M
Modalities: text · image
Ref. in/out · 1M: $0.30 / $2.50
Origin: US
Routable: active · cleared

text
tool_use
vision
long_context

Qwen3.7 Max (Novita)

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 57
Context: 256K
Modalities: text
Ref. in/out · 1M: $1.25 / $3.75
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

Qwen3.7 Max (Together)

Lab: Alibaba (Qwen)
Host: together
Intelligence: 57
Context: 256K
Modalities: text
Ref. in/out · 1M: $1.25 / $3.75
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

MiniMax-M3

Lab: MiniMax
Host: novita
Intelligence: 55
Context: 1M
Modalities: text
Ref. in/out · 1M: $0.30 / $1.20
Origin: CN
Routable: active · cleared

text
tool_use

Grok 4 Mini

Lab: xAI
Host: xAI
Intelligence: 55
Context: 128K
Modalities: text
Ref. in/out · 1M: $0.50 / $2.00
Origin: US
Routable: active · cleared

text
tool_use

Mistral Medium 3

Lab: Mistral
Host: Mistral
Intelligence: 54
Context: 128K
Modalities: text
Ref. in/out · 1M: $1.00 / $3.00
Origin: FR
Routable: active · cleared

text
tool_use

DeepSeek V4 Pro (DeepInfra)

Lab: DeepSeek
Host: deepinfra
Intelligence: 52
Context: 1.0M
Modalities: text
Ref. in/out · 1M: $1.30 / $2.60
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

DeepSeek V4 Pro (Fireworks)

Lab: DeepSeek
Host: fireworks
Intelligence: 52
Context: 512K
Modalities: text
Ref. in/out · 1M: $1.74 / $3.48
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

DeepSeek V4 Pro (Novita)

Lab: DeepSeek
Host: novita
Intelligence: 52
Context: 512K
Modalities: text
Ref. in/out · 1M: $1.60 / $3.20
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

DeepSeek V4 Pro (Together)

Lab: DeepSeek
Host: together
Intelligence: 52
Context: 512K
Modalities: text
Ref. in/out · 1M: $1.74 / $3.48
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

GLM 5.1 (Novita)

Lab: Z.ai (GLM)
Host: novita
Intelligence: 51
Context: 203K
Modalities: text
Ref. in/out · 1M: $1.38 / $4.40
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

GLM 5.1 (Together)

Lab: Z.ai (GLM)
Host: together
Intelligence: 51
Context: 203K
Modalities: text
Ref. in/out · 1M: $1.40 / $4.40
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

GLM-5

Lab: Z.ai (GLM)
Host: novita
Intelligence: 50
Context: 203K
Modalities: text
Ref. in/out · 1M: $1.00 / $3.20
Origin: CN
Routable: active · cleared

text
tool_use

MiniMax M2.7 (Novita)

Lab: MiniMax
Host: novita
Intelligence: 50
Context: 197K
Modalities: text
Ref. in/out · 1M: $0.30 / $1.20
Origin: CN
Routable: active · cleared

text
tool_use

MiniMax M2.7 (Together)

Lab: MiniMax
Host: together
Intelligence: 50
Context: 197K
Modalities: text
Ref. in/out · 1M: $0.30 / $1.20
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3.6 Plus

Lab: Alibaba (Qwen)
Host: together
Intelligence: 50
Context: 1M
Modalities: text
Ref. in/out · 1M: $0.50 / $3.00
Origin: CN
Routable: active · cleared

text

Gemini 3.1 Flash Lite

Lab: Google
Host: Google
Intelligence: 48
Context: 1M
Modalities: text
Ref. in/out · 1M: $0.10 / $0.40
Origin: US
Routable: active · cleared

text
tool_use
long_context

GLM-5-Turbo

Lab: Z.ai (GLM)
Host: novita
Intelligence: 47
Context: 203K
Modalities: text
Ref. in/out · 1M: $1.20 / $4.00
Origin: CN
Routable: active · cleared

text
tool_use

DeepSeek-V4-Flash

Lab: DeepSeek
Host: deepinfra
Intelligence: 46
Context: 1.0M
Modalities: text
Ref. in/out · 1M: $0.10 / $0.20
Origin: CN
Routable: active · cleared

text

Qwen3.6-27B

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 46
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.32 / $3.20
Origin: CN
Routable: active · cleared

text

Deepseek V4 Flash

Lab: DeepSeek
Host: novita
Intelligence: 46
Context: 1.0M
Modalities: text
Ref. in/out · 1M: $0.14 / $0.28
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3.6-27B

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 46
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.60 / $3.60
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3.5 397B A17B (DeepInfra)

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 45
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.49 / $3.60
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

Qwen3.5 397B A17B (Novita)

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 45
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.60 / $3.60
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

Qwen3.5 397B A17B (Together)

Lab: Alibaba (Qwen)
Host: together
Intelligence: 45
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.60 / $3.60
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

Qwen3.6-35B-A3B

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 44
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.15 / $0.95
Origin: CN
Routable: active · cleared

text

Qwen3.6-35B-A3B

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 44
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.25 / $1.49
Origin: CN
Routable: active · cleared

text
tool_use

GLM-5V-Turbo

Lab: Z.ai (GLM)
Host: novita
Intelligence: 43
Context: 205K
Modalities: text
Ref. in/out · 1M: $1.20 / $4.00
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3.5-27B

