OpenRouter model catalogue
OpenRouter adds Mistral Pixtral Large 2502 model
Do:Review whether this model's capabilities and pricing fit your use case.
Show the reasoning — raw diff, triage verdict, confidence
+id: mistralai/pixtral-large-2502 +name: Mistral: Pixtral Large 2502 +pricing.prompt: 0.000002 +pricing.completion: 0.000006 +context_length: 128000 +top_provider.max_completion_tokens: 102400
| triage verdict | MATERIAL at 0.95, needed 0.5 |
|---|---|
| triage reasoning | New model entry with pricing and capability specs added to platform catalogue. |
| signals | new model added to catalogue · pricing.prompt: $0.000002/token · pricing.completion: $0.000006/token · context_length: 128000 tokens · max_completion_tokens: 102400 tokens |
| suppression | — |
| triage model | anthropic/claude-haiku-4.5 ($0.00000) |
| writer model | anthropic/claude-sonnet-4.5 ($0.00000) |
Mistral Small 3.2 24B pricing decreased on OpenRouter
Do:Review current usage of mistralai/mistral-small-3.2-24b-instruct: reforecast monthly costs using the new rates, and verify that no requests exceed the new 16,384 complet…
Show the reasoning — raw diff, triage verdict, confidence
id: mistralai/mistral-small-3.2-24b-instruct name: Mistral: Mistral Small 3.2 24B -pricing.prompt: 0.0000001 -pricing.completion: 0.0000003 +pricing.prompt: 0.000000075 +pricing.completion: 0.0000002 context_length: 256000 -top_provider.max_completion_tokens: 26214 +top_provider.max_completion_tokens: 16384
| triage verdict | MATERIAL at 0.95, needed 0.5 |
|---|---|
| triage reasoning | Pricing dropped on both prompt and completion; max output tokens reduced significantly. |
| signals | pricing.prompt decreased: $0.0000001/token → $0.000000075/token (-25%) · pricing.completion decreased: $0.0000003/token → $0.0000002/token (-33.3%) · top_provider.max_completion_tokens reduced: 26214 → 16384 tokens (-37.5%) |
| suppression | — |
| triage model | anthropic/claude-haiku-4.5 ($0.00000) |
| writer model | anthropic/claude-sonnet-4.5 ($0.00000) |
CORRECTED DeepSeek V4 Flash completion price cut 25%, prompt price up 12.5%
Original text (as first published, superseded)
CORRECTED DeepSeek V4 Flash 0731 completion price halved, prompt price up 69.5%
Original text (as first published, superseded)
CORRECTED DeepSeek V4 Flash prompt pricing increased 22% on OpenRouter
Original text (as first published, superseded)
CORRECTED DeepSeek V4 Flash 0731 prompt pricing tripled to $0.0154/M tokens
Original text (as first published, superseded)
CORRECTED DeepSeek V4 Flash 0731 prompt pricing dropped 55.7%
Original text (as first published, superseded)
CORRECTED DeepSeek V4 Flash 0731 prompt pricing drops 37% on OpenRouter
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek V4.1 Flash prompt pricing reduced 21.5% on OpenRouter
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek V4 Flash pricing dropped 90% on completion tokens
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek V4.1 Flash completion price up 36.6%, prompt price down 43.4%
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
ARITHMETIC NOTE DeepSeek V4 Pro pricing increased 163% on OpenRouter
[ARITHMETIC NOTE · WHY IT MATTERS] Original: “goes from $24.36 to $64.14.” Fact: For 10M prompt and 30M completion tokens/month, captured cost is $24.36 before and $64.11552 after, approximately $64.12, not $64.14.
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
ARITHMETIC NOTE DeepSeek V3.2 Exp pricing doubled on OpenRouter
[ARITHMETIC NOTE · WHAT CHANGED] Original: “Total cost per request increases 102-103% across all workload mixes.” Fact: Across all nonnegative fixed token mixes, the price increase ranges from prompt-only 100.9% to completion-only 103.4%. At one, three and ten completions per prompt, it is approximately 102.4%, 102.9% and 103.2%.
[ARITHMETIC NOTE · WHY IT MATTERS] Original: “goes from $7.39 to $15.13.” Fact: At 10M prompt and 30M completion tokens/month, captured cost goes from $7.392 to $15.00.
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek Flash Latest pricing and output limits changed
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek Flash Latest pricing increased 35-71% effective now
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek V4 Flash Vision pricing more than doubled
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek V3 prompt price down 19.6%, completion price up 15.6%
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek Pro Latest pricing cut 79%, max completion tokens reduced 58%
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek V4.1 Flash pricing increased 3x prompt, 2x completion
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek V4 Flash pricing reduced 7% prompt, 24% completion
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek Flash Latest: prompt pricing cut 53%, completion tokens capped at 384k
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek V4 Flash 0731 prompt pricing dropped 30%
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek V4 Flash pricing changed: prompt down 25%, completion up 31%
Original text (as first published, superseded)
CORRECTED DeepSeek Flash Latest pricing: prompt up 87.5%, completion down 38.8%
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek V4.1 Flash pricing increased 2-3x, output limit tripled
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek Flash Latest pricing: prompt down 20%, completion up 300%
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
ARITHMETIC NOTE DeepSeek V4.1 Flash pricing up 50% prompt, 20% completion; output limit cut 58%
[ARITHMETIC NOTE · WHY IT MATTERS] Original: “Monthly costs will increase proportionally for all usage” Fact: The cost increase depends on token mix: prompt +50%, completion +20%. The stated 1B prompt plus 200M completion token workload correctly rises from $200 to $270/month (+35%).
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek V4 Flash pricing: prompt up 26.7%, completion down 45%
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED NVIDIA Nemotron 3.5 Lightning: prompt price +14%, output limit cut 44%
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
ARITHMETIC NOTE DeepSeek Pro Latest: pricing cut, max completion tokens reduced 59%
[ARITHMETIC NOTE · triage.signals] Original: “prompt pricing decreased ~9.8%” Fact: Prompt pricing decreases 9.6731%, approximately 9.7%.
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED OpenAI gpt-oss-20b pricing cut 40% prompt, 31% completion; output capped at 32K tokens
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
Original text (as first published, superseded)
CORRECTED DeepSeek Pro Latest pricing increased 12% prompt, 72% completion
[ARITHMETIC NOTE · triage.signals] Original: “pricing.completion increased ~71.6%” Fact: Completion pricing increases 71.8508%, approximately 71.9%.
[ARITHMETIC NOTE · WHAT CHANGED] Original: “(+71.6%)” Fact: Completion pricing increases 71.8508%, approximately 71.9%.
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.