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 42
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.26 / $2.60
Origin: CN
Routable: active · cleared

text

GLM-4.7

Lab: Z.ai (GLM)
Host: novita
Intelligence: 42
Context: 205K
Modalities: text
Ref. in/out · 1M: $0.60 / $2.20
Origin: CN
Routable: active · cleared

text
tool_use

MiniMax M2.5

Lab: MiniMax
Host: novita
Intelligence: 42
Context: 205K
Modalities: text
Ref. in/out · 1M: $0.30 / $1.20
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3.5-122B-A10B

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 42
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.40 / $3.20
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3.5-27B

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 42
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.30 / $2.40
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3-Max-Thinking

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 40
Context: 256K
Modalities: text
Ref. in/out · 1M: $1.20 / $6.00
Origin: CN
Routable: active · cleared

text

Minimax M2.1

Lab: MiniMax
Host: novita
Intelligence: 39
Context: 205K
Modalities: text
Ref. in/out · 1M: $0.30 / $1.20
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3.5-35B-A3B

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 37
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.14 / $1.00
Origin: CN
Routable: active · cleared

text

Qwen3.5-35B-A3B

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 37
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.25 / $2.00
Origin: CN
Routable: active · cleared

text
tool_use

GPT-OSS 120B (Fireworks)

Lab: OpenAI
Host: fireworks
Intelligence: 33
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.15 / $0.60
Origin: US
Routable: active · cleared

text
tool_use
code

GPT-OSS 120B (Groq)

Lab: OpenAI
Host: groq
Intelligence: 33
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.15 / $0.60
Origin: US
Routable: active · cleared

text
tool_use
code

GPT-OSS 120B (Novita)

Lab: OpenAI
Host: novita
Intelligence: 33
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.05 / $0.25
Origin: US
Routable: active · cleared

text
tool_use
code

GPT-OSS 120B (Together)

Lab: OpenAI
Host: together
Intelligence: 33
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.15 / $0.60
Origin: US
Routable: active · cleared

text
tool_use
code

Qwen3.5-9B

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 32
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.10 / $0.15
Origin: CN
Routable: active · cleared

text

Deepseek V3.2

Lab: DeepSeek
Host: novita
Intelligence: 32
Context: 164K
Modalities: text
Ref. in/out · 1M: $0.27 / $0.40
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3.5 9B FP8

Lab: Alibaba (Qwen)
Host: together
Intelligence: 32
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.17 / $0.25
Origin: CN
Routable: active · cleared

text

Qwen3-Max

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 31
Context: 256K
Modalities: text
Ref. in/out · 1M: $1.20 / $6.00
Origin: CN
Routable: active · cleared

text

Qwen3 Max

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 31
Context: 262K
Modalities: text
Ref. in/out · 1M: $2.11 / $8.45
Origin: CN
Routable: active · cleared

text
tool_use

GLM-4.6

Lab: Z.ai (GLM)
Host: deepinfra
Intelligence: 30
Context: 203K
Modalities: text
Ref. in/out · 1M: $0.43 / $1.74
Origin: CN
Routable: active · cleared

text

GLM-4.7-Flash

Lab: Z.ai (GLM)
Host: deepinfra
Intelligence: 30
Context: 203K
Modalities: text
Ref. in/out · 1M: $0.06 / $0.40
Origin: CN
Routable: active · cleared

text

GLM-4.7-Flash

Lab: Z.ai (GLM)
Host: novita
Intelligence: 30
Context: 200K
Modalities: text
Ref. in/out · 1M: $0.07 / $0.40
Origin: CN
Routable: active · cleared

text
tool_use

GLM 4.6 Fp8

Lab: Z.ai (GLM)
Host: together
Intelligence: 30
Context: 203K
Modalities: text
Ref. in/out · 1M: $0.60 / $2.20
Origin: CN
Routable: active · cleared

text

DeepSeek-V3.1

Lab: DeepSeek
Host: deepinfra
Intelligence: 28
Context: 164K
Modalities: text
Ref. in/out · 1M: $0.21 / $0.79
Origin: CN
Routable: active · cleared

text

DeepSeek-V3.1-Terminus

Lab: DeepSeek
Host: deepinfra
Intelligence: 28
Context: 164K
Modalities: text
Ref. in/out · 1M: $0.27 / $0.95
Origin: CN
Routable: active · cleared

text

DeepSeek V3.1

Lab: DeepSeek
Host: novita
Intelligence: 28
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.27 / $1.00
Origin: CN
Routable: active · cleared

text
tool_use

Deepseek V3.1 Terminus

Lab: DeepSeek
Host: novita
Intelligence: 28
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.27 / $1.00
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3 Coder Next

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 28
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.20 / $1.50
Origin: CN
Routable: active · cleared

text
tool_use
code

Deepseek V3.1 NVFP4

Lab: DeepSeek
Host: together
Intelligence: 28
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.60 / $1.70
Origin: CN
Routable: active · cleared

text

GLM-4.5

Lab: Z.ai (GLM)
Host: novita
Intelligence: 26
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.60 / $2.20
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3 235B A22B Instruct 2507

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 25
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.09 / $0.58
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3 Coder 480B A35B Instruct

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 25
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.38 / $1.55
Origin: CN
Routable: active · cleared

text
tool_use
code

GPT-OSS 20B (Groq)

Lab: OpenAI
Host: groq
Intelligence: 24
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.07 / $0.30
Origin: US
Routable: active · cleared

text

GPT-OSS 20B (Novita)

Lab: OpenAI
Host: novita
Intelligence: 24
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.04 / $0.15
Origin: US
Routable: active · cleared

text

MiniMax M1

Lab: MiniMax
Host: novita
Intelligence: 24
Context: 1M
Modalities: text
Ref. in/out · 1M: $0.55 / $2.20
Origin: CN
Routable: active · cleared

text
tool_use

GPT-OSS 20B (Together)

Lab: OpenAI
Host: together
Intelligence: 24
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.05 / $0.20
Origin: US
Routable: active · cleared

text

zai-org/glm-4.5-air

Lab: Z.ai (GLM)
Host: novita
Intelligence: 23
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.13 / $0.85
Origin: CN
Routable: active · cleared

text
tool_use

DeepSeek-V3-0324

Lab: DeepSeek
Host: deepinfra
Intelligence: 22
Context: 164K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.77
Origin: CN
Routable: active · cleared

text

DeepSeek V3 0324

Lab: DeepSeek
Host: novita
Intelligence: 22
Context: 164K
Modalities: text
Ref. in/out · 1M: $0.27 / $1.12
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3-VL-235B-A22B-Instruct

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 21
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.88
Origin: CN
Routable: active · cleared

text

Qwen3 VL 235B A22B Instruct

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 21
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.30 / $1.50
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3-Next-80B-A3B-Instruct

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 20
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.09 / $1.10
Origin: CN
Routable: active · cleared

text

Qwen3 Coder 30b A3B Instruct

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 20
Context: 160K
Modalities: text
Ref. in/out · 1M: $0.07 / $0.27
Origin: CN
Routable: active · cleared

text
tool_use
code

Qwen3 Next 80B A3B Instruct

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 20
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.15 / $1.50
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3 Next 80B A3b Instruct

Lab: Alibaba (Qwen)
Host: together
Intelligence: 20
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.15 / $1.50
Origin: CN
Routable: active · cleared

text

Qwen QwQ-32B

Lab: Alibaba (Qwen)
Host: together
Intelligence: 20
Context: 131K
Modalities: text
Ref. in/out · 1M: $1.20 / $1.20
Origin: CN
Routable: active · cleared

text

GLM 4.6V

Lab: Z.ai (GLM)
Host: novita
Intelligence: 17
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.30 / $0.90
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3-VL-32B-Instruct

Lab: Alibaba (Qwen)
Host: together
Intelligence: 17
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.50 / $1.50
Origin: CN
Routable: active · cleared

text

DeepSeek-V3

Lab: DeepSeek
Host: deepinfra
Intelligence: 16
Context: 164K
Modalities: text
Ref. in/out · 1M: $0.32 / $0.89
Origin: CN
Routable: active · cleared

text

Qwen2.5-72B-Instruct

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 16
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.36 / $0.40
Origin: CN
Routable: active · cleared

text

Qwen3-VL-30B-A3B-Instruct

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: 16
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.15 / $0.60
Origin: CN
Routable: active · cleared

text

DeepSeek R1 Distill LLama 70B

Lab: DeepSeek
Host: novita
Intelligence: 16
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.80 / $0.80
Origin: CN
Routable: active · cleared

text

qwen/qwen3-vl-30b-a3b-instruct

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 16
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.70
Origin: CN
Routable: active · cleared

text
tool_use

DeepSeek R1 Distill Llama 70B

Lab: DeepSeek
Host: together
Intelligence: 16
Context: 131K
Modalities: text
Ref. in/out · 1M: $2.00 / $2.00
Origin: CN
Routable: active · cleared

text

DeepSeek R1 Distill Qwen 14B

Lab: DeepSeek
Host: together
Intelligence: 16
Context: 131K
Modalities: text
Ref. in/out · 1M: $1.60 / $1.60
Origin: CN
Routable: active · cleared

text

Qwen2.5 72B Instruct

Lab: Alibaba (Qwen)
Host: together
Intelligence: 16
Context: 33K
Modalities: text
Ref. in/out · 1M: $1.20 / $1.20
Origin: CN
Routable: active · cleared

text

qwen/qwen3-vl-8b-instruct

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 14
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.08 / $0.50
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3-VL-8B-Instruct

Lab: Alibaba (Qwen)
Host: together
Intelligence: 14
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.18 / $0.68
Origin: CN
Routable: active · cleared

text

GLM 4.5V

Lab: Z.ai (GLM)
Host: novita
Intelligence: 13
Context: 66K
Modalities: text
Ref. in/out · 1M: $0.60 / $1.80
Origin: CN
Routable: active · cleared

text
tool_use

Qwen 2.5 Coder 32B Instruct

Lab: Alibaba (Qwen)
Host: together
Intelligence: 13
Context: 16K
Modalities: text
Ref. in/out · 1M: $0.80 / $0.80
Origin: CN
Routable: active · cleared

text
code

Qwen2 72B Instruct

Lab: Alibaba (Qwen)
Host: together
Intelligence: 12
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.90 / $0.90
Origin: CN
Routable: active · cleared

text

Qwen3 Omni 30B A3B Instruct

Lab: Alibaba (Qwen)
Host: novita
Intelligence: 11
Context: 66K
Modalities: text
Ref. in/out · 1M: $0.25 / $0.97
Origin: CN
Routable: active · cleared

text
tool_use

DeepSeek R1 Distill Qwen 1.5B

Lab: DeepSeek
Host: together
Intelligence: 9
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.18 / $0.18
Origin: CN
Routable: active · cleared

text

Ainfera Inference (auto-routed)

Lab: ainfera
Host: ainfera
Intelligence: —
Context: 0
Modalities: text
Ref. in/out · 1M: $0.00 / $0.00
Origin: —
Routable: active

text

AutoGLM-Phone-9B-Multilingual

Lab: Z.ai (GLM)
Host: novita
Intelligence: —
Context: 66K
Modalities: text
Ref. in/out · 1M: $0.04 / $0.14
Origin: CN
Routable: active · cleared

text

Claude Haiku 4.5

Lab: Anthropic
Host: Anthropic
Intelligence: —
Context: 200K
Modalities: text
Ref. in/out · 1M: $1.00 / $5.00
Origin: US
Routable: active · cleared

text
code

CoBuddy

Lab: Baidu (ERNIE)
Host: novita
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.28 / $1.13
Origin: CN
Routable: active · cleared

text
tool_use

Cogito v2.1 671B

Lab: DeepCogito
Host: together
Intelligence: —
Context: 164K
Modalities: text
Ref. in/out · 1M: $1.25 / $1.25
Origin: US
Routable: active · cleared

text

Deepseek Coder 33B Instruct

Lab: DeepSeek
Host: together
Intelligence: —
Context: 16K
Modalities: text
Ref. in/out · 1M: $0.80 / $0.80
Origin: CN
Routable: active · cleared

text
code

Deepseek Prover V2 671B

Lab: DeepSeek
Host: novita
Intelligence: —
Context: 160K
Modalities: text
Ref. in/out · 1M: $0.70 / $2.50
Origin: CN
Routable: active · cleared

text

DeepSeek R1 (Turbo)

Lab: DeepSeek
Host: novita
Intelligence: —
Context: 64K
Modalities: text
Ref. in/out · 1M: $0.70 / $2.50
Origin: CN
Routable: active · cleared

text
tool_use

DeepSeek R1 0528

Lab: DeepSeek
Host: novita
Intelligence: —
Context: 164K
Modalities: text
Ref. in/out · 1M: $0.70 / $2.50
Origin: CN
Routable: active · cleared

text
tool_use

DeepSeek R1 0528 NVFP4

Lab: DeepSeek
Host: together
Intelligence: —
Context: 164K
Modalities: text
Ref. in/out · 1M: $3.00 / $7.00
Origin: CN
Routable: active · cleared

text

DeepSeek V3

Lab: DeepSeek
Host: novita
Intelligence: —
Context: 64K
Modalities: text
Ref. in/out · 1M: $0.89 / $0.89
Origin: CN
Routable: active · cleared

text
tool_use

DeepSeek V3 (Turbo)

Lab: DeepSeek
Host: novita
Intelligence: —
Context: 64K
Modalities: text
Ref. in/out · 1M: $0.40 / $1.30
Origin: CN
Routable: active · cleared

text
tool_use

Deepseek V3.2 Exp

Lab: DeepSeek
Host: novita
Intelligence: —
Context: 164K
Modalities: text
Ref. in/out · 1M: $0.27 / $0.41
Origin: CN
Routable: active · cleared

text
tool_use

DeepSeek-OCR 2

Lab: DeepSeek
Host: novita
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.03 / $0.03
Origin: CN
Routable: active · cleared

text

DeepSeek-R1-0528

Lab: DeepSeek
Host: deepinfra
Intelligence: —
Context: 164K
Modalities: text
Ref. in/out · 1M: $0.50 / $2.15
Origin: CN
Routable: active · cleared

text

ERNIE 4.5 21B A3B

Lab: Baidu (ERNIE)
Host: novita
Intelligence: —
Context: 120K
Modalities: text
Ref. in/out · 1M: $0.07 / $0.28
Origin: CN
Routable: active · cleared

text
tool_use

ERNIE 4.5 VL 28B A3B

Lab: Baidu (ERNIE)
Host: novita
Intelligence: —
Context: 30K
Modalities: text
Ref. in/out · 1M: $0.14 / $0.56
Origin: CN
Routable: active · cleared

text
tool_use

ERNIE 4.5 VL 424B A47B

Lab: Baidu (ERNIE)
Host: novita
Intelligence: —
Context: 123K
Modalities: text
Ref. in/out · 1M: $0.42 / $1.25
Origin: CN
Routable: active · cleared

text

EssentialAI Rnj-1 Instruct

Lab: Essential AI
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.15 / $0.15
Origin: US
Routable: active · cleared

text

Gemma 3 27B

Lab: Google
Host: novita
Intelligence: —
Context: 98K
Modalities: text
Ref. in/out · 1M: $0.12 / $0.20
Origin: US
Routable: active · cleared

text

Gemma 3N E4B Instruct

Lab: Google
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.06 / $0.12
Origin: US
Routable: active · cleared

text

Gemma 4 26B A4B

Lab: Google
Host: novita
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.13 / $0.40
Origin: US
Routable: active · cleared

text
tool_use

Gemma 4 31B

Lab: Google
Host: novita
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.14 / $0.40
Origin: US
Routable: active · cleared

text
tool_use

Gemma 4 31B-it FP8

Lab: Google
Host: together
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.39 / $0.97
Origin: US
Routable: active · cleared

text

Gemma-2 Instruct (27B)

Lab: Google
Host: together
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.80 / $0.80
Origin: US
Routable: active · cleared

text

gemma-3-12b-it

Lab: Google
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.05 / $0.15
Origin: US
Routable: active · cleared

text

gemma-3-27b-it

Lab: Google
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.08 / $0.16
Origin: US
Routable: active · cleared

text

gemma-3-4b-it

Lab: Google
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.05 / $0.10
Origin: US
Routable: active · cleared

text

gemma-4-26B-A4B-it

Lab: Google
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.07 / $0.34
Origin: US
Routable: active · cleared

text

gemma-4-31B-it

Lab: Google
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.13 / $0.38
Origin: US
Routable: active · cleared

text

gemma-4-31B-it-turbo

Lab: Google
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.12 / $0.37
Origin: US
Routable: active · cleared

text

Glm 4.5 Air Fp8

Lab: Z.ai (GLM)
Host: together
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.20 / $1.10
Origin: CN
Routable: active · cleared

text

GLM 5.1 (Fireworks)

Lab: Z.ai (GLM)
Host: fireworks
Intelligence: —
Context: 203K
Modalities: text
Ref. in/out · 1M: $1.40 / $4.40
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

GLM-4-32B-0414

Lab: Z.ai (GLM)
Host: novita
Intelligence: —
Context: 32K
Modalities: text
Ref. in/out · 1M: $0.55 / $1.66
Origin: CN
Routable: active · cleared

text
tool_use

GLM-4.7

Lab: Z.ai (GLM)
Host: novita
Intelligence: —
Context: 205K
Modalities: text
Ref. in/out · 1M: $0.60 / $2.20
Origin: CN
Routable: active · cleared

text
tool_use

GLM-OCR

Lab: Z.ai (GLM)
Host: novita
Intelligence: —
Context: 32K
Modalities: text
Ref. in/out · 1M: $0.03 / $0.03
Origin: CN
Routable: active · cleared

text

gpt-oss-120b-Turbo

Lab: OpenAI
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.15 / $0.60
Origin: US
Routable: active · cleared

text

Hermes-3-Llama-3.1-405B

Lab: Nous Research
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $1.00 / $1.00
Origin: US
Routable: active · cleared

text

Hermes-3-Llama-3.1-70B

Lab: Nous Research
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.70 / $0.70
Origin: US
Routable: active · cleared

text

Kat Coder Pro

Lab: Kwaipilot (Kuaishou)
Host: novita
Intelligence: —
Context: 256K
Modalities: text
Ref. in/out · 1M: $0.30 / $1.20
Origin: CN
Routable: active · cleared

text
tool_use
code

Kimi K2 0905

Lab: Moonshot AI
Host: novita
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.60 / $2.50
Origin: CN
Routable: active · cleared

text
tool_use

Kimi K2 Instruct

Lab: Moonshot AI
Host: novita
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.57 / $2.30
Origin: CN
Routable: active · cleared

text
tool_use

Kimi K2 Thinking

Lab: Moonshot AI
Host: novita
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.60 / $2.50
Origin: CN
Routable: active · cleared

text
tool_use

Kimi K2.5

Lab: Moonshot AI
Host: novita
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.60 / $3.00
Origin: CN
Routable: active · cleared

text
tool_use

Kimi K2.5 FP4

Lab: Moonshot AI
Host: together
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.50 / $2.80
Origin: CN
Routable: active · cleared

text

Kimi K2.6 (DeepInfra)

Lab: Moonshot AI
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.75 / $3.50
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

Kimi K2.6 (Fireworks)

Lab: Moonshot AI
Host: fireworks
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.95 / $4.00
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

Kimi K2.6 (Novita)

Lab: Moonshot AI
Host: novita
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.80 / $3.40
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

Kimi K2.6 (Together)

Lab: Moonshot AI
Host: together
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $1.20 / $4.50
Origin: CN
Routable: active · cleared

text
tool_use
code
long_context

Kimi K2.7 Code

Lab: Moonshot AI
Host: novita
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.95 / $4.00
Origin: CN
Routable: active · cleared

text
tool_use
code

Kimi K2.7 Code

Lab: Moonshot AI
Host: together
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.95 / $4.00
Origin: CN
Routable: active · cleared

text
code

Kimi-K2.5

Lab: Moonshot AI
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.45 / $2.25
Origin: CN
Routable: active · cleared

text

L3 8B Stheno V3.2

Lab: Sao10K
Host: novita
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.05 / $0.05
Origin: —
Routable: active · cleared

text
tool_use

L3-8B-Lunaris-v1-Turbo

Lab: Sao10K
Host: deepinfra
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.04 / $0.05
Origin: —
Routable: active · cleared

text

L3.1-70B-Euryale-v2.2

Lab: Sao10K
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.85 / $0.85
Origin: —
Routable: active · cleared

text

L31 70B Euryale V2.2

Lab: Sao10K
Host: novita
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $1.48 / $1.48
Origin: —
Routable: active · cleared

text
tool_use

LFM2-24B-A2B

Lab: Liquid AI
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.03 / $0.12
Origin: US
Routable: active · cleared

text

Ling-2.6-1T

Lab: inclusionAI (Ling)
Host: novita
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.30 / $2.50
Origin: CN
Routable: active · cleared

text
tool_use

Ling-2.6-flash

Lab: inclusionAI (Ling)
Host: novita
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.10 / $0.30
Origin: CN
Routable: active · cleared

text
tool_use

Llama 3 8B Instruct

Lab: Meta
Host: novita
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.04 / $0.04
Origin: US
Routable: active · cleared

text

Llama 3.1 8B Instruct

Lab: Meta
Host: novita
Intelligence: —
Context: 16K
Modalities: text
Ref. in/out · 1M: $0.02 / $0.05
Origin: US
Routable: active · cleared

text

Llama 3.1 Nemotron 70B Instruct HF

Lab: NVIDIA
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.88 / $0.88
Origin: US
Routable: active · cleared

text

Llama 3.3 70B (DeepInfra)

Lab: Meta
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.10 / $0.32
Origin: US
Routable: active · cleared

text
tool_use

Llama 3.3 70B (Groq)

Lab: Meta
Host: groq
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.59 / $0.79
Origin: US
Routable: active · cleared

text
tool_use

Llama 3.3 70B (Novita)

Lab: Meta
Host: novita
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.14 / $0.40
Origin: US
Routable: active · cleared

text
tool_use

Llama 3.3 70B (Together)

Lab: Meta
Host: together
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $1.04 / $1.04
Origin: US
Routable: active · cleared

text
tool_use

Llama 4 Maverick (DeepInfra)

Lab: Meta
Host: deepinfra
Intelligence: —
Context: 1.0M
Modalities: text · image
Ref. in/out · 1M: $0.15 / $0.60
Origin: US
Routable: active · cleared

text
tool_use
vision
long_context

Llama 4 Maverick Instruct

Lab: Meta
Host: novita
Intelligence: —
Context: 1.0M
Modalities: text
Ref. in/out · 1M: $0.27 / $0.85
Origin: US
Routable: active · cleared

text

Llama 4 Scout Instruct

Lab: Meta
Host: novita
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.18 / $0.59
Origin: US
Routable: active · cleared

text

Llama 4 Scout Instruct (17Bx16E)

Lab: Meta
Host: together
Intelligence: —
Context: 1.0M
Modalities: text
Ref. in/out · 1M: $0.18 / $0.59
Origin: US
Routable: active · cleared

text

Llama-3.2-11B-Vision-Instruct

Lab: Meta
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.34 / $0.34
Origin: US
Routable: active · cleared

text

Llama-3.3-Nemotron-Super-49B-v1.5

Lab: NVIDIA
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.40 / $0.40
Origin: US
Routable: active · cleared

text

Llama-4-Scout-17B-16E-Instruct

Lab: Meta
Host: deepinfra
Intelligence: —
Context: 328K
Modalities: text
Ref. in/out · 1M: $0.10 / $0.30
Origin: US
Routable: active · cleared

text

Llama-Guard-4-12B

Lab: Meta
Host: deepinfra
Intelligence: —
Context: 164K
Modalities: text
Ref. in/out · 1M: $0.18 / $0.18
Origin: US
Routable: active · cleared

text

Llama3 70B Instruct

Lab: Meta
Host: novita
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.51 / $0.74
Origin: US
Routable: active · cleared

text

Meta Llama 3 70B Instruct Turbo

Lab: Meta
Host: together
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.88 / $0.88
Origin: US
Routable: active · cleared

text

Meta Llama 3 8B Instruct

Lab: Meta
Host: together
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.20
Origin: US
Routable: active · cleared

text

Meta Llama 3 8B Instruct Lite

Lab: Meta
Host: together
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.14 / $0.14
Origin: US
Routable: active · cleared

text

Meta Llama 3 8B Instruct Reference

Lab: Meta
Host: together
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.20
Origin: US
Routable: active · cleared

text

Meta Llama 3.1 405B Instruct

Lab: Meta
Host: together
Intelligence: —
Context: 4K
Modalities: text
Ref. in/out · 1M: $3.50 / $3.50
Origin: US
Routable: active · cleared

text

Meta Llama 3.1 70B Instruct Turbo

Lab: Meta
Host: together
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.88 / $0.88
Origin: US
Routable: active · cleared

text

Meta Llama 3.1 8B Instruct Turbo

Lab: Meta
Host: together
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.18 / $0.18
Origin: US
Routable: active · cleared

text

Meta Llama 3.2 1B Instruct

Lab: Meta
Host: together
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.06 / $0.06
Origin: US
Routable: active · cleared

text

Meta Llama 3.2 3B Instruct

Lab: Meta
Host: together
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.06 / $0.06
Origin: US
Routable: active · cleared

text

Meta-Llama-3.1-70B-Instruct-Turbo

Lab: Meta
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.40 / $0.40
Origin: US
Routable: active · cleared

text

Meta-Llama-3.1-8B-Instruct

Lab: Meta
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.02 / $0.05
Origin: US
Routable: active · cleared

text

Meta-Llama-3.1-8B-Instruct-Turbo

Lab: Meta
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.02 / $0.03
Origin: US
Routable: active · cleared

text

MiMo-V2.5

Lab: Xiaomi (MiMo)
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.40 / $2.00
Origin: CN
Routable: active · cleared

text

MiMo-V2.5-Pro

Lab: Xiaomi (MiMo)
Host: deepinfra
Intelligence: —
Context: 1.0M
Modalities: text
Ref. in/out · 1M: $1.00 / $3.00
Origin: CN
Routable: active · cleared

text

MiniMax M2.5-highspeed

Lab: MiniMax
Host: novita
Intelligence: —
Context: 205K
Modalities: text
Ref. in/out · 1M: $0.60 / $2.40
Origin: CN
Routable: active · cleared

text
tool_use

MiniMax M2.7-highspeed

Lab: MiniMax
Host: novita
Intelligence: —
Context: 205K
Modalities: text
Ref. in/out · 1M: $0.60 / $2.40
Origin: CN
Routable: active · cleared

text
tool_use

MiniMax M3

Lab: MiniMax
Host: together
Intelligence: —
Context: 524K
Modalities: text
Ref. in/out · 1M: $0.30 / $1.20
Origin: CN
Routable: active · cleared

text

Ministral 3 14B Instruct 2512

Lab: Mistral
Host: together
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.20
Origin: FR
Routable: active · cleared

text

Mistral (7B) Instruct v0.1

Lab: Mistral
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.20
Origin: FR
Routable: active · cleared

text

Mistral (7B) Instruct v0.3

Lab: Mistral
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.20
Origin: FR
Routable: active · cleared

text

Mistral Nemo

Lab: Mistral
Host: novita
Intelligence: —
Context: 60K
Modalities: text
Ref. in/out · 1M: $0.04 / $0.17
Origin: FR
Routable: active · cleared

text

Mistral Small (24B) Instruct 25.01

Lab: Mistral
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.10 / $0.30
Origin: FR
Routable: active · cleared

text

Mistral-Nemo-Instruct-2407

Lab: Mistral
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.02 / $0.04
Origin: FR
Routable: active · cleared

text

Mistral-Small-24B-Instruct-2501

Lab: Mistral
Host: deepinfra
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.05 / $0.08
Origin: FR
Routable: active · cleared

text

Mistral-Small-3.2-24B-Instruct-2506

Lab: Mistral
Host: deepinfra
Intelligence: —
Context: 128K
Modalities: text
Ref. in/out · 1M: $0.07 / $0.20
Origin: FR
Routable: active · cleared

text

Mixtral-8x7B Instruct v0.1

Lab: Mistral
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.60 / $0.60
Origin: FR
Routable: active · cleared

text

MythoMax-L2-13b

Lab: Gryphe
Host: deepinfra
Intelligence: —
Context: 4K
Modalities: text
Ref. in/out · 1M: $0.40 / $0.40
Origin: —
Routable: active · cleared

text

Nemotron 3 Nano 30B A3B

Lab: NVIDIA
Host: novita
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.05 / $0.20
Origin: US
Routable: active · cleared

text
tool_use

Nemotron-3-Nano-30B-A3B

Lab: NVIDIA
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.05 / $0.20
Origin: US
Routable: active · cleared

text

Nemotron-3-Nano-Omni-30B-A3B-Reasoning

Lab: NVIDIA
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.80
Origin: US
Routable: active · cleared

text

Nemotron-Content-Safety-3.5

Lab: NVIDIA
Host: deepinfra
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.20
Origin: US
Routable: active · cleared

text

Nous Hermes 2 Mixtral 8X7B Dpo

Lab: Nous Research
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.60 / $0.60
Origin: US
Routable: active · cleared

text

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4

Lab: NVIDIA
Host: together
Intelligence: —
Context: 512K
Modalities: text
Ref. in/out · 1M: $0.60 / $3.60
Origin: US
Routable: active · cleared

text

Nvidia Nemotron Nano 9B V2

Lab: NVIDIA
Host: together
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.06 / $0.25
Origin: US
Routable: active · cleared

text

NVIDIA-Nemotron-3-Super-120B-A12B

Lab: NVIDIA
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.10 / $0.50
Origin: US
Routable: active · cleared

text

NVIDIA-Nemotron-3-Ultra-550B-A55B

Lab: NVIDIA
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.50 / $2.50
Origin: US
Routable: active · cleared

text

NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

Lab: NVIDIA
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $1.00 / $5.00
Origin: US
Routable: active · cleared

text

phi-4

Lab: Microsoft (Phi)
Host: deepinfra
Intelligence: —
Context: 16K
Modalities: text
Ref. in/out · 1M: $0.07 / $0.14
Origin: US
Routable: active · cleared

text

Qwen 2 Instruct (1.5B)

Lab: Alibaba (Qwen)
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.02 / $0.02
Origin: CN
Routable: active · cleared

text

Qwen 2.5 14B Instruct

Lab: Alibaba (Qwen)
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.80 / $0.80
Origin: CN
Routable: active · cleared

text

Qwen 2.5 72B Instruct

Lab: Alibaba (Qwen)
Host: novita
Intelligence: —
Context: 32K
Modalities: text
Ref. in/out · 1M: $0.38 / $0.40
Origin: CN
Routable: active · cleared

text
tool_use

Qwen MT Plus

Lab: Alibaba (Qwen)
Host: novita
Intelligence: —
Context: 16K
Modalities: text
Ref. in/out · 1M: $0.25 / $0.75
Origin: CN
Routable: active · cleared

text

qwen/qwen3-vl-30b-a3b-thinking

Lab: Alibaba (Qwen)
Host: novita
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.20 / $1.00
Origin: CN
Routable: active · cleared

text
tool_use

Qwen2-VL (72B) Instruct

Lab: Alibaba (Qwen)
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $1.20 / $1.20
Origin: CN
Routable: active · cleared

text

Qwen2.5 72B Instruct Turbo

Lab: Alibaba (Qwen)
Host: together
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $1.20 / $1.20
Origin: CN
Routable: active · cleared

text

Qwen2.5 7B Instruct Turbo

Lab: Alibaba (Qwen)
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $0.30 / $0.30
Origin: CN
Routable: active · cleared

text

Qwen2.5-VL (72B) Instruct

Lab: Alibaba (Qwen)
Host: together
Intelligence: —
Context: 33K
Modalities: text
Ref. in/out · 1M: $1.95 / $8.00
Origin: CN
Routable: active · cleared

text

Qwen3 235B A22B

Lab: Alibaba (Qwen)
Host: novita
Intelligence: —
Context: 41K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.80
Origin: CN
Routable: active · cleared

text

Qwen3 235B A22B Instruct 2507 FP8 Throughput

Lab: Alibaba (Qwen)
Host: together
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.20 / $0.60
Origin: CN
Routable: active · cleared

text

Qwen3 235B A22b Thinking 2507

Lab: Alibaba (Qwen)
Host: novita
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.30 / $3.00
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3 Coder 480B A35B Instruct Fp8

Lab: Alibaba (Qwen)
Host: together
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $2.00 / $2.00
Origin: CN
Routable: active · cleared

text
code

Qwen3 Coder Next Fp8

Lab: Alibaba (Qwen)
Host: together
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.50 / $1.20
Origin: CN
Routable: active · cleared

text
code

Qwen3 Next 80B A3b Thinking

Lab: Alibaba (Qwen)
Host: together
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.15 / $1.50
Origin: CN
Routable: active · cleared

text

Qwen3 Next 80B A3B Thinking

Lab: Alibaba (Qwen)
Host: novita
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.15 / $1.50
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3 Omni 30B A3B Thinking

Lab: Alibaba (Qwen)
Host: novita
Intelligence: —
Context: 66K
Modalities: text
Ref. in/out · 1M: $0.25 / $0.97
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3 VL 235B A22B Thinking

Lab: Alibaba (Qwen)
Host: novita
Intelligence: —
Context: 131K
Modalities: text
Ref. in/out · 1M: $0.98 / $3.95
Origin: CN
Routable: active · cleared

text
tool_use

Qwen3-14B

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: —
Context: 41K
Modalities: text
Ref. in/out · 1M: $0.12 / $0.24
Origin: CN
Routable: active · cleared

text

Qwen3-235B-A22B-Thinking-2507

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.23 / $2.30
Origin: CN
Routable: active · cleared

text

Qwen3-30B-A3B

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: —
Context: 41K
Modalities: text
Ref. in/out · 1M: $0.12 / $0.50
Origin: CN
Routable: active · cleared

text

Qwen3-32B

Lab: Alibaba (Qwen)
Host: deepinfra
Intelligence: —
Context: 41K
Modalities: text
Ref. in/out · 1M: $0.08 / $0.28
Origin: CN
Routable: active · cleared

text

Ring-2.6-1T

Lab: inclusionAI (Ling)
Host: novita
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.30 / $2.50
Origin: CN
Routable: active · cleared

text
tool_use

Sao10k L3 8B Lunaris

Lab: Sao10K
Host: novita
Intelligence: —
Context: 8K
Modalities: text
Ref. in/out · 1M: $0.05 / $0.05
Origin: —
Routable: active · cleared

text

Seed-1.8

Lab: ByteDance (Seed)
Host: deepinfra
Intelligence: —
Context: 256K
Modalities: text
Ref. in/out · 1M: $0.25 / $2.00
Origin: CN
Routable: active · cleared

text

Seed-2.0-code

Lab: ByteDance (Seed)
Host: deepinfra
Intelligence: —
Context: 256K
Modalities: text
Ref. in/out · 1M: $0.50 / $3.00
Origin: CN
Routable: active · cleared

text
code

Seed-2.0-mini

Lab: ByteDance (Seed)
Host: deepinfra
Intelligence: —
Context: 256K
Modalities: text
Ref. in/out · 1M: $0.10 / $0.40
Origin: CN
Routable: active · cleared

text

Seed-2.0-pro

Lab: ByteDance (Seed)
Host: deepinfra
Intelligence: —
Context: 256K
Modalities: text
Ref. in/out · 1M: $0.50 / $3.00
Origin: CN
Routable: active · cleared

text

Step-3.5-Flash

Lab: StepFun
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.09 / $0.30
Origin: CN
Routable: active · cleared

text

Step-3.7-Flash

Lab: StepFun
Host: deepinfra
Intelligence: —
Context: 262K
Modalities: text
Ref. in/out · 1M: $0.20 / $1.15
Origin: CN
Routable: active · cleared

text

Trinity Mini

Lab: Arcee AI
Host: together
Intelligence: —
Context: 128K
Modalities: text
Ref. in/out · 1M: $0.04 / $0.15
Origin: US
Routable: active · cleared

text

Wizardlm 2 8x22B

Lab: Microsoft (Phi)
Host: novita
Intelligence: —
Context: 66K
Modalities: text
Ref. in/out · 1M: $0.62 / $0.62
Origin: US
Routable: active · cleared

text

XiaomiMiMo/MiMo-V2.5

Lab: Xiaomi (MiMo)
Host: novita
Intelligence: —
Context: 1.0M
Modalities: text
Ref. in/out · 1M: $0.17 / $0.34
Origin: CN
Routable: active · cleared

text
tool_use

XiaomiMiMo/MiMo-V2.5-Pro

Lab: Xiaomi (MiMo)
Host: novita
Intelligence: —
Context: 1.0M
Modalities: text
Ref. in/out · 1M: $0.52 / $1.04
Origin: CN
Routable: active · cleared

text
tool_use

Intelligence © Artificial Analysis, external + weekly. Origin reflects the lab’s home jurisdiction. How a model gets picked per call — how routing works →